Performance modeling and optimization of a smart sensor-based Hydroponic system using PSO and Genetic algorithms Authors: Amit Kumar, Sujata Jadhav Published: 2026 ABSTRACT Ensuring continuous and stable functioning of automated hydroponic systems is the key of sustainable agriculture, especially in resource-scarce regions or urbanization. This study explores the growing need for reliable smart farming technology by improving the reliability and availability of a hydroponic system which consists of sensors, micro controllers, and water pumps. A stochastic modeling approach using a Continuous-Time Markov Chain (CTMC) framework is adopted to simulate different system states namely operational, degraded, failed. The Chapman-Kolmogorov differential equations are derived from various state transitions and solved using Laplace transformation along with supplementary variable technique. These equations provide time-dependent probabilities, which are used to estimate the reliability and availability of the system. Nature-inspired optimization algorithms namely Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), optimize system performance and minimize downtime. The PSO yielded the highest availability of 0.9737 with the variation in iterations. Concurrently, GA achieved the highest availability of 0.9753 with population size 85. The findings show that using stochastic modeling alongside optimization techniques like PSO and GA helps in better parameter tunability for optimal maintenance planning and to understand how the system will behave over time. Introduction In modern engineering and technology-based domains, reliability is an important performance criterion that determines the capacity of a system or component to operate under defined conditions for a specified duration. High reliability is required in systems where failure could lead to economic loss, safety risks, or system disruptions. As technology systems become more complex and automated, ensuring their reliability has become increasingly important–both when they are being designed and in use. One innovation that’s gained notable attention in recent years is the hydroponic farming system, a modern approach to agriculture that eliminates soil and relies on nutrient-rich water to grow plants efficiently. Hydroponics is a technique of growing plants without soil using water solutions of nutrients in a controlled environment. The technique has several advantages (Fig. 1) over traditional farming practices, including water conservation, accelerated growth rate, space-saving, and the ability to grow plants without arable land. With the growing stress on world food production because of population increase, urbanization, and climate change, hydroponics is being seen as a viable alternative to conventional agriculture. However, the effectiveness and scalability of hydroponic systems heavily depend on their operational reliability. Hydroponic systems are usually made up of integrated subsystems that include sensors, pumps, nutritional delivery systems, lighting, and communication modules, all of which should continue to run continuously and correctly. Failure of these components will interfere with the growing environment, causing plant stress, low yield, or total crop loss. Therefore, reliability assessment and optimization of hydroponic systems are crucial to provide stable performance, reduce downtime, and facilitate mass implementation. This research looks at those reliability concerns by developing practical mathematical models to understand system behaviour better and improve its availability and efficiency in real-world conditions. The study contributes to building robust, fault-tolerant agricultural technologies suitable for future food production challenges by incorporating reliability engineering principles into hydroponic design and maintenance. Reliability modeling and optimization have been key focus areas in engineering systems, especially for complex, multistate, and smart systems. Lisnianski et al.1 provided a foundational framework for multistate system reliability and its practical applications, which have been widely adopted in various industries. Building on this, Xing et al.2 developed a behavior-based modeling strategy aimed at intelligent systems, analyzing the dynamic reliability issues of importance to contemporary automated settings. At the same time, Ram et al.3 created a standby system reliability model considering cost elements and sensitivity analysis,thereby providing enlightened perspectives on cost-effective and efficient system operation. Kumar et al.4 identified the role of human failure in multistate systems, highlighting the way real operational uncertainties can possibly affect the overall performance of the systems.In a another research study, Yadav et al.5 utilized a Markov-based approach for evaluating the reliability, availability,and maintainability of a repairable system. Their findings portrayed the advantage of modeling state changes in achieving system performance in different operating conditions. Oszczypała et al.6 focused on redundancy optimization of k-out-of-n systems using continuous-time Markov chains and Monte Carlo simulation, a technique suitable for fault-tolerant design. Tyagi et al.7 extended this by applying sensitivity analysis to IoT-based systems, indicating the need for robust fault-tolerant designs. Pant et al.8 proposed an AHP-based multi-criteria decision-making approach to improve the monitoring of health management practices in smart healthcare systems.Their study focuses on selecting and prioritizing key parameters for effective monitoring to enhance decision-making accuracy and system performance. Jensen and Jerez9 conducted a hydraulic reliability and sensitivity analysis of large-scale water distribution networks under uncertainty. They used a Subset Simulation method based on Markov Chain Monte Carlo (MCMC) to handle high-dimensional reliability problems efficiently. Kumar et al.10 suggested a reliability-centered methodology for an automated robotic arm system closely related to aspects of hydroponic automation and control. Rawal et al.11 discussed the availability of internet data centers for various maintenance policies with an emphasis on the significance of maintenance policies in attaining the maximum overall system uptime. Silva et al.12 recognized the pressing need to quantify reliability and availability in Wireless Sensor Networks (WSNs), specifically in industrial settings where a system error could have severe consequences. The authors focused on the impact of permanent faults in network devices, which can disrupt communication and compromise control systems. Chopra13 analyzed food industry systems with seasonal demand patterns, revealing the effect of variable usage on system reliability. Kumar and Kumar14 applied the Markov decision process to assess public address system reliability, suggesting its adaptability to smart monitoring systems. The study15 evaluated system behavior by distinguishing between user-induced failures and manufacturing defects, determining warranty coverage. Kumar et al.16 presented a detailed reliability analysis of Wireless Sensor Networks (WSNs) using a continuous-time Markov process. The results offer valuable guidance for designing more reliable and fault-tolerant WSNs, especially for agriculture, healthcare, and environmental monitoring applications. Despite significant advancements in reliability and sensitivity analysis across various sectors, the agricultural field–particularly in the context of wireless sensor networks remains relatively underexplored. Thakur et al.17 provided a broad review of wireless sensor networks in precision agriculture, identifying gaps in reliability-focused research. Catelani et al.18 highlighted the importance of reliability in wireless sensor networks (WSNs) in smart agriculture. They called for secure data transmission and guaranteed reliable power supply to ensure efficiency in operational performance in real-world agricultural applications. Zhang et al.19 optimized the maintenance cost and reliability of wind-photovoltaic hybrid systems, providing a framework for balancing cost and performance. Kumar et al.20 conducted a comprehensive RAMD (Reliability, Availability, Maintainability, and Dependability) analysis of Tube-wells Integrated with Underground Pipelines (TIUP), recognizing their vital role in agricultural irrigation systems. Using a Markov-based stochastic model, supported by FMEA, the study estimated the steady-state availability of the system. The authors21 developed a stochastic modeling framework to optimize condition-based maintenance policies for solar farms operating under variable environmental conditions. The study focused on performance degradation caused by dust accumulation and temperature rise, using a non-homogeneous compound Poisson process to model dust effects and a Markov chain to represent environmental co-variates like wind and rain. Parallelly, with the rise of precision agriculture, hydroponic systems have become increasingly relevant. Several studies have demonstrated the potential of IoT in improving the monitoring and control of hydroponic systems. Marques et al.22 developed an advanced hydroponic setup using IoT, incorporating sensors to monitor key environmental conditions essential for healthy plant growth. Sneineh and Shabaneh23 implemented a smart hydroponics system powered by an ESP32 micro-controller, allowing real-time tracking of parameters like pH, electrical conductivity (EC), and water levels. Tatas et al.24 highlighted the importance of dependable IoT-based monitoring and control, showing how wireless communication modules can enhance automation and quickly respond to system faults. Lakshmi et al.25 and Suresh et al.26 both contributed to developing IoT-based hydroponic systems, underlining how sensor integration enhances resource efficiency in indoor farming. From an optimization perspective, Particle Swarm Optimization (PSO) and hybrid algorithms have been applied successfully to improve system reliability and maintenance scheduling in various industrial setups. Dahiya and Garg27 addressed the Redundancy Allocation Problem (RAP), a key reliability optimization challenge in complex systems, by applying both Genetic Algorithm (GA) and a Hybrid Genetic–Particle Swarm Optimization (H-GAPSO) approach. Noting the limitations of using standalone algorithms, the authors developed a hybrid method that combines the exploratory strength of GA with the fast convergence of PSO. Chen et al.28 focused on enhancing the reliability and redundancy design of satellite communication systems, which are vital for continuous global connectivity. The authors modeled the system using a Markov Bayesian Network and a non-working reserve strategy to evaluate system reliability in a harsh space environment. Jagtap et al.29 applied Particle Swarm Optimization (PSO) to optimize the availability of thermal power plant subsystems, demonstrating the effectiveness of metaheuristic algorithms in maintenance scheduling. The authors30 emphasized the growing need for computational intelligence in optimizing complex systems like hydroelectric power plants. The authors developed a stochastic model with constant failure and repair rates for all subsystems to address the limitations of traditional optimization methods. They applied various nature-inspired algorithms–such as Grey Wolf, Dragonfly, Grasshopper, and Whale Optimization–to evaluate and optimize system availability. Bhandari et al.31 proposed a cost-reliability optimization model for a solar seed sowing machine, while Saini et al.32 optimized the availability of a reverse osmosis system using metaheuristic algorithms–both relevant to water-based systems like hydroponics. Abdullah and Hassan33 compared GA and PSO for reliability allocation, highlighting their suitability for complex system design. Ghorbani et al.34 optimized the sizing of an off-grid PV/wind/battery system using hybrid GA-PSO and MOPSO algorithms. Aiming to minimize total cost while ensuring a reliable power supply, the study used LPSP as the reliability metric and compared the results with those of HOMER software. Jagtap et al.35 evaluated the availability of a thermal power plant’s turbo-generator subsystem using Markov modeling and Particle Swarm Optimization (PSO). Key subsystems like turbine lubrication and generator excitation were identified as most critical to overall availability. Bhandari et al.36 proposed a hybrid GWO-PSO (HPSGWO) algorithm to solve the cold-standby reliability redundancy allocation problem (RRAP), a complex challenge in system design. The model also accounts for imperfect switching in active-to-standby transitions, capturing a pragmatic detail that is usually overlooked. Ouyang et al.37 improved the PSO algorithm to solve reliability-redundancy allocation with mixed strategies, offering a more flexible and efficient modeling tool for complex systems. The authors Ala et al.38 have utilized artificial intelligence approaches along with optimization strategies to enhance data handling, decision-making, and overall performance of the smart healthcare application system. The suggested hybrid approach can be very useful in enhancing the process of monitoring and managing patient health information.Liu et al.39 presented an optimized pH-sensing framework for precision farming using IoT-based networks. Their study focuses on making pH monitoring in agriculture more accurate and efficient.These studies mainly focus on improving monitoring systems, sensing accuracy, and data handling in engineering and agricultural applications. However, less attention has been given to the reliability and availability analysis of smart hydroponic systems using stochastic modeling and optimization techniques such as CTMC, PSO, and GA. A substantial body of metaheuristic literature exists on various industrial systems’ reliability and availability assessment. Numerous researchers have employed nature-inspired algorithms for reliability allocation and availability optimization. However, only a limited number of studies have focused on hydroponic systems and the integration of IoT in such applications. Despite their growing importance, smart hydroponic systems remain underexplored, particularly from the perspective of reliability modeling and availability enhancement. There is a clear research gap in combining stochastic modeling techniques with optimization algorithms to assess and improve the performance of sensor-based hydroponic setups. The paper aims to address that gap by analyzing the reliability of a hydroponic system using Markov processes and optimizing its availability through Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The study contributes toward building more dependable and automated agricultural solutions, supporting the advancement of precision farming technologies. The structure of this research study is organized as follows: “Mathematical preliminaries” section presents the mathematical preliminaries; “System description” section describes the system components and parameter notations; “Mathematical modeling of hydroponic system and methodological framework” section details the mathematical modeling of the hydroponic system and the solution of governing equations; “Behavioral study of the hydroponic system” section provides the behavioral study, including availability and reliability evaluation as well as optimization using PSO and GA; “Conclusion” section concludes the study, and “Future scope” section outlines potential future work.Fig. 1Advantages of the hydroponic system. Advantages of the hydroponic system. Mathematical preliminaries In engineering systems, availability is a key indicator of how reliably a system can keep running over time. Understanding and estimating availability helps ensure smooth operation and plays a vital role in planning maintenance activities–both to prevent issues and to fix them quickly–so that downtime is reduced and the system stays dependable. Over the years, researchers have adopted various techniques–such as fault tree analysis, maximum likelihood estimation, and fuzzy logic-based approaches–to analyze and predict system reliability and associated performance indicators.Among these methods, Markov decision processes (MDPs) have proven especially useful for modeling the operational behavior of both industrial and networked systems. These models allow us to examine how systems transition between different operational states, such as operational, partially operational, or degraded, and completely failed, based on the conditions of their components. The Markov process, named after Russian mathematician Andrei Markov, is a stochastic process–a mathematical framework for modeling random systems that evolve over time. What makes the Markov process unique is its memoryless property: the future state of the system depends solely on its current state, not on the sequence of events that preceded it. In formal terms, while general stochastic processes consider the whole history of prior states, Markov processes rely only on the present state to determine future outcomes.This characteristic makes Markov models particularly suitable for analyzing complex systems where components fail and are repaired over time and where specific failure and repair rates can define state transitions. In a continuous-time Markov chain (CTMC), each state corresponds to a distinct configuration of the system, typically characterized by the operational status of its components. These transitions are usually modeled using exponential distributions , which simplifies the mathematical analysis and reflects the random nature of real-world failures.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \begin{aligned} P[X_{t+s}=k \mid X_s= j, X_u= m,0\le u\le s] \\ =P[X_{t+s}= k\mid X_s= j] \end{aligned} \end{aligned}$$\end{document} If the conditional probability \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P[X_ {t+s}= k\mid X_s= j]$$\end{document} remains unchanged regardless of the value of s; then the process is said to be time-homogeneous. In such cases, the transition probabilities depend only on the time difference t, not on the specific time s. This implies that the Markov process has stationary transition probabilities, a key feature of time-homogeneous Markov chains.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & P_{jk}\left( t\right) = P[X_ {t+s}= k\mid X_s= j] \nonumber \\ & P_k(t)=P[X_t=j] \end{aligned}$$\end{document}Here, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{jk}(t)$$\end{document} denotes the probability that the Markov chain moves from state j to state k, and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_k(t)$$\end{document} represents the probability that the system is in state k at a given time t. Thus \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{jk}(t)$$\end{document} are transition probability functions which represent the likelihood that the process,initially in state j, will be in state k after a time interval t. These probabilities satisfy the condition:\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \sum _{k}{P_{jk}}(t)=1, \forall t\ge 0,\forall j\in S \end{aligned}$$\end{document}where S denotes the set of all possible system states.2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & P_{jk}(t+s)= \sum _k P[X_{t+s}=k, X_t =m \mid X_0=j] \nonumber \\ & =\sum _m\frac{ P[X_0=j, X_t=m, X_{t+s}=k]}{P[X_0=j]} \nonumber \\ & =\sum _m\frac{P[X_0=j, X_t =m]}{P[X_0=j]}*\frac{ P[X_0=j, X_t =m, X_{t+s}=k]}{P[X_0=j, X_t =m]} \nonumber \\ & =\sum _m P[X_t =m\mid X_0=j]*{P[X_{t+s}=k)\mid X_0=j, X_t =m]} \nonumber \\ & =\sum _m P[X_t =m\mid X_0=j]*{P[X_{t+s}=k\mid X_t =m]} \nonumber \\ & P_{jk}(t+s)= \sum _m P_{jm}(t) P_{mk}(s) \end{aligned}$$\end{document} Equation (2) represents the Kolmogorov equations, which are fundamental to CTMC-based modeling as they establish a mathematical relationship between the system’s structure defined by its states and transitions and its dynamic behavior. By solving these equations numerically or analytically, one can evaluate the performance and reliability metrics of hydroponic systems under various operating conditions. System description The hydroponic system used in the research is a soilless culture system that allows accurate environmental control to maximize plant growth. The system comprises various working units like sensors, a micro-controller, pumps, and a communication module with feasible monitoring, control, and data transmission. Sensors: The pH sensor monitors the acidity or alkalinity of the nutrient solution, which is critical for the uptake of nutrients by plants. Maintaining the correct pH range ensures plant health and maximizes nutrient absorption. The Total Dissolved Solids (TDS) or Electrical Conductivity (EC) sensor measures the concentration of nutrients in the water. It helps determine whether the nutrient levels are optimal for plant growth. This sensor detects the water level in the reservoir to prevent the pump from running and automating the refilling process when necessary. The temperature sensor keeps track of changes in heat within the system and provides real-time feedback to help control the temperature of the nutrient solution and maintain the right environment for healthy plant growth. Micro-controller: The system’s central control unit is a micro-controller (e.g., ESP32 or Arduino). It collects real-time data from all connected sensors and processes it to make decisions. Based on the sensor inputs, the micro-controller controls the operation of pumps and triggers alerts if any parameter exceeds safe thresholds. Water pump: A water pump circulates the nutrient solution to the plant roots, maintaining proper hydration. A nutrient dosing pump or set of peristaltic pumps automatically adds nutrients or pH adjustment solutions based on sensor readings. These pumps provide steady nutrient delivery without human intervention. Communication module: For remote monitoring and control, the system has a communication module that sends real-time information to a mobile application or cloud server so that users can monitor parameters like pH, EC, and water level. It also facilitates sending alerts or control signals remotely in case of abnormalities. The integration of automated sensing, intelligent control, and real-time communication makes the system very efficient, minimizing the use of manual labour while increasing the reliability and yield of crops. It is crucial that the reliable working of every device is ensured because failure in any component, particularly sensors, pumps, or the controller, can negatively impact the whole process of growing. The block diagram (Fig.2) is an illustration of the entire architecture of the hydroponic system, illustrating the primary components and their interactions.Fig. 2Configuration and flow of the hydroponic system. Configuration and flow of the hydroponic system. System parameters and notations The terminology represented in Table 1 has been used to describe the failure and repair rates of the hydroponic system. Table 2 presents the notations and parameter definitions used to represent the state transition probabilities in the evaluation of various reliability metrics.Table 1Description of various failure and repair rates.ParameterExplanation\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document}Failure rate of the micro-controller.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}$$\end{document}/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}$$\end{document}Failure rate of the communication module/sensors.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document}/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document}Failure rate of the water pump 1 and 2.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document}Repair rate of the failure in micro-controller.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document}/ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document}Repair rate of communication module and sensors.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document}/ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document}Repair rate of the failure in water pump 1 and 2.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{1}$$\end{document}Repair rate when water pump 1, water pump 2, and sensors fail simultaneously.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _2$$\end{document}Repair rate when water pump 1 and micro-controller fail simultaneously.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _3$$\end{document}Repair rate when Sensors and micro-controller fail simultaneously.Table 2Terminology and mathematical representation of different state’s probability.NotationDescriptiont/sTime-Frequency variables.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_i$$\end{document}(t)Probability that the system is in the ith state at time t.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_i$$\end{document} (x,t)Probability that the system is in ith failed state at time t,considering variable x.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_0$$\end{document} (t)System operating in normal (good ) condition.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_1$$\end{document} (t)Degraded system state caused by water pump 1 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_2$$\end{document} (x,t)System in failed state due to water pump 2 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_3$$\end{document} (x,t)System in failed state due to communication module failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_4$$\end{document} (x,t)System in failed state due to micro-controller failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_5$$\end{document} (t)Degraded system state caused by sensor 1 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_6$$\end{document} (t)Degraded system state caused by sensor 2 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_7$$\end{document} (t)Degraded system state caused by sensor 3 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_8$$\end{document} (x,t)System in failed state due to all sensors failure..\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_9$$\end{document} (t)Degraded system state caused by water pump 1 sensor failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{10}$$\end{document} (x,t)System enters a failed state due to the failure of Water Pump 2, following the prior failure of Water Pump 1 and the sensor.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{11}$$\end{document} (x,t)System enters a failed state due to the failure of micro-controller, following the prior failure of Water Pump 1 and the sensor.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{12}$$\end{document} (x,t)System enters a failed state due to the failure of micro-controller, following the prior failure of the sensors. Table 1Description of various failure and repair rates.ParameterExplanation\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document}Failure rate of the micro-controller.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}$$\end{document}/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}$$\end{document}Failure rate of the communication module/sensors.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document}/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document}Failure rate of the water pump 1 and 2.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document}Repair rate of the failure in micro-controller.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document}/ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document}Repair rate of communication module and sensors.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document}/ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document}Repair rate of the failure in water pump 1 and 2.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{1}$$\end{document}Repair rate when water pump 1, water pump 2, and sensors fail simultaneously.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _2$$\end{document}Repair rate when water pump 1 and micro-controller fail simultaneously.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _3$$\end{document}Repair rate when Sensors and micro-controller fail simultaneously. Description of various failure and repair rates. Table 2Terminology and mathematical representation of different state’s probability.NotationDescriptiont/sTime-Frequency variables.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_i$$\end{document}(t)Probability that the system is in the ith state at time t.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_i$$\end{document} (x,t)Probability that the system is in ith failed state at time t,considering variable x.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_0$$\end{document} (t)System operating in normal (good ) condition.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_1$$\end{document} (t)Degraded system state caused by water pump 1 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_2$$\end{document} (x,t)System in failed state due to water pump 2 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_3$$\end{document} (x,t)System in failed state due to communication module failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_4$$\end{document} (x,t)System in failed state due to micro-controller failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_5$$\end{document} (t)Degraded system state caused by sensor 1 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_6$$\end{document} (t)Degraded system state caused by sensor 2 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_7$$\end{document} (t)Degraded system state caused by sensor 3 failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_8$$\end{document} (x,t)System in failed state due to all sensors failure..\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_9$$\end{document} (t)Degraded system state caused by water pump 1 sensor failure.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{10}$$\end{document} (x,t)System enters a failed state due to the failure of Water Pump 2, following the prior failure of Water Pump 1 and the sensor.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{11}$$\end{document} (x,t)System enters a failed state due to the failure of micro-controller, following the prior failure of Water Pump 1 and the sensor.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{12}$$\end{document} (x,t)System enters a failed state due to the failure of micro-controller, following the prior failure of the sensors. Terminology and mathematical representation of different state’s probability. Mathematical modeling of hydroponic system and methodological framework In a hydroponic system, key components such as water pumps, pH and EC sensors, micro-controllers, and communication module can exist in either an operational or failed state. The system’s overall condition depends on the combined status of these components. A Markov-based modeling approach analyzes the system’s behavior over time. This model describes the system as a set of states, with transitions occurring due to component failures or repairs. The transition from one state to another is governed by failure rates (λ) and repair rates (η), which are commonly assumed to follow an exponential distribution. This assumption simplifies the modeling process and aligns with the memoryless nature of real-world failure and repair events. A state transition diagram is developed to illustrate how the system moves between operational, degraded, and failed conditions. Each arrow in the diagram corresponds to a possible transition due to a component failure or a successful repair. The notations used in the diagram are detailed in Tables 1, 2 , and the whole transition map is shown in Fig. 3.Fig. 3Transition state diagram of hydroponic system. Transition state diagram of hydroponic system. Based on this diagram, differential equations are formulated using the Chapman-Kolmogorov framework to capture the probabilities of the system being in each state over time. Solving these equations enables the estimation of steady-state probabilities, which are further used to calculate the overall availability of the hydroponic system. This availability measure is the objective function in the subsequent optimization phase to improve system reliability and performance. By considering the system’s transition at time (t, t + Δ t) and allowing Δ t to approach zero, a set of differential equations governing the system’s dynamics can be derived.3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \begin{aligned} P_0 (t+\Delta t) = (1-\lambda _{mc}\Delta t)(1-\lambda _{c}\Delta t)(1-\lambda _s\Delta t)(1-\lambda _{p_1}\Delta t)P_0(t)\\ +\eta _{{p}_{1}} P_1(t)\Delta t +\eta _s P_5(t)\Delta t +\sum _{i,j}{\int _{0}^{\infty }{\eta _{i}P_{j}(x,t)\ \Delta t dx}}&\end{aligned} \nonumber \\ & \begin{aligned} \frac{P_0 (t+\Delta t)-P_0(t)}{\Delta t}+(\lambda _{mc}+\lambda _{c}+\lambda _{s}+\lambda _{p_{1}})P_0(t)=\eta _{{p}_{1}} P_1(t)\\ +\eta _s P_5(t) +\sum _{i,j}{\int _{0}^{\infty }{\eta _{i}P_{j}(x,t)\ dx}}&\end{aligned} \nonumber \\ & \begin{aligned} \lim _{\Delta t \rightarrow 0} \frac{P_0 (t+\Delta t)-P_0(t)}{\Delta t}+(\lambda _{mc}+\lambda _{c}+\lambda _{s}+\lambda _{p_{1}})P_0(t)=\eta _{{p}_{1}} P_1(t)\\ +\eta _s P_5(t) +\sum _{i,j}{\int _{0}^{\infty }{\eta _{i}P_{j}(x,t)\ dx}}&\end{aligned} \nonumber \\ & \begin{aligned} (\frac{d}{dt}+\lambda _{mc}+\lambda _{c}+\lambda _{s}+\lambda _{p_{1}})P_{0}(t)=\eta _{{p}_{1}} P_1(t) +\eta _s P_5(t) +\sum _{i,j}{\int _{0}^{\infty }{\eta _{i}P_{j}(x,t)\ dx}} \end{aligned} \end{aligned}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \text{ Where } i&= \ c\ ,\ mc\ ,\ p\ ,\ s\ ,\ 1\ ,\ 2\ ,\ 3\\ j&=3\ ,\ 4\ ,\ 2\ ,\ 8\ ,\ 10\ ,\ 11\ ,\ 12 \end{aligned}$$\end{document}Additionally, the differential equations for the partially operational state (degraded state) and completely failed states are derived as follows: For Degraded State: 4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \left( \frac{d}{dt}+\eta _{{p}_1}+\lambda _{{p}_2}+\lambda _s\right) P_1\left( t\right) =\lambda _{{p}_1}P_0\left( t\right) +\eta _s{\ P}_9\left( t\right) \end{aligned}$$\end{document} 5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \left( \frac{d}{dt}+\eta _s+\lambda _{mc}+\lambda _s+\lambda _{{p}_1}\right) P_5\left( t\right) =\lambda _s{\ P}_0\left( t\right) +\eta _{p_1}\ P_9\left( t\right) \ +\eta _{s}P_6\left( t\right) \end{aligned}$$\end{document} 6\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \left( \frac{d}{dt}+\eta _s+\lambda _{mc}+\lambda _s+\lambda _{{p}_1}\right) P_6\left( t\right) =\lambda _s{\ P}_5\left( t\right) +\eta _s P_7\left( t\right) +\eta _{p_1}\ P_9\left( t\right) \end{aligned}$$\end{document} 7\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \left( \frac{d}{dt}+\eta _s+\lambda _{mc}+\lambda _s+\lambda _{{p}_1}\right) P_7\left( t\right) =\lambda _s{\ P}_6\left( t\right) +\eta _{p_1}\ P_9\left( t\right) \end{aligned}$$\end{document} 8\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \left( \frac{d}{dt}+\eta _s+3\eta _{p_1}+\lambda _{mc}+\lambda _{{p}_2}\right) P_9\left( t\right) =\lambda _s{\ P}_1\left( t\right) +\lambda _{p_1}(\ P_5\left( t\right) +\ P_6\left( t\right) +\ P_7\left( t\right) ) \end{aligned}$$\end{document} For Failed State:9\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \left( \frac{\partial }{\partial t}\ +\frac{\partial }{\partial x}\ +\eta _i\right) \ P_j\left( x,t\right) \ =\ 0 \end{aligned}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \text{ Where } i&= \ c\ ,\ mc\ ,\ p\ ,\ s\ ,\ 1\ ,\ 2\ ,\ 3\\ j&=3\ ,\ 4\ ,\ 2\ ,\ 8\ ,\ 10\ ,\ 11\ ,\ 12 \end{aligned}$$\end{document}Initial and boundary conditions:10\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & P_i(t) = \left\{ \begin{array}{lr} 1, & \text {if } i=0, t=0\\ 0, & \text {otherwise } \end{array} \right. \end{aligned}$$\end{document}11\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & P_m(0,t)=\lambda _n P_l(t) \end{aligned}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \text{ Where } \textit{m}&=2,3,4,8,10,11 \\ \textit{n}&=p_2,c,mc,s,p_2,mc \\&\textit{l}= 1,0,0, 7,9,9 \end{aligned}$$\end{document}12\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} P_{12}(0,t)=\lambda _{mc} (P_5(t)+P_6(t)+P_7(t)) \end{aligned}$$\end{document}Now, the derived Chapman-Kolmogorov differential equations (3)-(8) are solved using the Laplace transform and the supplementary variable technique, along with the specified initial and boundary conditions. The resulting expressions provide the probabilities of different system states, as shown below.13\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_0}(s)=\frac{A_1}{\left[ {\begin{matrix}A_1(K_1- S_2)- \lambda _{p_1} (A_2\ S_1 - \lambda _s A_6\ {S}_5)\\ - \lambda _{s}(A_3\ S_3 -A_5 S_4)+ \frac{\eta _3 \lambda _{mc} \lambda _{s} A_4}{s+\eta _3}\end{matrix}}\right] } \end{aligned}$$\end{document}14\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_1}(s)=\frac{\lambda _{\textrm{p}_1}A_2}{A_1} \overline{P_0}(s) \end{aligned}$$\end{document}15\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_5}(s)=\frac{\lambda _{\textrm{s}}A_3}{A_1} \overline{P_0}(s) \end{aligned}$$\end{document}16\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_6}(s)=-\frac{\lambda _{\textrm{s}}A_4}{A_1} \overline{P_0}(s) \end{aligned}$$\end{document}17\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_7}(s)=-\frac{\lambda _{\textrm{s}}A_5}{A_1} \overline{P_0}(s) \end{aligned}$$\end{document}18\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P_9}(s)= -\frac{\lambda _{\textrm{p}_1}\lambda _\textrm{s}A_6}{A_1} \overline{P_0}(s) \end{aligned}$$\end{document}where,\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & S_1=\eta _{\textit{p}_{1}}+\frac{\eta _{p} \lambda _{p_2}}{s+\eta _{p}} \\ & S_2=\frac{\eta _{c} \lambda _{c}}{s+\eta _{c}}+\frac{\eta _{mc} \lambda _{mc}}{s+\eta _{mc}} \\ & S_3=\eta _{s}+\frac{\eta _{3} \lambda _{mc}}{s+\eta _{mc}} \\ & S_4=\frac{\eta _{s} \lambda _{s}}{s+\eta _{s}}+\frac{\eta _{3} \lambda _{mc}}{s+\eta _{3}} \\ & S_5=\frac{\eta _{1} \lambda _{p_2}}{s+\eta _{1}}+\frac{\eta _{2} \lambda _{mc}}{s+\eta _{2}} \\ & \begin{aligned} A_1= k_{2} k_{3}^{3}(3\lambda _{p_1} \eta _{p_1}- k_{4} ) + 2 k_{2} k_{3} (k_{4} \lambda _{s} \eta _{s}+ \lambda _{s} \lambda _{p_{1}} \eta _{p_{1}}+\lambda _{p_{1}} \eta _{s} \eta _{p_{1}})\\ +k_{2} \lambda _{s}^{2} \lambda _{p_{1}} \eta _{p_{1}}-2 k_{2} \lambda _{s} \lambda _{p_{1}} \eta _{s} \eta _{p_{1}}+k_{2} \lambda _{p_{1}} \eta _{s}^{2} \eta _{p_{1}}+k_{3}^{3} \lambda _{s} \eta _{s}-2 k_{3} \lambda _{s}^{2} \eta _{s}^{2} \end{aligned} \\ & \begin{aligned} A_2= k_{3}^{3} k_{4}-k_{3}^{2} \lambda _{s} \eta _{s}+3 k_{3}^{2} \lambda _{p_{1}} \eta _{p_{1}}+2 k_{3} k_{4} \lambda _{s} \eta _{s} -k_{3} \lambda _{s}^{2} \eta _{s}+2 k_{3} \lambda _{s} \lambda _{p_{1}} \eta _{p_{1}} \\ +2 k_{3} \lambda _{p_{1}} \eta _{s} \eta _{p_{1}}-\lambda _{s}^{3} \eta _{s}+\lambda _{s}^{2} \lambda _{p_{1}} \eta _{p_{1}}+\lambda _{s}^{2} \eta _{s}^{2}-2 \lambda _{s} \lambda _{p_{1}} \eta _{s} \eta _{p_{1}}+\lambda _{p_{1}} \eta _{s}^{2} \eta _{p_{1}} \end{aligned} \\ & \begin{aligned} A_3= k_{2} k_{3}^{2} k_{4}+2 k_{2} k_{3} \lambda _{p_{1}} \eta _{p_{1}}+k_{2} k_{4} \lambda _{s} \eta _{s}+k_{2} \lambda _{p_{1}} \eta _{p_{1}}(\lambda _{s}+ \eta _{s})\\ +k_{3}^{2} (\lambda _{s} \eta _{s} - \lambda _{p_{1}} \eta _{p_{1}}) -k_{3} \lambda _{p_{1}} \eta _{s} \eta _{p_{1}}-\lambda _{s}^{2} \eta _{s}^{2}+\lambda _{s} \lambda _{p_{1}} \eta _{s} \mu _{p_{1}}-\lambda _{p_{1}} \eta _{s}^{2} \eta _{p_{1}} \end{aligned} \\ & \begin{aligned} A_4=k_{2} k_{3} (k_{4} \lambda _{s}+ \lambda _{p_{1}} \eta _{p_{1}})-k_{2} \lambda _{p_{1}} \eta _{p_{1}}(\lambda _{s}- \eta _{s}) \\ +k_{3}^{2} \lambda _{p_{1}} \eta _{p_{1}} -k_{3} \lambda _{s}^{2} \eta _{s}+k_{3} \lambda _{p_{1}} \eta _{p_{1}}(\lambda _{s}+ \eta _{s}) \end{aligned} \\ & \begin{aligned} A_5=k_{2} k_{3} \lambda _{p_{1}} \eta _{p_{1}}+k_{2} k_{4} \lambda _{s}^{2}+k_{3}^{2} \lambda _{p_{1}} \eta _{p_{1}} + \lambda _{s} \lambda _{p_{1}} \eta _{p_{1}}\\ (2 k_{2}+k_{3})-\lambda _{s}^{3} \eta _{s}+\lambda _{s} \lambda _{p_{1}} \eta _{p_{1}}(\lambda _{s}- \eta _{s}) \end{aligned} \\ & \begin{aligned} A_6=k_{2} k_{3}^{2}+k_{2} k_{3} \lambda _{s}+k_{2} \lambda _{s}^{2}-k_{2} \lambda _{s} \eta _{s}+k_{3}^{3}-2 k_{3} \lambda _{s} \eta _{s} \end{aligned} \\ & k_1=s+\lambda _{\textit{mc}}+\lambda _{c}+\lambda _{s}+\lambda _{p_{1}} \\ & k_2=s+\eta _{p_{1}}+\lambda _{p_{2}}+\lambda _{s} \\ & k_3=s+\eta _{s}+\lambda _{p_{1}}+\lambda _{s}+\lambda _{\textit{mc}} \\ & k_4=s+\eta _{s}+3\eta _{p_{1}}+\lambda _\textit{mc}+\lambda _{p_{2}} \end{aligned}$$\end{document} The transformed equations associated with the failed states are solved in a similar manner by considering the corresponding transition and repair terms. The obtained state probability expressions are then used to evaluate the system’s downstate probability. After determining the probability of each system state, the overall availability (upstate) and unavailability (downstate) probabilities at time t can be easily calculated. The upstate probability refers to the combined probability of all states where the system is either fully operational or operating in a degraded condition. In contrast, the downstate probability represents the total probability of all states in which the system has completely failed.19\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \overline{P}_{upstate}(s)=\overline{P}_0(s)+\overline{P}_1(s)+\overline{P}_5(s)+\overline{P}_6(s)+\overline{P}_7(s)+\overline{P}_9(s) \end{aligned}$$\end{document}20\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & \begin{aligned} \overline{P}_{downstate}(s)=&\sum _{i=2,3,4,8, 10,11,12}\overline{P}_i(x,s) \\ \end{aligned} \end{aligned}$$\end{document} Behavioral study of the hydroponic system Availability analysis of hydroponic system using Markov modeling Availability is about how reliably a system performs when needed,factoring in how long it runs and how often maintenance is required.It is the likelihood that a system is working efficiently without failure throughout its intended operating time, particularly in automated systems such as hydroponics.To calculate the time-dependent availability of the hydroponic system, the numerical values of failure and repair rates (Tyagi et al.7; Kumar et al.16) for each component are substituted into the derived Eq. (19). Using failure rates as \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}= 0.031$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}= 0.021$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}= 0.025$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{\textit{p}_{1}}= 0.002$$\end{document},\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{\textit{p}_{2}}= 0.002$$\end{document} and assuming all repair rates to be 1, the system’s availability function is determined, as shown in Eq. 21. This function helps estimate the probability that the system remains operational over time, supporting preventive maintenance planning and enhancing overall system reliability.21\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \begin{aligned} Av(t)= 1.598921\times 10^{-8} {\mathrm e}^{- 4.042924 t}+ 0.000451 {\mathrm e}^{- 1.282171 t}+ 0.014532 {\mathrm e}^{- 1.094728 t}\\ + 0.0349761 {\mathrm e}^{- 1.042985 t}- 0.000381 {\mathrm e}^{- 1.017551 t}- 0.000696 {\mathrm e}^{- 0.832639 t}+ 0.951117 \end{aligned} \end{aligned}$$\end{document}By varying the time parameter from t = 0 to t = 10 in Eq. (21), the system availability can be calculated. The graphical representation of availability curve is shown in Fig. 4.Fig. 4Availability curve of the hydroponic system over time. Availability curve of the hydroponic system over time. Reliability analysis of hydroponic system using Markov modeling Reliability is the probability that a system or component operates without failure over a given time and under specified conditions. It reflects the consistency and dependability of the system during operation. The reliability of the hydroponic system is calculated by setting all repair rates to zero and using the specified failure rates as \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}= 0.031$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}= 0.021$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}= 0.025$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{\textit{p}_{1}}= 0.002$$\end{document},\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{\textit{p}_{2}}= 0.002$$\end{document} in Eq. (22). The resulting reliability expression is given below,22\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} \begin{aligned} R(t)= 0.814451 {\mathrm e}^{- 0.079 t}+ 0.0769231 {\mathrm e}^{- 0.053 t} \sinh \! \left( 0.026 t\right) + 2.380952 \\ {\mathrm e}^{- 0.0685 t} \sinh \! \left( 0.0105 t\right) - 0.050725 {\mathrm e}^{- 0.033 t}+ 0.160256 {\mathrm e}^{- 0.027 t}\\ + 3.374365\times 10^{-8} {\mathrm e}^{- 0.058 t} \left( 10143.0 t^{2}- 225120.0 t+ 2.252800\times 10^{6}\right) \end{aligned} \end{aligned}$$\end{document} Figure 5 graphically illustrates the decline in reliability over time, highlighting how the system’s performance degrades without any repair interventions.Fig. 5Reliability curve of the hydroponic system over time. Reliability curve of the hydroponic system over time. Availability optimization using nature inspired algorithms Nature-inspired algorithms are used to optimize the performance and reduce the downtime of the hydroponic system. Techniques like Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and their hybrid forms help find the best possible values for failure and repair rates that lead to higher system availability. These algorithms mimic natural processes–such as animal swarming or biological evolution–to smartly explore and identify the most effective combinations. The availability function, developed using the Markov model, is the main target to guide this optimization. Availability optimization of hydroponic system using Particle Swarm Optimization (PSO) Particle Swarm Optimization (PSO) is a population based stochastic optimization technique that Kennedy and Eberhart initially introduced. The collective movement and intelligence of bird flocks or fish schools inspire the PSO algorithm. Each individual in the swarm called a particle, represents a possible solution within the overall search space.The position and velocity of each swarm are updated iteratively based on two key components: The particle’s own best-known position (personal best, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(P_{best})$$\end{document}). The global best position \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(g_{best})$$\end{document} discovered by the swarm. The particle’s own best-known position (personal best, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(P_{best})$$\end{document}). The particle’s own best-known position (personal best, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(P_{best})$$\end{document}). The global best position \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(g_{best})$$\end{document} discovered by the swarm. The global best position \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(g_{best})$$\end{document} discovered by the swarm. The particles converge toward the optimal solution by striking a balance between exploration (searching new areas) and exploitation (refining known good areas). PSO is simple to implement and effective for continuous nonlinear optimization problems. Let \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$s_i(t)$$\end{document} be the position of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$i^{th}$$\end{document} particle at time t in search space.The equations below define how the velocity and position of each particle are updated at the next iteration \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${t+1}$$\end{document}. These updates guide the movement of particles within the search space based on their current state and previous performance.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\begin{aligned} & v_i\left( t+1\right) =\omega v_i\left( t\right) +c_1\left( P_{best}\left( t\right) -s_i\left( t\right) \right) +c_2\left( g_{best}\left( t\right) -s_i\left( t\right) \right) \\ & s_i\left( t+1\right) =s_i\left( t\right) +v_i\left( t+1\right) \end{aligned}$$\end{document}Where \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$c_{1}$$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$c_{2}$$\end{document} are the acceleration coefficients,ω is the inertia coefficient and v represents velocity vector. This study focuses on optimizing the availability of a hydroponic system using Particle Swarm Optimization (PSO). For the analysis, specific constraints are applied by setting upper and lower limits for system components’ failure and repair rates (Table 3). The PSO pseudo code and its corresponding flowchart are depicted in Figs. 6 and 7 for a better understanding of the algorithmic process.Table 3Prescribed range of failure and repair rates of hydroponic system.Failure ratesRepair rates\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} ε (0.01 - 0.04)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} ε (0.1 - 0.3)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}$$\end{document} ε (0.015 - 0.03)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{c}$$\end{document} ε (0.3 - 0.6)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}$$\end{document} ε (0.015 - 0.035)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{s}$$\end{document} ε (0.3 - 0.5)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} ε (0.001 - 0.003)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} ε (0.25 - 0.35)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} ε (0.001 - 0.003)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} ε (0.25 - 0.35) Table 3Prescribed range of failure and repair rates of hydroponic system.Failure ratesRepair rates\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} ε (0.01 - 0.04)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} ε (0.1 - 0.3)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{c}$$\end{document} ε (0.015 - 0.03)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{c}$$\end{document} ε (0.3 - 0.6)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{s}$$\end{document} ε (0.015 - 0.035)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{s}$$\end{document} ε (0.3 - 0.5)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} ε (0.001 - 0.003)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} ε (0.25 - 0.35)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} ε (0.001 - 0.003)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} ε (0.25 - 0.35) Prescribed range of failure and repair rates of hydroponic system. Fig. 6Pseudo code of the PSO algorithm. Fig. 7Flow chart representation of the PSO process. Table 4Optimized availability values for varying population sizes using PSO.Pop. size816243240485664 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03460.01350.01620.03040.03470.03770.01630.0157 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02940.02520.02160.02640.01630.02070.01760.0158 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02340.02490.02180.02020.03040.02490.02620.0262 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00240.00260.00280.00290.00280.00230.00180.0023 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00160.00200.00170.00110.00280.00120.00160.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.18780.13470.12250.23450.10990.10440.17890.2155 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.51280.41170.31780.57990.47470.36880.46250.3353 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.49190.43330.47860.35110.49520.33480.43270.3093 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.33910.26560.26610.34120.33560.25130.28590.3257 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.33140.33240.34360.2860.33280.30670.31330.2543Ava.0.94750.96860.96710.95440.95570.94860.97190.9730 Pseudo code of the PSO algorithm. Flow chart representation of the PSO process. Table 4Optimized availability values for varying population sizes using PSO.Pop. size816243240485664 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03460.01350.01620.03040.03470.03770.01630.0157 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02940.02520.02160.02640.01630.02070.01760.0158 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02340.02490.02180.02020.03040.02490.02620.0262 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00240.00260.00280.00290.00280.00230.00180.0023 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00160.00200.00170.00110.00280.00120.00160.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.18780.13470.12250.23450.10990.10440.17890.2155 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.51280.41170.31780.57990.47470.36880.46250.3353 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.49190.43330.47860.35110.49520.33480.43270.3093 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.33910.26560.26610.34120.33560.25130.28590.3257 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.33140.33240.34360.2860.33280.30670.31330.2543Ava.0.94750.96860.96710.95440.95570.94860.97190.9730 Optimized availability values for varying population sizes using PSO. Fig. 8Impact of population size on availability optimization using PSO. Table 5Availability optimization results across different no, of iterations.Iter.3691215182124 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.01810.01820.03090.01200.03810.03940.01220.0183 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02080.02260.02530.02730.02560.02500.02040.0251 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02790.02080.02140.02620.02840.01810.02700.0225 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00160.00170.00150.00190.00180.00200.00250.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00130.00240.00130.00110.00260.00250.00220.0020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.12550.16660.12530.29850.15870.26850.11430.2798 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.43170.46960.44320.39370.38870.57860.58230.4565 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.31390.46080.30720.49700.33370.44120.34200.3452 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.30550.28100.29500.33140.29430.29710.25850.3248 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document} 0.32100.27530.26280.25940.27680.32480.27610.2893Ava.0.96700.96610.95210.96800.94570.94850.97370.9650 Impact of population size on availability optimization using PSO. Table 5Availability optimization results across different no, of iterations.Iter.3691215182124 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.01810.01820.03090.01200.03810.03940.01220.0183 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02080.02260.02530.02730.02560.02500.02040.0251 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02790.02080.02140.02620.02840.01810.02700.0225 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00160.00170.00150.00190.00180.00200.00250.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00130.00240.00130.00110.00260.00250.00220.0020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.12550.16660.12530.29850.15870.26850.11430.2798 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.43170.46960.44320.39370.38870.57860.58230.4565 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.31390.46080.30720.49700.33370.44120.34200.3452 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.30550.28100.29500.33140.29430.29710.25850.3248 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document} 0.32100.27530.26280.25940.27680.32480.27610.2893Ava.0.96700.96610.95210.96800.94570.94850.97370.9650 Availability optimization results across different no, of iterations. Fig. 9Effect of iterations on availability optimization using PSO. Effect of iterations on availability optimization using PSO. The results of the PSO-based optimization for the hydroponic system are illustrated in Tables 4, 5. The table displays the optimized availability values obtained by varying the population size and the number of iterations used in the algorithm. Each combination reflects how the Particle Swarm Optimization (PSO) algorithm explores the solution space to maximize system availability.In the experiments,the PSO algorithm starts with a set of initial suggested solutions, and each particle is a possible combination of the failure and repair rates in a solution space.As the process continues, each particle updates its values by learning from both its past performance and the success of other particles in the group.The goal is to find the best possible availability value based on the Markov-derived availability function. The accompanying Figs. 8, 9 graphically show the impact of increasing population size and iterations on the system’s availability. Increasing these parameters significantly improves results, but after a point, the improvement levels off–indicating convergence. This visualization helps select optimal algorithm settings for balancing computational effort and optimization quality.Together, these results demonstrate how the PSO algorithm effectively tunes the failure and repair parameters to maximize the availability of the hydroponic system under the given constraints. Availability optimization of hydroponic system using Genetic Algorithm (GA) Genetic Algorithms (GA) are metaheuristic search methods based on natural selection and genetics principles.GA regulates on a population of potential solutions encoded as chromosomes. Through several generations, it applies the following operators:Selection (based on fitness ): Choosing the fittest individuals based on an objective (fitness) function.Crossover (recombination): Combining parts of two parents to create new off spring (solutions).Mutation (random variation) : Introducing small random changes to maintain diversity and avoid premature convergence.GA is particularly effective in handling complex search spaces, discrete optimization problems, and problems with multiple local optima. The fitness function evaluates and assigns a score to every chromosome in the population. Genetic algorithms are based on biologically inspired operations like selection, crossover, and mutation. Under selection, chromosomes with greater fitness values are given greater chances of being selected into the next generation.The crossover operation involves selecting a random point (locus) in the chromosome and swapping segments between two parent chromosomes to generate new offspring. In mutation, specific bits within a chromosome are randomly changed based on a defined probability. However, in recent years, advancements in genetic algorithm components–such as operators, chromosome representation, and fitness evaluation–have slowed down.To provide a better understanding, the pseudo code (Fig. 10) and flowchart (Fig. 11) of the Genetic Algorithm are included below, illustrating the main steps and process flow clearly.Fig. 10Pseudo code of the genetic algorithm.Fig. 11Flow Chart representation of the GA process.Table 6Optimized availability values for varying population sizes using GA.Generations=200,Mutation=0.2,Crossover=0.72,iterations=70Pop. size102540557085100115\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document}0.03960.03610.03190.01500.01820.01300.01150.0222\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document}0.01790.01860.01900.01860.01760.01610.02240.0294\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document}0.01600.02490.02770.01740.01710.03300.01990.0215\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document}0.00270.00180.00210.00230.00160.00190.00260.0017\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document}0.00210.00200.00270.00140.00210.00130.00130.0025\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document}0.21670.16300.29110.17030.28150.22520.13980.1206\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document}0.31320.59720.52930.34530.31680.32960.58370.5916\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document}0.35310.34270.31300.32810.39890.30020.46250.4273\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document}0.31250.30420.30020.28630.31920.25270.31710.3309\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document}0.31390.31120.33930.31680.31710.28550.31030.2943Ava.0.95150.95420.95750.97110.96860.97530.97290.9583 Selection (based on fitness ): Choosing the fittest individuals based on an objective (fitness) function. Selection (based on fitness ): Choosing the fittest individuals based on an objective (fitness) function. Crossover (recombination): Combining parts of two parents to create new off spring (solutions). Crossover (recombination): Combining parts of two parents to create new off spring (solutions). Mutation (random variation) : Introducing small random changes to maintain diversity and avoid premature convergence. Mutation (random variation) : Introducing small random changes to maintain diversity and avoid premature convergence. Pseudo code of the genetic algorithm. Flow Chart representation of the GA process. Table 6Optimized availability values for varying population sizes using GA.Generations=200,Mutation=0.2,Crossover=0.72,iterations=70Pop. size102540557085100115\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document}0.03960.03610.03190.01500.01820.01300.01150.0222\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document}0.01790.01860.01900.01860.01760.01610.02240.0294\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document}0.01600.02490.02770.01740.01710.03300.01990.0215\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document}0.00270.00180.00210.00230.00160.00190.00260.0017\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document}0.00210.00200.00270.00140.00210.00130.00130.0025\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document}0.21670.16300.29110.17030.28150.22520.13980.1206\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document}0.31320.59720.52930.34530.31680.32960.58370.5916\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document}0.35310.34270.31300.32810.39890.30020.46250.4273\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document}0.31250.30420.30020.28630.31920.25270.31710.3309\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document}0.31390.31120.33930.31680.31710.28550.31030.2943Ava.0.95150.95420.95750.97110.96860.97530.97290.9583 Optimized availability values for varying population sizes using GA. Fig. 12Effect of population size on availability optimization with GA. Table 7Optimized availability values for varying generations using GA.Population size=50, Mutation=0.2, Crossover=0.72, iterations=70Gen4080120160200240280320 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03050.01740.01440.01240.01670.01320.02880.0280 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.01960.02560.02550.02860.01910.02450.01930.0270 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.01600.02490.02770.01740.01710.03300.01990.0215 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00270.00120.00190.00240.00240.00110.00150.0020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00290.00280.00280.00210.00260.00290.00260.0024 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.27630.17290.12350.22380.15670.20820.17080.2327 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.52570.31080.32310.45850.53530.40570.52720.3677 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.40600.48270.46430.34540.48600.35990.36060.4512 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.31080.32690.33600.33940.32590.34620.33010.2895 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document} 0.26320.31740.26640.32140.34660.33620.28190.2912Ava.0.95930.96560.96680.97050.96880.96880.95980.9541 Effect of population size on availability optimization with GA. Table 7Optimized availability values for varying generations using GA.Population size=50, Mutation=0.2, Crossover=0.72, iterations=70Gen4080120160200240280320 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03050.01740.01440.01240.01670.01320.02880.0280 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.01960.02560.02550.02860.01910.02450.01930.0270 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.01600.02490.02770.01740.01710.03300.01990.0215 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00270.00120.00190.00240.00240.00110.00150.0020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00290.00280.00280.00210.00260.00290.00260.0024 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.27630.17290.12350.22380.15670.20820.17080.2327 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.52570.31080.32310.45850.53530.40570.52720.3677 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.40600.48270.46430.34540.48600.35990.36060.4512 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.31080.32690.33600.33940.32590.34620.33010.2895 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _p$$\end{document} 0.26320.31740.26640.32140.34660.33620.28190.2912Ava.0.95930.96560.96680.97050.96880.96880.95980.9541 Optimized availability values for varying generations using GA. Fig. 13Effect of generation count on availability optimization with GA. Table 8Optimized availability values for varying crossover rates using GA.Population size=50,Mutation=0.2,Generations=200,iterations=70C-R0.650.690.730.770.810.850.890.93 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03130.02390.01980.02270.03780.01360.03780.0199 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02390.01560.02120.02040.02190.01990.02190.0209 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02070.02670.02060.02230.01800.03170.02050.0262 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00290.00230.00240.00260.00240.00210.00270.0021 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00230.00200.00150.00100.00290.00100.00290.0024 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.23150.20160.15990.11100.10070.12390.10280.2271 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.46230.35110.33520.47130.37050.43390.38880.5020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.39540.34220.36290.32020.45550.34600.44870.4624 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.26240.30690.31800.28710.26810.26690.33270.3073 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.26990.32680.34920.34240.28610.33490.34990.3380Ava.0.95440.96600.95290.96330.94760.97180.94780.9667 Effect of generation count on availability optimization with GA. Table 8Optimized availability values for varying crossover rates using GA.Population size=50,Mutation=0.2,Generations=200,iterations=70C-R0.650.690.730.770.810.850.890.93 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03130.02390.01980.02270.03780.01360.03780.0199 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02390.01560.02120.02040.02190.01990.02190.0209 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02070.02670.02060.02230.01800.03170.02050.0262 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00290.00230.00240.00260.00240.00210.00270.0021 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00230.00200.00150.00100.00290.00100.00290.0024 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.23150.20160.15990.11100.10070.12390.10280.2271 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.46230.35110.33520.47130.37050.43390.38880.5020 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.39540.34220.36290.32020.45550.34600.44870.4624 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.26240.30690.31800.28710.26810.26690.33270.3073 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.26990.32680.34920.34240.28610.33490.34990.3380Ava.0.95440.96600.95290.96330.94760.97180.94780.9667 Optimized availability values for varying crossover rates using GA. Fig. 14Effect of crossover rate on availability optimization with GA. Table 9Optimized availability values for varying mutation count using GA.Pop. size=50, Crossover rate =0.72,Generations=200,iterations=70M0.0050.0250.0450.0650.0850.1050.1250.145 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03970.01700.02580.01800.03420.01170.03130.0394 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02430.02330.02500.02750.01710.02220.01870.0219 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02130.03120.02260.02140.02660.02070.02700.0268 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00160.00110.00300.00200.00230.00120.00120.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00230.00110.00120.00110.00170.00130.00190.0010 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.19950.19040.11330.26810.17240.27930.17500.1084 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.48420.41650.50250.43070.53520.30920.38240.4936 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.36110.38110.48850.36710.36750.32570.38250.4029 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.29620.26820.27680.25570.29510.28790.29110.2805 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.29540.28840.26850.30830.34390.30130.31950.2957Ava.0.94650.96660.95730.96710.95670.97270.95710.9473 Effect of crossover rate on availability optimization with GA. Table 9Optimized availability values for varying mutation count using GA.Pop. size=50, Crossover rate =0.72,Generations=200,iterations=70M0.0050.0250.0450.0650.0850.1050.1250.145 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{mc}$$\end{document} 0.03970.01700.02580.01800.03420.01170.03130.0394 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _c$$\end{document} 0.02430.02330.02500.02750.01710.02220.01870.0219 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _s$$\end{document} 0.02130.03120.02260.02140.02660.02070.02700.0268 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_1}$$\end{document} 0.00160.00110.00300.00200.00230.00120.00120.0019 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _{p_2}$$\end{document} 0.00230.00110.00120.00110.00170.00130.00190.0010 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{mc}$$\end{document} 0.19950.19040.11330.26810.17240.27930.17500.1084 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _c$$\end{document} 0.48420.41650.50250.43070.53520.30920.38240.4936 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _s$$\end{document} 0.36110.38110.48850.36710.36750.32570.38250.4029 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p_1}$$\end{document} 0.29620.26820.27680.25570.29510.28790.29110.2805 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\eta _{p}$$\end{document} 0.29540.28840.26850.30830.34390.30130.31950.2957Ava.0.94650.96660.95730.96710.95670.97270.95710.9473 Optimized availability values for varying mutation count using GA. Fig. 15Effect of mutation count on availability optimization with GA.. Effect of mutation count on availability optimization with GA.. The presented tables and corresponding figures illustrate how system availability responds to changes in key Genetic Algorithm parameters, including population size, number of generations, crossover rates, and mutation count. The effect on the availability outcome is clearly observed by varying these parameters across multiple experimental runs. Table 6/Fig. 12 shows how population size affects availability. As the number of individuals in the population increases, the algorithm becomes more capable of exploring a diverse solution space. The best result was achieved at a population size of 85, yielding the highest availability of 0.9753. Table 7/Fig. 13 illustrates the impact of the number of generations on availability. More generations allow the algorithm to evolve better solutions over time. An optimal availability of 0.9705 was obtained at 160 generations, after which the improvement became marginal. Table 8/Fig. 14 evaluates the role of the crossover rate. The best-performing rate was 0.85, which gave an availability of 0.9718. Higher crossover rates beyond this point slightly disturbed the convergence and reduced availability. Table 9/Fig. 15 explores how mutation rate influences the system. A mutation rate of 0.105 resulted in the availability of 0.9727, highlighting its effectiveness in maintaining diversity and preventing premature convergence. The results for the comparison in availability of values for the parameters used by PSO and GA are presented in Fig. 16 below. As depicted in the figure, both PSO and GA methods are effective at improving the availability of the hydroponics system. Nonetheless, GA produced slightly better values than PSO.Fig. 16Comparison of PSO and GA availability results.. Comparison of PSO and GA availability results.. Conclusion This research investigated an innovative hydroponic system’s reliability and availability modeling using a Markov-based model with added nature-inspired optimization methods. The analysis employed different failure and repair rates of the main components like sensors, micro controllers, and water pumps. Time-dependent availability and reliability were computed, where the availability becomes steady at 0.9511 after time t = 5, whereas the reliability dips gradually with time, reaching about 0.6128 at t = 10. The availability obtained from the CTMC model represents the baseline performance of the hydroponic system using the initially selected failure and repair rates. The PSO and GA optimization techniques further search for improved combinations of these parameters within the prescribed solution space. Therefore, the optimized availability values obtained through Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are higher than the baseline Markov availability. Through the PSO algorithm, a maximum availability of 0.9737 was reached after 21 iterations, and the highest availability reached through population variation was 0.9730. In the Genetic Algorithm (GA) analysis, various parameters–population size, generations, crossover rate, and mutation rate–were adjusted to find the best setup for maximizing the availability of the hydroponic system.The highest availability, 0.9753, was achieved with a population size of 85. Availability increased with population size up to 85 but did not improve much beyond that. Similarly, 160 generations produced a strong availability of 0.9705, balancing search depth and convergence. Availability is more stable at medium crossover values, and the highest availability (0.9718) is achieved at a crossover rate of 0.85. This shows that choosing a balanced crossover rate works better than using very small or very large values. In the same way, the mutation rate also affects availability. Moderate mutation rates give better performance, while very low or very high mutation rates reduce availability. The best result (0.9727) is obtained near a mutation rate of 0.105, suggesting that a balanced mutation rate helps explore new solutions without disturbing good ones too much. Overall, careful tuning of GA parameters significantly improved the system’s availability, proving GA to be an effective tool for optimizing performance in automated hydroponic systems. In conclusion, the study underlines the effectiveness of the combination of stochastic models and swarm optimization techniques to enhance the consistency, reliability, and availability of automated hydroponic systems. The findings are essential in designing more reliable systems and designing maintenance policies. By avoiding unexpected operational disruptions, the approach boosts the resilience of systems and enhances agricultural production. Future scope Future research can focus on integrating real-time sensor data for dynamic reliability modeling. It can also explore hybrid algorithms like PSO-GA for better optimization and apply machine learning for predicting failures. Expanding the model to large-scale hydroponic networks and including cost, energy, and security aspects will improve system strength and practical use.