A resource-efficient machine learning framework for real-time non-intrusive load monitoring and performance optimization in solar-powered aviation systems
Aguida Mohammed Echarif, Yanbo Che, El Moundher Aouiche, Abdrabbi Bourezg, Muhammad Zain Yousaf, Wajid Khan, Mohit Bajaj, Oleksandr Rubanenko · 2025
Read A resource-efficient machine learning framework for real-time non-intrusive load monitoring and performance optimization in solar-powered aviation systems by Aguida Mohammed Echarif, Yanbo Che, El Moundher Aouiche, Abdrabbi Bourezg, Muhammad Zain Yousaf, Wajid Khan, Mohit Bajaj, Oleksandr Rubanenko (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12795806.txt.
Description
Aguida Mohammed Echarif and co-authors build, in twenty twenty-five, a resource-light machine learning framework for real-time load monitoring in solar-powered aviation. Non-intrusive load monitoring infers which devices draw power from one aggregate signal. Aircraft impose strict limits on weight, latency, and compute. The team evaluated six learning models on high-rate power data, sampled two hundred thousand times per second. The data captured transients and steady states across all flight phases. Smoothing and downsampling cut noise while keeping key features.
A nearest neighbor model gave the best balance of accuracy and cost, with a score near zero point nine four and a run time of a fifth of a second. A hybrid neural model had the lowest error but took over four minutes, suiting offline analysis.
Catalog record
| CREATOR | Aguida Mohammed Echarif, Yanbo Che, El Moundher Aouiche, Abdrabbi Bourezg, Muhammad Zain Yousaf, Wajid Khan, Mohit Bajaj, Oleksandr Rubanenko |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |