FRLTC: A new topology control algorithm using federated reinforcement learning for software-defined wireless sensor network in IoT

Le Huu Binh, Thuy-Van T. Duong, Duc Huy Le · 2026

Read FRLTC: A new topology control algorithm using federated reinforcement learning for software-defined wireless sensor network in IoT by Le Huu Binh, Thuy-Van T. Duong, Duc Huy Le (2026) 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/plos-pone-0355604.txt.

Description

Le Huu Binh, Thuy-Van Duong, and Duc Huy Le present a learning-based method for organizing wireless sensor networks in this 2026 paper. In software-defined sensor networks for the Internet of Things, each node's radio range shapes the whole network's energy use and reliability. The goal is for every node to end up with a sensible number of neighbors. Their algorithm lets each node adjust its own range using reinforcement learning. A second learning model at the central controller picks which node learns next. The nodes share lessons without sharing raw data.

In simulations, the federated approach hit the target neighbor counts more accurately than well-known topology control algorithms, while also using less energy and delivering better transmission quality. The authors argue that splitting learning between nodes and controller suits networks too large and too privacy-sensitive for purely central control.

Catalog record

CREATORLe Huu Binh, Thuy-Van T. Duong, Duc Huy Le
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE48547
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355604

Browse the full library · About the Tower of Babel