佛山科学技术学院学报（自然科学版）2025，Vol.43Issue(1)：41-47,7.
基于路径质量和联邦学习的WSN数据传输效能研究
Research on WSN for IoT device collaboration based on path quality and federated learning
摘要
Abstract
This study proposes a novel routing mechanism based on path quality and federated learning to address the stability and reliability issues of wireless sensor networks(WSN)during data transmission.This mechanism comprehensively considers key indicators such as signal strength,latency,and packet loss rate,and achieves data privacy protection between devices and collaborative training of global models through federated learning algorithms.The experimental results show that the new routing mechanism achieves a success rate of 95.8%in data transmission,reduces the average energy consumption of nodes to 2.0 joules,and extends the network lifetime to a maximum of 320 rounds,significantly better than traditional routing mechanisms.In addition,the introduced node energy balance strategy further optimizes the energy consumption distribution,providing a guarantee for the long-term stable operation of WSN.关键词
无线传感器网络/路由机制/路径质量/联邦学习/数据传输效能Key words
wireless sensor network/routing mechanism/path quality/federated learning/data transmission efficiency分类
信息技术与安全科学引用本文复制引用
马玉洁..基于路径质量和联邦学习的WSN数据传输效能研究[J].佛山科学技术学院学报（自然科学版）,2025,43(1):41-47,7.基金项目
安徽文达信息工程学院重点科研项目(XZR2023A12) （XZR2023A12）
