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

作　　者：马玉洁 MA Yujie(School of Computer Engineering,Anhui Wenda Information Engineering College,Hefei 231201,China)

机构地区：[1]安徽文达信息工程学院计算机工程学院,安徽合肥231201

出　　处：《佛山科学技术学院学报(自然科学版)》2025年第1期41-47,共7页Journal of Foshan University(Natural Science Edition)

基　　金：安徽文达信息工程学院重点科研项目(XZR2023A12)。

摘　　要：针对无线传感器网络(WSN)在数据传输过程中的稳定性和可靠性问题,提出了一种基于路径质量和联邦学习的新型路由机制。该机制综合考量了信号强度、时延和数据包丢失率等关键指标,并通过联邦学习算法实现了设备间的数据隐私保护和全局模型的协同训练。实验结果表明,新型路由机制在数据传输成功率上达到95.8%,节点平均能耗降至2.0 J,网络寿命最多延长至320轮次,显著优于传统路由机制。此外,引入的节点能量平衡策略进一步优化了能耗分布,为WSN的长期稳定运行提供了保障。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 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]