基于数据驱动的无线传感器网络拥塞控制  

Congestion control of wireless sensor networks based on data driving

作　　者：杨美艳[1] YANG Mei-yan(College of Artificial Intelligence,Tianjin University of Science&Technology,Tianjin 300457,China)

机构地区：[1]天津科技大学人工智能学院,天津300457

出　　处：《沈阳工业大学学报》2022年第5期570-574,共5页Journal of Shenyang University of Technology

基　　金：国家自然科学基金项目(61976156).

摘　　要：为解决当前无线传感器网络拥塞问题,加快数据传输速度,提出基于数据驱动的无线传感器网络拥塞控制方法.通过传输节点被动监察附近节点传输的数据帧,量化节点活跃度判断附近节点是否存在拥塞问题,基于离散指数趋近率控制的抖振分析结果设计自适应离散滑模拥塞控制器,针对存在拥塞问题的节点,采用数据驱动技术根据节点间关联性设计无线传感器网络拥塞控制策略.测试结果表明,相比传统的控制方法,本文方法能降低节点内数据队列长度的波动性,提升单位时间内数据传输量,节点信道拥塞标记率具有一致性,控制在4.5%左右,其响应时间控制在100 ms左右,具有良好的控制性能.In order to solve the current congestion problem of wireless sensor networks and speed up data transmission,a congestion control method for wireless sensor networks based on data driving was proposed.Data frames transmitted by nearby nodes were passively supervised,the activity of nodes was quantified to determine whether there were congestion problems in nearby nodes,and an adaptive discrete sliding mode congestion controller was designed according to the chattering analysis results,which was controlled by discrete exponential convergence rate.A data driving technology was used to design a control strategy for wireless sensor network congestion based on the relevance among nodes.The test results show that the as-proposed method can reduce the fluctuation of data queue length within nodes and improve the data transmission per unit time,compared with traditional control methods.The mark rates of node channel congestion are consistent and controlled at about 4.5%,and its response time is controlled at about 100 ms,showing favorable control performance.

关 键 词：数据驱动 无线传感器网络 网络拥塞控制 被动监察 节点关联性 数据帧 队列长度 拥塞控制器 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]