传感技术学报2017，Vol.30Issue(8)：1267-1273,7.DOI:10.3969/j.issn.1004-1699.2017.08.023
一种基于时空相关性和异常检测的改进WSN节能策略
An Improved WSN Energy Saving Strategy Based on Spatio-TemporalCorrelation and Anomaly Detection
摘要
Abstract
In order to reduce the contradiction between the network energy consumption and the accuracy of the data,we consider the spatial and temporal correlation of the data collected by the network and propose an method of adaptive sampling and using compressed sensing.Wireless sensor data compression based on the traditional compressed sensing only sampling data of a few nodes and the incidents detected by those not sampled nodes maybe be ignored.This paper detect all nodes'' data and compress,so it can effectively avoid failure report.According to the characteristics of time correlation,this paper adopts adaptive sampling frequency method based on variance analysis ANOVA(Analysis of Variance)and take nodes'' residual energy into consideration to reduce the smooth signal acquisition and equilibrium the energy consumption of network.On the basis of LEACH protocol,the data of cluster is compressed and transmitted to the Sink node to reduce the overall energy consumption of the network.In order to reduce the failure report caused by the adaptive sampling and traditional compressed sensing method,an improved local event monitoring algorithm sliding window local event monitoring SW-LED(Sliding Window-Local Event Detection)algorithm is proposed,which realizes real-time and accurate anomaly detection and early warning.The experimental results show that this method can effectively balance the nodes'' energy consumption to improve the network lifetime,ensuring the accuracy of the data and the recognition rate of abnormal situation is also greatly improved.关键词
无线传感网/时空相关性/SW-LED/ANOVA/压缩感知/异常检测Key words
wireless sensor network/spatio-temporal correlation/SW-LED/ANOVA/anomaly identification分类
信息技术与安全科学引用本文复制引用
万叶晶,叶继华,江爱文..一种基于时空相关性和异常检测的改进WSN节能策略[J].传感技术学报,2017,30(8):1267-1273,7.基金项目
国家自然科学基金项目(61462042,61365002) （61462042,61365002）
江西师范大学研究生创新基金项目(YJS2016086) （YJS2016086）
