一种基于时空相关性和异常检测的改进WSN节能策略

发布时间：2018-05-30 12:06

本文选题：无线传感网 + 时空相关性　；参考：《传感技术学报》2017年08期

【摘要】：针对降低无线传感网能耗和保证数据精度之间的矛盾,提出了自适应采样数据并利用压缩感知进行压缩的方法。传统的基于压缩感知的无线传感器数据压缩,只采样部分节点的数据,对于未被采样节点感知到的突发事件很有可能发生漏检情况。本文方法检测所有节点上传的数据再进行压缩,可以有效避免漏检情况的发生。根据信号具有时间相关性的特点,本文采用基于方差分析ANOVA(Analysis of Variance)原理改进的传感器自适应采样频率方法,并考虑节点剩余能量,减少平稳信号的采集次数,均衡网络节点能耗。在LEACH协议基础上,对簇内数据进行压缩感知的方法对数据进行压缩从而减少数据的空间相关性并传输到汇聚节点,以减少网络整体的能量消耗。针对可能的漏报情况,提出一种改进的局部事件监测算法—滑动窗口局部事件监测SW-LED(Sliding Window-Local Event Detection)算法,实现了实时准确的异常检测和预警。实验结果表明本文方法既可以有效的均衡网络节点能耗以提高网络生存周期,同时保证了数据的精度,对于异常情况的识别率也有很大的提高。
[Abstract]:Aiming at the contradiction between reducing the energy consumption of wireless sensor network and ensuring the precision of the data, an adaptive data sampling method is proposed and compression sensing is used to compress the data. Traditional wireless sensor data compression based on compressed sensing only samples the data of some nodes. It is very possible to miss detection for unexpected events which are not perceived by the sampled nodes. In this paper, the data uploaded by all nodes are detected and compressed, which can effectively avoid the occurrence of missed detection. According to the time dependence of the signal, an adaptive sampling frequency method based on the ANOVA(Analysis of Variance principle is proposed in this paper. Considering the residual energy of the sensor, the acquisition frequency of stationary signal is reduced, and the energy consumption of the network node is equalized. Based on the LEACH protocol, the data is compressed and sensed to reduce the spatial correlation of the data and transmit to the convergent node to reduce the energy consumption of the network as a whole. An improved local event monitoring algorithm, sliding window Local event Monitoring (SW-LED(Sliding Window-Local Event Detection) algorithm, is proposed to realize real-time and accurate anomaly detection and early warning. The experimental results show that the proposed method can effectively balance the energy consumption of network nodes to improve the network lifetime, ensure the accuracy of the data, and improve the recognition rate of abnormal cases.
【作者单位】：江西师范大学计算机信息工程学院;
【基金】：国家自然科学基金项目(61462042,61365002) 江西师范大学研究生创新基金项目(YJS2016086)
【分类号】：TN929.5;TP212.9

【相似文献】