基于分布式压缩感知的无线传感器网络异常数据处理

Data Abnormality Processing in Wireless Sensor Networks Based on Distributed Compressed Sensing

无线传感器网络的海量数据采集、传输和处理,对传感器节点的处理能力和功耗提出了严峻挑战,而且现实环境中传感器故障或者环境因素的突变会导致部分采集数据异常,而传统的数据处理方法无法对包含异常的数据进行有效的处理。针对上述问题,文中提出了两类无线传感器网络的异常数据模型,以及相应的基于分布式压缩感知的异常数据处理方法。通过协同的多个传感器进行数据压缩采样,当多个传感器采集的数据包含异常成分时,分布式压缩感知技术对数据中相同的正常分量进行一次统一重构,仅对不同的异常分量进行单独重构,从而避免了对相同数据分量的重复处理,提高了对包含异常成分数据处理的效率。另外,分布式压缩感知技术充分利用数据间的相关性,可有效减少传感器网络的数据采集量,加强其对抗异常数据的鲁棒性。对两类异常数据模型的数值仿真结果表明:相比于传统的基于单组测量值的压缩感知技术,基于分布式压缩感知技术的数据处理方法在提高异常数据重构准确率的同时,将采样数据量减少了约33%,证明了该方法的有效性。

In wireless sensor networks,massive data acquisition,transmission and processing not only pose severe challenges to the processing ability and power consumption of sensors,but also suffer data anomalies frequently due to sensor failures or sudden changes of environmental factors,which cannot be effectively dealt with by traditional data processing methods.Regarding the problems above,this paper proposed two kinds of data abnormality models and corresponding processing method based on distri-buted compressed sensing(DSC)for wireless sensor networks.When the data collected by multiple sensors contains abnormal components,the DCS reconstructs the same normal component of data only once and the different abnormal components individual-ly,which avoids the repeated processing of the same normal component and improves the processing efficiency of the data containing abnormal components.In addition,DCS makes full use of the correlation of data,which can effectively reduce the amount of data acquisition and enhance the robustness against data anomalies.Numerical simulation results of two kinds of data abnormality models show that compared with the traditional compressed sensing based on single set of measurement,the data processing method based on DCS improves the accuracy of abnormal data reconstruction and reduces the amount of data by about 33%,which proves the effectiveness of the proposed method.