基于时间序列数据的无线传感器网络的异常检测方法

伴随着无线传感器网络的发展和广泛应用,针对传感器网络在恶劣环境下传感器之间采样值差异大以及随着无线传感器网络故障节点增多导致事件检测不准确的问题,提出一种基于传感器网络时间序列数据的检测方法.利用传感器采集的K个正常数据的中位数建立枢轴量,构造置信区间,提出一种计算数据区间差异度的方法以判断发生异常的来源.实验结果表明,本文方法对传感器网络的异常数据检测率保持在98%以上,误报率保持在0.5%以下,具有一定的实用性.

Anomaly detection method for wireless sensor networks based on time series data

With the development and widespread application of wireless sensor networks,focusing on the problems of high variation in sampling value from sensors and the increase of inaccuracy of event detection in wireless sensor networks,a method based on sensor network time series data is presented.Using the median of k normal data collected by the sensor to establish the pivot amount and construct the confidence interval,a method to calculate the data interval discrepancy is proposed to judge the origin of the anomaly. The experimental results show that the detection rate of the abnormal data in the sensor network is above 98% and the false alarm rate remains below 0.5%,which have some certain utilities and commonality.