基于高阶马尔可夫链的无线传感器网络异常节点检测

Outlier Detection in Wireless Sensor Networks Based on High-Order Markov Chain

现有无线传感器网络异常节点检测方法由于应用技术自身局限性,存在误检率较高的问题,基于此,提出基于高阶马尔可夫链的无线传感器网络异常节点检测方法。为了降低网络异常节点的误检率,构建无线传感器网络节点属性模型,以此为基础,构建高阶马尔可夫链定义网络正常节点模型;制定节点分簇协议,确定簇头节点并获取节点相关信息,与网络正常节点高阶马尔可夫链进行比较,判定待检测节点的类别,实现无线传感器网络异常节点检测。实验数据显示:在时间与节点密集度两种自变量背景下,与现有方法相比较,基于高阶马尔可夫链的无线传感器网络异常节点检测方法异常节点误检率较低,具有一定可靠性。

Due to the limitations of application technology,the existing abnormal node detection methods in wireless sensor networks have the problem of high false detection rate.Based on this problem,this paper proposes a high-order Markov chain based abnormal node detection method in wireless sensor networks.In order to reduce the false detection rate of abnormal nodes,the attribute model of wireless sensor network nodes is constructed.On this basis,the normal node model is defined by high-order Markov chain;the node clustering protocol is established,the cluster head node is determined,and the node related information is obtained.Compared with the normal node,the high-order Markov chain is used to determine the type of the node to be detected,and the abnormal node detection in wireless sensor network is realized.Experimental data show that in the context of time and node density,compared with the existing methods,the proposed method has lower false detection rate of abnormal nodes,and has certain reliability.