WSN中基于分布式机器学习的异常检测仿真研究

Simulation Study of Anomaly Detection Based on Distributed Machine Learning for WSN

安全问题是无线传感器网络应用的关键问题之一。设计了一种基于分布式机器学习的异常检测方案。该方案利用K最近邻算法对传感器网络节点进行分簇,时簇内节点的异常检测采用贝叶斯分类算法,对簇头节点的异常检测采用基于平均概率的方法。利用网络仿真工具NS2构建了入侵检测规则、模拟了网络攻击场景,在此基础上,通过仿真评估了方案的检测率、平均检测率、误检率和平均误检率等性能。仿真实验结果表明,该方案与当前典型的无线传感器网络入侵检测方案相比具有较高的检测率和较低的误检率。

Security is one of the most important challenges in wireless sensor network （WSN） applications. A Distributed Machine Learning （DML） based anomaly detection scheme was proposed and designed, where a new clustering approach was presented by using the K nearest neighbor algorithm, Bayesian classification algorithm was used to detect anomaly nodes in inter-cluster, the anomaly detection of cluster-head nodes was detected by using average probability approach. By using network simulation tool NS2, intrusion detection rules were developed, network attack traffic was generated and simulated. And based on this, its detection rate, average detection rate, false positive rate and average false positive rate were evaluated. Simulation results demonstrate that the scheme achieves higher accuracy rate of detection and lower false positive rate than the current important intrusion detection schemes of WSN.