多参量状态下网络节点异常故障诊断仿真

摘要

多参量状态下对网络节点异常故障进行诊断,可以有效保障网络的运行质量.对网络节点异常故障的诊断,需要提取异常节点特征参数,进而设置故障检测阈值,完成网络节点异常故障诊断.传统方法构造一系列具有表征状态能力的特征向量,对不同的特征向量进行分类,但忽略了设置故障检测阈值,导致诊断误差较大.提出基于信息熵的多参量状态下网络节点异常故障诊断方法.该方法先融合于信息熵理论选择受网络状态变化影响较小的信息熵作为故障特征参数提取,按照地理位置进行分簇,在能量不受限的汇节点处进行簇内故障特征再聚类,在此基础上设置故障检测阈值,利用该阈值完成对多参量状态下网络节点异常故障诊断.实验结果表明,所提方法故障诊断精度高,为保障网络的稳定运行质量奠定有力的基础.%An abnormal fault diagnosis method of network nodes in multi-parameter state is proposed based on information entropy.Firstly,integrated with theory of information entropy,information entropy with less influenced by change of network state is selected as parameter extraction of fault feature,and the cluster is carried out according to geographic position.Then,fault feature in cluster is carried out in sink node without energy limitation.On that basis,threshold value of fault diagnosis is set.Finally,the threshold value is used to complete the abnormal fault diagnosis.Simulation results show that the method has high precision of fault diagnosis.It lays powerful foundation for ensuring quality of stable operation of network.