Security Situation Identification of Distribution Automation Network Based on Deep Neural Network
In the automatic identification of distribution network security situation,the existing methods mainly extract data fea-tures through a single hidden layer neural network,which makes the standard error of identification results larger.Therefore,this study proposes an automatic identification algorithm of distribution automation network security situation based on deep neural network.From static security and dynamic security,a complete evaluation index system is established to describe the operation state of the power grid.The evaluation value of network security situation is calculated by combining the analytic hi-erarchy process and the improved entropy weight method,and the risk level is reasonably divided.A deep neural network is used to build an identification model,extract the deep level characteristics of multi-level network data,and obtain the network security situation identification results.The gravity function and fitness function are used to search the optimal security situa-tion identification results.The experimental results show that compared with BP neural network identification algorithm and RBP neural network identification algorithm,the standard error of the automatic situation identification algorithm is reduced by 27 percentage points,29 percentage points,and the accuracy of security situation identification is up to 99.55％.
deep neural networkdistribution networknetwork securitysituational awarenessautomatic identificationeval-uation index
万方数据
维普
