Power system network intrusion detection method, system and equipment

The invention discloses a power system network intrusion detection method, system and device, and relates to the technical field of power system network security. The method comprises the following steps: acquiring network intrusion data of a power system and carrying out data normalization processing; clustering the normalized feature data by adopting an agglomerated hierarchical clustering algorithm to obtain a clustered feature data set; carrying out undersampling on the clustered feature data set by adopting an edge-preserved K-nearest neighbor algorithm to obtain a plurality of undersampled feature subsets, and splicing the subsets to obtain an overall undersampled feature data set; a greedy recursion elimination cross validation algorithm is adopted to perform feature selection on the overall undersampling feature data set to obtain an optimal feature subset; and inputting the optimal feature subset into the parallel deep neural network model, and outputting an intrusion detection result. According to t