Network Intrusion Detection Method for Secondary System of Intelligent Substation based on Semantic Enhancement
Bo Xiang, Changchun Zhang, Jugang Wang, Bo Wang · 2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT) · 2022
Aiming at the problems of low detection accuracy, high false detection rate and high missed detection rate of traditional Intelligent Substation (I-S) secondary system network Intrusion Detection (I-D) methods, a semantic enhanced network I-D method for I-S secondary system is proposed. First of all, through the analysis of the secondary system network of I-S and the existing security risks, the information network security protection architecture is built based on network I-D. Then, the overall structure of I-S secondary network I-D is constructed by integrating CNN and BiLSTM. Finally, the semantic analysis of Latent Dirichlet Allocation (LDA) is introduced to enhance the network I-D model, which greatly improves the detection accuracy. The proposed method is compared with the other two methods under the same conditions through simulation experiments. The results show that the detection accuracy of the proposed method is the highest (95.02%) in the face of 10 different types of attack traffic, and the false detection rate and missed detection rate are the lowest (1.3% and 3.8% respectively). The algorithm performance is better than the other three comparison algorithms.