Power System Network Attack Event Prediction Model Based on Long Short-Term Memory Network

With the expansion of the network scale and the increase of data traffic, power systems face serious network security risks. Security issues such as malicious attacks, data breaches, and device tampering pose a huge threat to the stability and reliability of power systems. Therefore, the analysis and prediction of network attack events have become the key to ensuring the security of power systems. This paper proposes a network attack event prediction model based on the Long Short - Term Memory (LSTM) network. By statistically analyzing the network attack events of a certain power system, the LSTM network is used to capture the temporal dependencies in the time - series data of attack events, so as to better understand the dynamic changes in the behavior of attack events, focus on the important information in historical data in a targeted manner. The proposed LSTM model can improve the prediction accuracy. Experimental verification shows that the designed network attack number prediction model can complete the prediction task with a small prediction error.