Research on Network Security Situation Assessment and Forecasting Technology

In recent years, the network security issues have become more prominent, and traditional network security protection technologies have been unable to meet the needs. To solve this problem, this paper improves and optimizes the existing methods, and proposed a set of network security situation assessment and prediction methods. First, the cross-layer particle swarm optimization with adaptive mutation (AMCPSO) algorithm proposed in this paper is combined with the traditional D-S evidence theory to evaluate the current network security situation; Then, the parameters and structure of traditional RBF neural network are optimized by introducing FCM (fuzzy c-means), HHGA (hybrid hierarchy genetic algorithm) and least square method. According to the optimized RBF neural network and situation assessment results, the next stage of network security situation is predicted. Finally, the effectiveness of the network security situation assessment and prediction method proposed in this paper is verified by simulation experiments. The algorithm in this paper improves the accuracy of situation assessment and prediction, and has certain reference significance for the research of network security.