Network security situation prediction method based on MEA-BP

Abstract

At present, network attacks on networks have become very complex. As the highest level of network security situation awareness, network security situation prediction provides effective information for network administrators to make security protection strategy. Network analysis decision-makers not only need to understand, but also need to predict the current network security situation. In the field of network security, the study of network security situation prediction has become a hotspot. According to the characteristics of network security situation value of nonlinear time series, when BP algorithm is adopted, it has been applied to the problem of local optimal solution, multiple iterations and low efficiency. In order to overcome these shortcomings, this paper improves the positive effects, optimizes its weights and thresholds, and uses the MEA to develop a MEA-BP model to predict the network security situation. An example of case prediction is provided. The results show that this method can improve the accuracy and efficiency.