A Quantitative Forecast Method of Network Security Situation Basedon BP Neural Network with Genetic Algorithm

The accurate real-time forecast of network security situations is the premise and basis of preventing large- scale network intrusions and attacks. In order to forecast the security situation more accurately, a quantitative forecast method of network security situations based on the back propagation neural network with genetic algorithm (GABPN) is proposed. After analyzing the past and the current network security situation in detail, we build a network-security-situation forecast mode based on the BP neural network that is optimized by the improved genetic algorithm, and then adopt the GABPN to forecast the non-linear time series of network security situation. Simulation experiments prove that the proposed method in this paper has advantages over the back propagation neural network method (BPNN) with the same architecture in the convergence speed, functional approximation and forecast accuracy.