Multiscale Entropy-based Weighted Hidden Markov Network Security Situation Prediction Model

The prediction of network security situation is to predict the change of the overall security. It is essential for network security managers. However, existing methods cannot make good use of historical data to predict future situation changes. In view of the above problems, this paper proposes a network security situation prediction model based on weighted Hidden Markov Model (HMM). Firstly, multiscale entropy information is used to solve the problem of training data. The parameter training of HMM transfer matrix is also optimized. Besides, the autocorrelation coefficient can reasonably use the association between the characteristics of the historical data to predict future security situation. The experiments on DARPA2000 prove the feasibility and effectiveness of this method.