Abstract:

In order to solve the problem of insufficient accuracy of current network security situation prediction methods,a new network security situation prediction model was proposed based on self-correcting coefficient smoothing.Firstly,a network security assessment quantification method was designed to transform the alarm information into situation real value time series based on the entropy correlation degree.Then,the adaptive solution of the static smoothing coefficient was calculated and the predicted initial value was obtained by using the variable domain space.Finally,based on the error category,the time-changing weighted Markov chain was built to modify the initial network situation prediction result and the prediction accuracy was further raised.The prediction model was tested with LL_DOS_1.0 dataset and the experimental results show that the proposed model has higher adaptability and prediction accuracy for network situation time series.

Key words: security situation, quantification method, variable domain space, modify, multiple coefficient smoothing