Research On Network Security Situation Awareness Key Technology

With the continuously development of information technology in our country, the economic and social life of the reliance of the information network for more and more high, the influence degree of various network security incidents will gradually increase, more and more the main economic information security problem. But because of the complexity of the network, as well as new technologies such as cloud computing, Internet of things will continue to be used widely in the field of information technology, network security harder in key areas. Therefore, through comprehensive, centralized security management and intelligence, based on the analysis of events, will be different in the field of security components into a seamless system of security, has become the development trend of the next generation of the whole network security solutions. And network security situational awareness model based on network security situational awareness model research, break through the network security situational framework design, quantitative trend data preprocessing, situational awareness and situational to predict key technical problems, such as its research results can improve the efficiency of the network security decision, reduce the risk and loss caused by the network security. The main research results are as follows:(1) On the network security situation factor and situation awareness progress are analyzed, and according to the situation analysis results, the network security situational awareness index system is built, which contains information assets, vulnerability and risk etc. Combining the idea of data fusion and, the network situation awareness model based on hierarchy is proposed.(2) In order to resolve the problem of parameter optimization in situation awareness method, a method of parameter optimization based on PSO is proposed in this paper, which can get better in time consuming and improve the accuracy of balance; At the same time, according to the grey correlation analysis to determine the index weight, the training sample input into the support vector machine(SVM) for training, the parameters of support vector machine was optimized by using improved particle swarm optimization(pso) algorithm, the network security situation assessment model is established, and the simulation was carried out on the model performance test. The simulation results show that the model can accurately and objectively to evaluate network security situation.(3) In order to resolve the problem of weight optimization in situation forecast method, based on the related theory of neural network to network security situation prediction model was built, as well as the Elman neural network is optimized, refer to the double feedback Elman neural network, and by using the trend of introducing correction factor parameters are optimized, the optimization is constructed after the introduction of the trend of correction factor of the double feedback Elman neural network security situation prediction model, and simulated test, the testing results show that the optimized trend of the introduction of the correction factor of double feedback Elman neural network, the prediction ability is superior to the basic Elman neural network, the forecast result satisfied.