Modeling and Prediction of Network Security Situation in Big Data Environment

In order to meet the real-time performance and improve prediction accuracy of the security situation, a network security situation prediction model in big data environment is proposed in this paper. Firstly, According to the non-linear and time-varying network security situation, extreme learning machine is used to online model for network security situation, and secondly Map/Reduce programming framework is used to process in parallel for network security situation prediction model, finally, the performance is tested and analyzed by using Honeynet data set compared with others models. The results show that the proposed model not only greatly shortens the training time, but also accurately describe the network security situation changes, and can meet the requirements of network security situation prediction.