Abstract: To address the prediction problem in the Network Security Situational Awareness, the RI3F neural network method was proposed to predict the situation value. In order to improve the prediction accuracy of RBF neural network,the HHUA was used for training to acquire the neural network parameters. Experimental results show the validity of this prediction method,and the accuracy of the proposed algorithm was verified by comparative experiment with the existing forecasting methods.

Key words: HHGA, Network security situation, Situation prediction, RI3F neural network