Abstract
Network security situation (NSS) prediction has attracted a great attention in recent years, and gained promising results to avoid different types of network attacks in advance. However, current methods still suffer from several drawbacks. In this paper, we propose a novel iterative optimized RBF-NN method for NSS prediction. Our proposed method applies a resource allocation network (RAN) to determine the optimal number of neurons in the hidden layer. Moreover, it builds a cross-model method with a genetic algorithm to compute the optimal weights for the RBF-NN model. Specifically, we come up with a chaos search strategy during the iterative optimization process to prevent the RBF-NN model from falling into a local extreme point. Due to our opti-mization technique, compared with other optimization techniques, the proposed method could shorten training process by at most 29.2% and increase prediction accuracy by at most 86.6% with well generalization ability.