Network Security Situation Assessment of Power Information System Based on Improved Artificial Bee Colony Algorithm

Abstract

The network security situation assessment of power information system is popular in the field of network security research. However, the current neural network-based security situation assessment method is inefficient and easy to fall into local optimum, which results in low evaluation accuracy. This paper proposes a new network security situation assessment method based on neural network which is optimized by an improved artificial bee colony (ABC) algorithm. Firstly, the chaotic sequence is introduced to ABC algorithm to improve the diversity of bee colonies, which can make ABC algorithm have more powerful global search capabilities. Then, the improved ABC algorithm is used to optimize the weight parameters of the neural network instead of the back propagation algorithm. Finally, the new method carries out a security situation assessment and prediction for a real network attack of power information system.