Electricity Network Security Monitoring Based on Bee Colony Algorithm

In order to effectively detect and discover network threats in the initial stage, this study proposes an electricity security intrusion detection method based on feature selection. A heuristic selection algorithm bee colony is proposed overcome shortcomings of existing evaluation methods. The uses average mutual information measure importance features more truly reflects relationship between selected features, classification labels. Aiming at problem that easy fall into local optimization, a random search proposed, which iteratively optimizes generate smaller subsets, improves speed accuracy detection. experimental results show compared with traditional algorithm, can evaluate risk attack path data set, gap generation strategy optimal reduced by 71.3%, enhances practicability graph analysis large-scale environment. Conclusion. This has good scalability be applied environments. It obtain paths are line real threat situation acceptable time, so as find threats.