Research on the optimisation of whitelisting technology for network firewall in industrial control system using genetic algorithm

Industrial control systems improve the efficiency of industrial production management but also bring network risks. This paper briefly introduced the industrial control system and the industrial firewall adopting whitelist policy and proposed to optimise the whitelist of industrial firewall with the genetic algorithm-support vector machine (GA-SVM) algorithm to make it learn the rules independently. Finally, simulation experiments were performed using industrial control data collected from light-emitting diode (LED) lamp production enterprises to compare the GA-SVM algorithm with K-means and traditional SVM algorithms. The results demonstrated that the GA-SVM algorithm had better detection accuracy and shorter detection time for abnormal industrial control data; the industrial firewall adopting the GA-SVM-optimised whitelist had lower false blocking rate.