Detection of false data injection attack in power information physical system based on SVM–GAB algorithm
Xiaoping Xiong, Siding Hu, Di Sun, Shaolei Hao, Hang Li, Guangyang Lin
Abstract
Cyber physical power system (CPPS) is highly dependent on information and communication technology, which makes it vulnerable to network attacks. Among them, false data injection attack (FDIA) is not easy to be found by traditional bad data detection methods, and becomes one of the main threats to the safe operation of power systems. However, the high complexity, large amount of data and transient characteristics of CPPS put forward higher requirements for the accuracy and efficiency of FDIA detection method. Therefore, in view of the characteristics of CPPS, this paper proposes SVM–GAB (Support Vector Machines–Gentle Adaboost) algorithm to effectively detect FDIA. Through the effective dimension reduction and classification of the measured data, the real-time and high-precision detection of FDIA is realized. This algorithm is compared with mainstream detection algorithms in IEEE-14 and IEEE-39 standard systems. The results show that the false alarm rate of this algorithm is reduced by at least 25% compared with the traditional detection algorithm, and the accuracy and real-time performance of the proposed detection algorithm are verified by experiments.