A false data attack detection method for power grid based on an improved AIGA

As a typical cyber-physical attack， false data are measured unchanged， thus deceiving the detection based on chi-square detector. To this end， a false data attack detection method for smart grid based on an improved adaptive immune genetic algorithm （AIGA） is proposed. First， a three-phase voltage measurement network model is established to analyze the hidden characteristics of the false data attack. Then， the similarity index between antibodies is utilized to establish an anomalous data detector to detect the intruding false data. In addition， the convergence speed and global optimization ability of the algorithm are improved by introducing the adaptive design of selection operators， crossover operators， and mutation operators， which improves the performance index of the attack detection. Finally， the detection rate and false detection rate of the proposed method for false data attack detection are analyzed through simulation experiments， and the results verify the effectiveness of the method.