As a key component of the energy internet

cyber-physical power systems face the threat of false data injection attacks. Detection techniques for such attacks often neglect the localization of the attack injection

and research attempting to solve this problem has difficulty balancing detection accuracy and computation time. Therefore

this paper proposes a false data injection attack localization method based on adaptive differential evolution-fuzzy broad learning system. The proposed algorithm employs a fuzzy broad learning system with a transversal network structure to constitute the localization algorithm

which realizes the fast detection. Meanwhile

an adaptive differential evolution algorithm is proposed to perform feature selection on the measured data and eliminate the redundant features

which effectively improves the accuracy of the algorithm for location detection. Extensive simulations in IEEE-14 and 57-node systems verify that the proposed method is capable of precise localization of spurious data injection attacks

and has better accuracy

precision

recall

and F1-score compared with multiple traditional detection algorithms.