A Joint FDIA Detection and Localization Scheme and Experimental Analysis Based on Adversarial Anomaly Transformer for Power Distribution System

The false data injection attacks (FDIA) pose significant threats to the security of the power distribution systems, underscoring the critical need for efficient FDIA detection and localization schemes. In this article, a joint FDIA detection and localization scheme based on an adversarial anomaly transformer is proposed, and the experimental analysis is performed using a developed cyber-physical power distribution simulation system testbed. To address the prevalent overgeneralization issue in reconstruction-based unsupervised methods, an anomaly attention mechanism is first introduced into the FDIA detection and localization scheme to amplify the distinguishability between normal and attacked data. Subsequently, a generative adversarial network framework is used to capture the distribution of data accurately. In addition, the drift streaming peaks over threshold dynamic threshold method is used to adapt to fluctuant measurements and enhance online detection applications. Finally, simulations and experiments are conducted on the developed cyber-physical testbed to demonstrate the superiority of proposed scheme.