Fuzzy Electricity Management System with Anomaly Detection and Fuzzy Q-Learning

Smart grid management is an emerging research topic that recently has adopted artificial intelligence algorithms to assist in the task. However, as more and more data is used, data insecurity and cyber-physical attacks hinder the performance of intelligent systems. In this paper, we propose a fuzzy electricity management system (FEMS) consisting of an attention-based anomaly detection module for attack classification and a fuzzy Q-learning decision module for grid management. Experimental results show that the proposed anomaly detection module achieves high accuracy and F1 scores, significantly outperforming state-of-the-art systems. As for the management evaluation, FEMS achieves extremely low convergence days and mean absolute error (MAE) of supply distribution, which proves the effectiveness of the proposed FEMS in shaping supply distribution. Moreover, FEMS achieves the lowest failure rate (highest stability) but a slightly higher MAE of operating reserve rate due to the unavoidable trade-off between grid stability and energy efficiency.