Anomaly Detection in a Smart Grid Using a Novel Hybrid Deep Learning Approach

Abstract

ABSTRACT The evolution of smart grids has enabled more efficient fulfilment of energy demands and addressed the limitations of conventional power systems through rapid detection of electrical and cyber anomalies. This study presents deep learning models based on LSTM, CNN and GRU architectures designed to ensure fast and reliable anomaly detection while maintaining a minimal false positive rate, thereby preventing unnecessary service interruptions. An LSTM‐CNN model is initially applied to anomaly datasets to address challenges associated with imbalanced classification. A hybrid LSTM‐GRU model is subsequently employed for feature extraction and identification of false data. Finally, these models are integrated into a combined LSTM‐GRU‐CNN framework, demonstrating superior anomaly detection performance across large‐scale datasets, with enhanced accuracy and execution speed. Experimental evaluation on a real‐world consumer database confirms the effectiveness of the proposed hybrid models. The LSTM‐GRU‐CNN hybrid architecture emerged as the best performer, achieving an excellent precision of 99.9%, an F1‐score of 94.83%, and an excellent MCC of 91.25%, and resulting in a total absence of false positives. This performance underscores the ability of optimised deep learning models to identify anomalies with high acuity while avoiding false triggers.