AI-enhanced resilience in power systems: Adversarial deep learning for robust short-term voltage stability assessment under cyber-attacks

• Published in: Chaos, solitons and fractals Vol. 196; p. 116406
• Main Authors: Li, Yang, Zhang, Shitu, Li, Yuanzheng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.07.2025
• Subjects: Adversarial deep learning; AI-based cyber resilience; Graph Attention Network; Power system; Resilient control strategy; Short-term voltage stability; Smart grid cybersecurity; Power system; Short-term voltage stability; Adversarial deep learning; AI-based cyber resilience; Resilient control strategy; Graph Attention Network; Smart grid cybersecurity
• ISSN: 0960-0779
• DOI: 10.1016/j.chaos.2025.116406

In the era of Industry 4.0, ensuring the resilience of cyber-physical systems against sophisticated cyber threats is increasingly critical. This study proposes a pioneering AI-based control framework that enhances short-term voltage stability assessments (STVSA) in power systems under complex composite cyber-attacks. First, by incorporating white-box and black-box adversarial attacks with Denial-of-Service (DoS) perturbations during training, composite adversarial attacks are implemented. Second, the application of Spectral Normalized Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (SNCWGAN-GP) and Fast Gradient Sign Method (FGSM) strengthens the model's resistance to adversarial disturbances, improving data quality and training stability. Third, an assessment model based on Long Short-Term Memory (LSTM)-enhanced Graph Attention Network (L-GAT) is developed to capture dynamic relationships between the post-fault dynamic trajectories and electrical grid topology. Experimental results on the IEEE 39-bus test system demonstrate the efficacy and superiority of the proposed method in composite cyber-attack scenarios. This contribution is pivotal to advancing AI-based resilient control strategies for nonlinear dynamical systems, marking a substantial enhancement in the security of cyber-physical systems. •Combines DoS attacks and FGSM for composite adversarial training in power system assessments•Enhances model robustness against composite cyber-attacks with adversarial deep learning•Refines data enhancement techniques, improving sample quality and model generalization•Integrates LSTM-enhanced Graph Attention Networks for accurate STVSA