Robust Detection in Power Systems: Iterative Reinforcement Learning Based Adversarial Training

Stealthy cyberattacks pose a significant threat to modern power systems by exploiting advanced techniques to manipulate system behavior while avoiding detection by traditional security measures. In this study, we focus on the impact of Deep Reinforcement Learning (DRL) based attackers on a sample microgrid and develop robust detectors to mitigate these threats. Leveraging an iterative training process, we enhance the capabilities of successive attackers and detectors, resulting in improved system security. Our experiments demonstrate that DRL-based attackers can effectively disrupt system operations, highlighting the importance of robust detection mechanisms. Subsequently, we develop robust detection mechanisms, making new attacker attempts unsuccessful. We show that detectors developed through our mechanism are more effective in mitigating system impact and quickly identifying anomalies.