AI-Driven Secure Load Frequency Control of Renewable Energy and Electric Vehicle Integrated Power Systems

Abstract

The increasing integration of renewable energy sources (RES) and electric vehicles (EVs) has transformed modern power systems into complex cyber-physical networks. While these advancements enhance sustainability and flexibility, they introduce vulnerabilities to cyber-attacks such as false data injection and denial-of-service attacks. Load Frequency Control (LFC), a critical mechanism for maintaining system stability, is particularly susceptible due to its reliance on communication networks. This paper proposes an AI-based framework for real-time cyber-attack detection and mitigation in LFC systems. The proposed approach integrates a deep learning-based anomaly detection model with an adaptive control strategy to ensure resilient frequency regulation. Simulation results demonstrate improved detection accuracy (96.8%) and reduced frequency deviation compared to conventional methods. The framework effectively balances robustness and computational efficiency, making it suitable for next-generation smart grids.