Key points are not available for this paper at this time.
The stability and reliability of smart grids are essential for ensuring efficient and secure electricity delivery, particularly amid the increasing integration of renewable energy sources. This review presents a comprehensive analysis of artificial intelligence (AI)-based methods for real-time grid management, and fault detection. Unlike previous works that focus on isolated grid functions, this study provides a unified framework encompassing energy monitoring and control, optimization, and resilience. Machine learning, deep learning, and reinforcement learning techniques are systematically evaluated across diverse grid tasks, highlighting their strengths, limitations, and implementation challenges. Special attention is given to hybrid models that combine AI with optimization strategies to address issues such as scalability, computational complexity, and adaptability. The paper identifies critical research gaps and offers actionable recommendations to advance AI-driven smart grid operations, promoting more resilient, adaptive, and intelligent power systems.
Ahmadi et al. (Sat,) studied this question.