Abstract Global momentum toward intelligent power infrastructure is accelerating as electricity demand grows, renewable energy penetration deepens, and sustainability imperatives intensify. Artificial intelligence (AI) technologies—encompassing machine learning, deep learning, reinforcement learning, expert systems, fuzzy logic, and hybrid frameworks—have become indispensable enablers of next-generation grid operations. These approaches support intelligent monitoring, accurate load and renewable-energy forecasting, autonomous fault detection, demand-response orchestration, and optimal distributed energy resource integration. Notwithstanding these advantages, practical deployment faces persistent barriers including cyber security vulnerabilities, data-privacy constraints, infrastructure investment costs, device interoperability deficits, and insufficient regulatory frameworks. This study presents a structured original review of AI-enabled smart grid architectures and operational paradigms, systematically evaluates capabilities and trade-offs of principal AI methods, analyzes prevailing challenges alongside viable mitigation strategies, quantifies documented operational benefits, and maps prospective technological trajectories—including edge AI, digital twins, explainable AI, block chain, and federated learning—toward autonomous grid operation. Findings indicate that strategic AI adoption is critical to achieving resilient, efficient, and low-carbon power systems for the future.
B et al. (Sat,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: