Abstract
Artificial Intelligence (AI) revolutionizes the renewable energy sector by enabling advanced forecasting, real-time optimization, and autonomous system control. As global efforts toward decarbonization intensify, AI applications have rapidly expanded across various renewable energy domains. However, the literature remains fragmented, lacking a focused synthesis of evolving AI techniques and their domain-specific implementations. This study addresses this gap by systematically reviewing AI applications in three critical energy sectors: Solar Energy, Wind Energy, and Energy Storage & Smart Grids. Using the PRISMA methodology, peer-reviewed articles published between 2015 and 2025 were extracted from two authoritative databases—IEEE Xplore and ScienceDirect. The selected studies were classified based on AI methods, including machine learning, deep learning, reinforcement learning, fuzzy logic, and emerging paradigms such as explainable AI (XAI), generative AI, graph neural networks (GNNs), and physics-informed neural networks (PINNs). Key contributions of this review include a cross-source comparative analysis, domain-specific trend mapping over a decade, and the identification of gaps in methodological transparency. Findings reveal increasing use of hybrid models, growing interest in interpretable and physically grounded techniques, and persistent underreporting of AI methodologies in the literature. This review provides actionable insights and research directions toward developing intelligent, explainable, sustainable energy systems.