Abstract—Solar photovoltaic energy has become an important component of modern electricity systems, yet its variable nature creates challenges for grid stability, demand balancing and energy management. This review examines AI-driven demand response management in solar-powered smart grids, with emphasis on how artificial intelligence supports forecasting, load flexibility, battery coordination and renewable energy utilisation. The study adopted a structured narrative review approach and synthesised recent scholarly literature on smart grids, solar Photovoltaic (PV) integration, machine learning, deep learning, reinforcement learning, federated learning and explainable ArtificiaI Intelligence. The findings show that AI improves demand response by enabling accurate load prediction, solar generation forecasting, dynamic pricing, automated appliance scheduling and real-time grid optimisation. Reinforcement learning and multi-agent systems were found to be particularly useful in solar-powered environments where consumers, prosumers, batteries and distributed energy resources interact under uncertain grid conditions. The review further shows that AI-driven demand response can reduce peak demand, increase solar self-consumption, minimise curtailment and strengthen grid flexibility. However, implementation remains constrained by privacy concerns, cybersecurity threats, black-box algorithms, infrastructure limitations and low consumer trust. The study concludes that AI-driven demand response is essential for the effective operation of solar-powered smart grids, but its success depends on secure data governance, transparent algorithms, interoperable technologies and supportive regulation. The review provides useful insight for researchers, policymakers, utilities and energy planners working toward intelligent renewable energy systems.

Keywords—artificial intelligence, demand response, solar photovoltaic energy, smart grids, energy management

Cite: Kwadwo Larbi, Clinton Amponsah, "AI‐driven Demand Response Management in Solarpowered Smart Grids: A Review," International Journal of Smart Grid and Clean Energy, Vol. 15, No. 2, pp. 92-107, 2026. doi: 10.12720/sgce.15.2.92-107

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).