Hybrid generative AI–driven demand–supply balancing and energy management for renewable-integrated smart grids

The increasing penetration of renewable energy sources introduces significant uncertainty and intermittency in smart grid operations, leading to frequent demand–supply imbalances and inefficient energy management. To address these challenges, this paper proposes a Hybrid Generative AI–Driven framework for demand–supply balancing and energy management in renewable-integrated smart grids. The proposed approach combines deep learning–based forecasting with generative modeling to accurately capture stochastic renewable generation patterns and dynamically coordinate power demand and supply. An AI-driven energy management strategy is further employed to optimize power distribution, reduce peak load stress, and minimize operational costs. The effectiveness of the proposed framework is evaluated using real-world load demand and renewable generation datasets and compared against conventional statistical and deep learning models. Experimental results demonstrate that the proposed method significantly reduces demand–supply deviations, improves grid stability, and enhances power distribution efficiency. Moreover, the optimized energy management strategy achieves substantial peak load reduction and operational cost savings while reducing renewable energy curtailment. The results confirm that Hybrid Generative AI provides a robust and scalable solution for balancing demand and supply and improving energy management in modern renewable-integrated smart grids.