Dynamic demand response strategies for load management using machine learning across consumer segments

Grid optimization and stability are essential for sustainable power management while energy demand keeps increasing. Demand Response (DR) programs, which provide financial incentives to promote participation, aim to modify customer energy usage patterns, especially during periods of peak demand. The effectiveness of six demand response models in the residential, commercial, and industrial sectors is investigated in this research. These systems efficiently support load adjustment tactics, such as load shifting and curtailment, to achieve notable peak load reductions by utilizing sophisticated prediction approaches, such as machine learning, statistical methods, and reinforcement learning. The study assesses each model’s performance in terms of load reduction and other metrics, emphasizing how customized incentive programs and sophisticated predictive analytics affect grid stability. Received: 06 November 2024 Accepted: 03 December 2024 Published: 17 December 2024