Akademik Veri Yönetim Sistemi
IEEE 13th International Conference on Smart Grid (icSmartGrid), Glasgow, İngiltere, 27 - 29 Mayıs 2025, ss.75-83, (Tam Metin Bildiri)
There is a growing interest in developing costeffective and modern power systems, particularly considering the increasing popularity of renewable energy sources and decentralized power systems. The microgrid concept prioritizes distributed power generation and renewable energy sources and encompasses nanogrids that can be managed independently or integrated into larger systems. A novel approach, designated as nanogrid clusters, includes the integration of multiple nanogrids under a unified control framework. This strategy enhances the scalability, reliability, and security of energy supply. To optimize the efficiency of distributed generation and renewable energy, it is crucial to implement effective control and energy management strategies at the nanogrid cluster level. This paper proposes an optimal energy management strategy for standalone nanogrid clusters coordinating the Markov Decision Process (MDP) and QLearning. The approach considers the inherent uncertainties associated with renewable energy generation and load demand, enabling optimal decision-making even in unpredictable conditions. The simulations demonstrate the success of the proposed approach in terms of energy efficiency, load balancing, and effective control of energy costs. This study highlights the potential of the MDP framework in managing uncertainties and optimizing the performance of nanogrid clusters, thereby supporting the development of sustainable and resilient energy systems.