Preference based multi-objective reinforcement learning for multi-microgrid system optimization problem in smart grid

Abstract Grid-connected microgrids comprising renewable energy, energy storage systems and local load, play a vital role in decreasing the consumption of fossil diesel greenhouse gas emissions. A distribution power network connecting several can promote more potent reliable operations to enhance security privacy system. However, operation control for multi-microgrid system is big challenge. To design system, an intelligent multi-microgrids management method proposed based on preference-based multi-objective reinforcement learning (PMORL) techniques. The model be divided into three layers: consumer layer, independent operator grid layer. Each layer intends maximize its benefit. PMORL lead Pareto optimal set each object achieve these objectives. non-dominated solution decided execute balanced plan not favor any particular participant. results show that effectively learn different preferences. simulation outcomes confirm performance verify viability method.