This paper presents a novel fully decentralized and intelligent energy management system (EMS) for a smart microgrid based on reinforcement learning (RL) strategy. The purpose of the proposed EMS is to maximize the benefit of all microgrid entities comprising customers and distributed energy resources (DERs). Due to unpredictable features of renewable energy sources and variability of consumers’ demands, designing the microgrid EMS is a complicated task. To overcome this issue, the multi‐agent hour‐ahead energy management problem is modelled as a finite Markov decision process. The microgrid entities are considered as intelligent agents. The optimal policy of agents is obtained through a newly developed framework of the model‐free Q‐learning algorithm to maximize the benefit of all renewable and non‐renewable energy resources and battery energy storage system. The degradation model of the battery is considered to reduce the number of battery replacements. To ensure customers’ comfort, customers’ expenses are decreased without demand curtailment via introducing two types of load shifting techniques. The microgrid operation is analysed under four scenarios comprising no‐learning, generator‐learning, customer‐learning, and whole‐learning. the performance of the proposed algorithm is compared to the Monte Carlo method and simulation results on the real power‐grid dataset show the superiority of the algorithm.
Microgrids are considered to be smart power grids that can integrate Distributed Energy Resources (DERs) in the main grid cleanly and reliably. Due to the random and unpredictable nature of Renewable Energy Sources (RESs) and electricity demand, designing a control system for microgrid energy management is a complex task. In addition, the policies of microgrid agents are changing over time to improve their expected profits. Therefore, the problem is stochastic and the policies of the agents are not stationary and deterministic. This paper proposes a fully decentralized multiagent Energy Management System (EMS) for microgrids using the reinforcement learning and stochastic game. The microgrid agents, comprising customers, and DERs are considered as intelligent and autonomous decision makers. The proposed method solves a distributed optimization problem for each self-interested decision maker. Interactions between the decision makers and the environment during the learning phase lead the system to converge to the optimal equilibrium point in which the benefits of all the agents are maximized. Simulation studies using a real dataset demonstrate the effectiveness of the proposed method for the hourly energy management of microgrids.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.