Search

In this paper, a decentralized energy management system is presented for intelligent microgrids with the presence of distributed resources using reinforcement learning. Due to the unpredictable nature of renewable energy resources, the variability of load consumption, and the nonlinear model of batteries, the design of a microgrid energy management system is associated with many challenges. In addition, centralized control structures in large-scale systems increase computational volume and complexity in control algorithms. In this paper, a fully decentralized multi-agent structure for a microgrid energy management system is proposed and the Markov decision process is used to model the stochastic behavior of agents in the microgrid. Electrical and thermal distributed resources, batteries, and consumers are considered intelligent and independent agents. They have the learning ability to explore and exploit the environment in a fully decentralized manner and achieve their optimal policies. The proposed method for hourly microgrid management is model-independent and based on learning. The method maximizes the profits of all manufacturers, minimizes consumer costs, and reduces the dependence of the microgrid on the maingrid. Finally, using real data from renewable energy sources and consumers, the accuracy of the proposed method in the Iranian electricity market is simulated and verified. [ABSTRACT FROM AUTHOR]

The presence of electric vehicle technology in distribution networks as controllable resources provides advantages such as voltage regulation, power peaking, and loss reduction. This technology has a positive effect on the performance of the distribution network, but the simultaneous presence of electric vehicles and distributed generation sources requires optimal planning because the lack of access to an application reduces the life of these technologies and can cause blackouts in the power network. Therefore, in this study, the dynamic reconfiguration of the distribution network in the simultaneous presence of distributed generation sources and electric vehicles is proposed. Also, the time-of-use mechanism has been proposed as one of the demand response applications to improve the power consumption of subscribers. The objective functions in this study include the reduction of energy loss, operational cost and energy not supplied as the objective function of reliability. In general, the optimization problem of distribution network reconfiguration is complex and non-convex. Also, considering the effect of distributed generation units and electric vehicles makes the problem more complicated than before. Therefore, finding a practical method to solve the optimization problem is one of the main challenges of this paper. For this purpose, a novel hybrid algorithm based on a combination of an improved particle swarm optimization-artificial bee colony is presented to overcome the complexities of the optimization problem. The proposed method has [ABSTRACT FROM AUTHOR]