Optimal operation of an electrical microgrid via recurrent neural network

This paper focuses on the optimal operation of a microgrid, interconnected to the utility grid; moreover, it incorporates batteries for energy storing and supplying, and an electric car. It presents a neural network optimization approach combined with a multi-agent system (MAS). This work determines the power optimal amounts over a time horizon of one day for wind, solar, and batteries systems, including the one of the electric car, in order to minimize the utility grid power and maximize the power supplied by renewable energy sources. Simulation results illustrate that generation levels for each energy source over a time horizon can be reached in an optimal form using the proposed method.