Multi-stage optimal scheduling of multi-microgrids using deep-learning artificial neural network and cooperative game approach

This article proposes a two-stage system for the daily energy management of micro-grids (MGs) in the presence of wind turbines, photovoltaic (PV) panels, and electrical energy storage systems (ESSs). Each MG uses historical data to predict its consumers' load demand, wind speed, and solar irradiance in the first stage. In the second stage, the cooperative game method is used to determine the MG's daily dispatch and energy transaction. The paper develops a prediction model using artificial neural network (ANN) and rough neuron water cycle (RNWC) algorithms, called deep learning artificial neural network (DLANN), which is a combination of technology from the artificial neural network and WC algorithm in order to predict uncertain parameters. The above model is implemented in the 33bus power distribution system; the simulation results show that the DLANN method provides more accurate predictions than the ANN method. The results also show that a MG can achieve energy cost savings through an alliance of MGs using the cooperative game approach. Furthermore, analysis of the impact of the ESS on the operation of the MG shows that the absence of the ESS will reduce the power output of the wind turbine. (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This article presents a two-stage energy management system for micro-grids, utilizing historical data to predict load demand, wind speed, and solar irradiance, followed by cooperative game method to determine energy dispatch and transaction. By combining artificial neural network and rough neuron water cycle algorithms in the DLANN model, more accurate predictions can be achieved for energy savings.