Multi-objective energy management of multiple microgrids under random electric vehicle charging

Abstract

In view of the increasing development of decentralized power systems and electric vehicles, this paper seeks to improve the energy management performance of multiple microgrid systems under the uncertainty associated with electric vehicle charging. A multi-objective optimization model is established for minimizing the transmission losses, operating costs, and carbon emissions of multiple microgrid systems. Firstly, a novel method is proposed for forecasting electric vehicle charging loads based on a back propagation neural network improved by long short-term memory deep learning. Based on the forecast data, a double layer solution algorithm is proposed, which consists of an adaptive multi-objective evolutionary algorithm based on decomposition and differential evolution at the multiple microgrids layer and a modified consistency algorithm for fast economic scheduling at the single microgrid layer. Finally, a model system composed of four interconnected IEEE microgrids is simulated as a case study, and the performance of the proposed algorithm is compared with that of conventional multi-objective evolutionary algorithms based on decomposition. The simulation results demonstrate the superiority of the global search performance and the rapid convergence performance of the proposed improved algorithm.