A MAPPO Algorithm-Based Approach to Energy Management for Integrated Energy Systems in Communities

The rapid growth in the number of electric vehicles (EVs) has become an important part of the smart grid. With its advantages of energy saving, environmental protection and high energy efficiency, its role in the smart grid is becoming more and more prominent. However, when it is connected to the grid in large quantities, it also brings great challenges to the stability of the grid. In this paper, the benefits between EVs and the grid are considered comprehensively from a grid-oriented perspective. The optimization goal is to make the load of the grid stable. We formulate the EV charging scheduling problem as a Markov decision process and propose a MAPPO-based integrated energy optimization strategy for parks to find the optimal charging strategy. In the proposed strategy framework, an actor network is utilized to provide guidance for the EV charging strategy, and two objective Q-networks are used to ensure the stability of training. Using this approach, EV users can maximize benefits for themselves and contribute to grid peak shaving.