Intelligent Algorithms for Coordinated Control Strategy of Electric Vehicle Pile Group Load Based on Virtual Aggregation Using Hybrid DRL-SAC With Ant Colony Optimization Model

Abstract In an effort to lessen the impact of cities on the environment, more and more electric vehicles (EVs) are entering the market as a viable substitute for fossil fuels. But advancements in electric car technology have been slowed by the wrong positioning of charging sites. This study presents an index method for assessing the position of electric car charging heaps. It is based on 16 parameters chosen from four categories: economy, environment, cost, as well as service quality. This study develops a set coverage concept and uses a greedy heuristic approach to determine the best places to put charge piles based on the assessment. In this research, we build a model for managing household electric car charging piles using a deep reinforcement learning method. The report suggested a novel method of controlling the conventional plug-and-play charging method in homes, which reduced the negative effects of unauthorized charging of EVs on the power grid. This control method suggests a charging pile group control model using a deep reinforcement learning algorithm, taking into account the time-sharing pricing of electric car charging as well as the safe and economical functioning of the transmission network. Delay in dispatching depend on the power grid's load change rate, reference load dispatching, and dispatching load increments, which are the primary components of this control method. The district distribution network can run more smoothly, charging pile operators can make more money, and electric vehicle users can pay less to charge their vehicles. Lastly, the report analyzes the current placement of electric car charging heaps to confirm the model's reasonableness and viability. The evaluation-based set coverage model is a novel approach to determining the best locations for electric car charging heaps across China, and this research intends to lay the theoretical groundwork for the growth of this emerging energy sector.