Optimal EVCS planning via spatial-temporal distribution of charging demand forecasting and traffic-grid coupling

As the penetration of electric vehicles (EVs) continues to rise globally, the mismatch between charging demand and available supply has become increasingly prominent. Therefore, it is imperative to accelerate the construction of related facilities for electric vehicle charging station (EVCS). However, the unplanned and random location of EVCS can result in high investment costs, prolonged user queuing times, and a decrease in grid stability. To tackle these challenges, this work presents a multi-objective planning model for EVCS based on the spatial-temporal distribution of EV charging demand and traffic-grid coupling. First, a real-time traffic model is developed using the actual road network to simulate EV moving patterns. Then, the planning region is partitioned by analyzing point of interest data. Finally, an optimal EVCS planning model is designed with the objective of minimizing total costs, user dissatisfaction, and voltage fluctuations, based on predictions of charging demand considering both spatial and temporal variations. The proposed model is applied to the Kunming second ring road area and is solved using the multi-objective thermal exchange optimization (MOTEO) algorithm. Results demonstrate that, compared to the multi-objective Lichtenberg algorithm (MOLA), the proposed model reduces total costs by 11.92 %, user dissatisfaction by 19.64 %, and voltage fluctuations by 44 %.