A PHET Dispatching Method Considering Customer Demand and Charging Resources

Plug-in electrical vehicles (PEVs) play a significant role in environment protection and attract global attentions. However, with the popularization of PEVs, low-efficiency supporting facilities such as the charging system impede its future development. To improve the charging system, we focus on plug-in hybrid electric taxis (PHETs) as they are the main users of public charging system. In this paper, we first predict the order numbers and mileage consumption of orders with the help of convolutional neural networks (CNNs). We then divide the area into 30 groups using K-means method and plan the charging capacity of station in each area. Two coordinated dispatching and charging strategies are proposed considering the states of charge (SOCs) at vehicle level and considering the real-time effect at region level, respectively. Finally, we test the dispatching effect using order car ratio (OCR) models at region level. The results show that it works quite well when testing on the real dataset. This method provides optimal instructions for PHETs to pick orders, satisfy their charging demand and also meet the order demands for taxis.