Spatial-Temporal Distribution Prediction of Charging Load for Electric Vehicles Based on Dynamic Traffic Information
Liangliang Chen, Fengkun Yang, Qiang Xing, Shengjun Wu, Ruisheng Wang, Jiachen Chen
Abstract
Charging load prediction of electric vehicles (EVs) is an important prerequisite for studying the interaction between electric vehicles and power grid. Aiming at the influence of traffic road network information on the driving rule of EVs, a spatial-temporal distribution prediction method of charging load for EVs based on dynamic traffic information is presented. In this methodology, given the characteristic of multiple intersections in the urban road network, a dynamic road network model with the impedance of the road section and the impedance of the node are established firstly. The corresponding interactive model of transportation network-distribution network is determined according to the scale of road network. And then, the origin destination (OD) matrix analysis method and the real-time Dijkstra dynamic path search algorithm are introduced to assign start-stop nodes and plan driving paths for EVs and simulate their dynamic driving process and charging behavior. At last, the EV path planning experiment and the charging load prediction experiment in typical regions are designed to verify the effectiveness and feasibility of the proposed strategy.