Abstract
Accurate prediction of electric vehicle (EV) charging loads is a foundational step in the establishment of expressway charging infrastructures. This study introduces an approach to enhance the precision of expressway EV charging load predictions. The method considers both the battery dynamic state-of-charge (SOC) and user charging decisions. Expressway network nodes were first extracted using the open Gaode Map API to establish a model that incorporates the expressway network and traffic flow features. A Gaussian mixture model is then employed to construct a SOC distribution model for mixed traffic flow. An innovative SOC dynamic translation model is then introduced to capture the dynamic characteristics of traffic flow SOC values. Based on this foundation, an EV charging decision model was developed which considers expressway node distinctions. EV travel characteristics are extracted from the NHTS2017 datasets to assist in constructing the model. Differentiated decision-making is achieved by utilizing improved Lognormal and Sigmoid functions. Finally, the proposed method is applied to a case study of the Lian-Huo expressway. An analysis of EV charging power converges with historical data and shows that the method accurately predicts the charging loads of EVs on expressways, thus revealing the efficacy of the proposed approach in predicting EV charging dynamics under expressway scenarios.
