基于出行链的电动汽车充电行为影响因素分析

随着电动汽车的快速发展，大规模电动汽车充电将给电力系统规划和运行带来不可忽视的影响，研究电动汽车的充电行为及其影响因素，并实时预测潜在的充电行为越发迫切。基于北京市私家电动汽车的历史车联网数据，引入出行链的概念，综合电动汽车充电过程和放电过程的数据，从实际出发考虑影响电动汽车充电行为的多种潜在因素，并通过logistic回归模型分析确定了显著影响充电行为的因素。分别基于单一和多个显著影响因素建立电动汽车充电行为的预测模型，预测结果表明，基于多个显著影响因素的模型准确率更高，且对晴天的预测效果更好。研究成果将有助于优化电动汽车的充电行为，进而提高电动汽车的充电效率。 

Influential factors analysis of electric vehicle charging behavior based on trip chain

With the rapid development of electric vehicles, large-scale electric vehicle charging behavior will bring tremendous influence on the planning and operation of electric power systems. It is more and more urgent to study the charging behavior of electric vehicles and its influential factors, and predict the potential charging behavior in real time. Based on the historical data of private electric vehicles in Beijing, this paper introduces the concept of trip chain to comprehensively analyze the data of electric vehicle charging process and discharge process. This research considers the various potential influential factors on electric vehicles' charging behavior in the actual situation and determines the factors that significantly affect charging behavior through logistic regression analysis. Finally, the charging behavior forecasting model for electric vehicle is established based on the single and multiple significant influential factors. The results show that the model based on multiple significant influential factors has higher accuracy and better prediction effect in sunny days. This research will help optimize the charging behavior of electric vehicles, thus improving the charging efficiency of electric vehicles.