山东科学2026，Vol.39Issue(3)：22-32,11.DOI:10.3976/j.issn.1002-4026.2025061
多源数据驱动下公共充电站智能选址优化研究
Evaluation and location optimization of public charging stations using multisource spatiotemporal data
摘要
Abstract
With the increasing number of new energy vehicles globally,the density and spatial distribution of urban public charging infrastructure lag behind demand.Moreover,supply-demand imbalance has become an increasingly prominent issue,posing a key bottleneck in the development of green mobility.To address this challenge,this study considers Shunyi District,Beijing,as a case study to propose a comprehensive evaluation and location optimization method for public charging stations using multisource spatiotemporal data.By combining multisource spatiotemporal data such as vehicle trajectories and points of interest,we constructed a spatiotemporal distribution model of urban charging demand to accurately characterize the dynamic charging loads in different functional zones.Furthermore,through traffic accessibility analysis and charging behavior simulation,the effectiveness of the layout of the existing stations is quantitatively assessed and service blind spots are identified.The results reveal that the service capacity in some high-demand areas of Shunyi District is insufficient,with considerable coverage gaps.To overcome this issue,we used the K-means clustering algorithm to identify the cores of unmet demand and proposed a priority-based construction plan for new stations.This study provides a theoretical basis and a practical approach for mitigating regional supply-demand imbalances and enhancing the scientific layout and systemic adaptability of urban public charging facilities.关键词
充电站选址/布局优化方案/动态充电仿真/服务半径/充电需求分析Key words
charging station location/layout optimization plan/dynamic charging simulation/service radius/charging demand analysis分类
交通工程引用本文复制引用
何佳,胡艳磊,王涛..多源数据驱动下公共充电站智能选址优化研究[J].山东科学,2026,39(3):22-32,11.基金项目
国家自然科学基金项目(72371004,72231001) （72371004,72231001）
