1.上海交通大学电气工程学院,上海市 200240
2.上海市新能源汽车公共数据采集与监测研究中心,上海市 201805
3.国网上海市电力公司电力科学研究院,上海市 200437
尹文航(2002—),男,博士研究生,主要研究方向:电动汽车能量管理、电动汽车充电资源规划配置。E-mail:yinwenhang@sjtu.edu.cn
孙弢(1993—),男,博士,主要研究方向:电力系统气候风险与应对。E-mail:luke18@sjtu.edu.cn
冯冬涵(1981—),男,通信作者,博士,教授,博士生导师,主要研究方向:电力市场、车网互动。E-mail:seed@sjtu.edu.cn
收稿:2025-09-30,
修回:2026-04-23,
网络首发:2026-10-26,
移动端阅览
尹文航,孙弢,冯冬涵等.基于数据驱动的电动出租车充电需求概率估计与场景模拟[J/OL].电力系统自动化, http://dx.doi.org/10.7500/AEPS20250930008.
YIN Wenhang,SUN Tao,FENG Donghan,et al.Data-driven Probabilistic Estimation and Scenario Simulation of Charging Demand for Electric Taxis[J/OL].Automation of Electric Power Systems, http://dx.doi.org/10.7500/AEPS20250930008.
尹文航,孙弢,冯冬涵等.基于数据驱动的电动出租车充电需求概率估计与场景模拟[J/OL].电力系统自动化, http://dx.doi.org/10.7500/AEPS20250930008. DOI:
YIN Wenhang,SUN Tao,FENG Donghan,et al.Data-driven Probabilistic Estimation and Scenario Simulation of Charging Demand for Electric Taxis[J/OL].Automation of Electric Power Systems, http://dx.doi.org/10.7500/AEPS20250930008. DOI:
在交通电气化转型的大背景下,电动出租车作为城市公共交通的重要组成部分,其充电需求的准确建模估计对电力系统规划和城市能源管理至关重要。文中提出一种基于数据驱动的概率建模方法,用于大规模电动出租车充电负荷估计与长期规划。首先,通过分层建模捕捉充电需求的不确定性和随机性,包含3个要素:司机类群划分、充电场景分布、充电会话参数建模。基于上海市2023—2024年逾2.5万辆电动出租车的真实充电数据,采用凝聚聚类方法根据充电历史记录对司机进行分组,识别出13类具有异质性充电行为和偏好的司机类群,捕捉其在不同充电场景下的差异化特征。然后,运用概率混合模型刻画各司机类群在不同外部条件下的充电会话特征,识别各场景内的独特充电模式。最后,通过调整模型中代表司机类群分布、充电行为特征和场景分布概率的控制参数,构建了上海市电动出租车全面电气化、充电引导政策实施等多种场景下的充电需求估计。所提方法还复原了过去6年上海市电动出租车充电功率的演化历程,验证了模型的有效性和可扩展性,可为电动出租车运营调度、充电设施规划和智能电网优化提供实用的分析工具。
Against the backdrop of transportation electrification
electric taxis
as an important component of urban public transportation
require accurate modeling and estimation of their charging demand for power system planning and urban energy management. This paper proposes a data-driven probabilistic modeling method for charging load estimation and long-term planning of large-scale electric taxis. First
a hierarchical modeling approach is adopted to capture the uncertainty and randomness of charging demand
encompassing three elements: driver group classification
charging scenario distribution
and charging session parameter modeling. Based on real-world charging data from over 25 000 electric taxis in Shanghai spanning 2023—2024
the agglomerative clustering method is employed to group drivers according to their charging history
identifying 13 driver groups with heterogeneous charging behaviors and preferences
and capturing their differentiated characteristics across various charging scenarios. Next
the probabilistic mixture model is used to characterize the charging session features of each driver group under various external conditions
identifying unique charging patterns within each scenario. Finally
by adjusting the model control parameters representing driver cluster distributions
charging behavior characteristics
and charging scenario probabilities
this paper constructs charging demand estimates for multiple scenarios in Shanghai
including full electrification of the electric taxi fleet and the implementation of charging guidance policies. The proposed method also reconstructs the evolution of electric taxi charging power in Shanghai over the past six years
thereby validating its effectiveness and scalability. This study provides a practical analytical tool for electric taxi operation scheduling
charging infrastructure planning
and smart grid optimization.
国务院办公厅 . 国务院办公厅关于印发新能源汽车产业发展规划 ( 2021 — 2035 年)的通知[EB/OL].[ 2025-09-01 ]. https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm .
General Office of the State Council . Notice of the General Office of the State Council on issuing the development plan for the new energy vehicle industry ( 2021 — 2035 )[EB/OL]. [ 2025-09-01 ]. https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm .
上海市统计局 . 上海统计年鉴2024 [EB/OL].[ 2025-09-01 ]. https://tjj.sh.gov.cn/tjnj/nj24.htm?d1=2024tjnj/C0105.htm https://tjj.sh.gov.cn/tjnj/nj24.htm?d1=2024tjnj/C0105.htm .
Shanghai Municipal Bureau of Statistics . Shanghai statistical yearbook 2024 [EB/OL]. [ 2025-09-01 ]. https://tjj.sh.gov.cn/tjnj/nj24.htm?d1=2024tjnj/C0105.htm https://tjj.sh.gov.cn/tjnj/nj24.htm?d1=2024tjnj/C0105.htm .
刘超 , 李青 , 马明明 , 等 . 基于DATA模型的电动汽车充电需求时空演化规律分析 [J]. 电力系统自动化 , 2023 , 47 ( 12 ): 86 - 94 .
Liu Chao , Li Qing , Ma Mingming , et al . Analysis on spatial-temporal evolution law of electric vehicle charging demand based on dynamic activity-travel assignment model [J]. Automation of Electric Power Systems , 2023 , 47 ( 12 ): 86 - 94 .
张越 , 刘佳 , 陈哲 , 等 . “车-路-站-网”耦合下基于动态吸引聚合的多类型充电站合作博弈优化 [J]. 电网技术 , 2025 , 49 ( 12 ): 5101 - 5112 .
Zhang Yue , Liu Jia , Chen Zhe , et al . Cooperative game optimization of multi-type charging stations based on dynamic attraction aggregation under vehicle-road-station-grid coupling [J]. Power System Technology , 2025 , 49 ( 12 ): 5101 - 5112 .
Li Y J , Su S , Liu B , et al . Trajectory-driven planning of electric taxi charging stations based on cumulative prospect theory [J]. Sustainable Cities and Society , 2022 , 86 : 104125 .
Liu Z Y , Yin W H , Feng D H , et al . A framework for analyzing the spatiotemporal distribution of urban electric vehicle charging load: a case study of Shanghai [J]. Sustainable Cities and Society , 2025 , 127 : 106392 .
文欣 , 黄学良 , 高山 , 等 . 考虑区域差异性的电动私家车网格化充电需求预测 [J]. 电力系统自动化 , 2025 , 49 ( 7 ): 158 - 168 .
Wen Xin , Huang Xueliang , Gao Shan , et al . Grid charging demand forecasting for private electric vehicles considering regional differences [J]. Automation of Electric Power Systems , 2025 , 49 ( 7 ): 158 - 168 .
李宏伟 , 宋玉峰 , 李帅兵 , 等 . 基于ArcGIS路网结构与交通拥挤度分析的电动汽车充电负荷预测方法 [J]. 电网技术 , 2025 , 49 ( 5 ): 1920 - 1930 .
Li Hongwei , Song Yufeng , Li Shuaibing , et al . Electric vehicle charging load prediction based on ArcGIS road network structure and traffic congestion analysis [J]. Power System Technology , 2025 , 49 ( 5 ): 1920 - 1930 .
韩富佳 , 王晓辉 , 乔骥 , 等 . 基于人工智能技术的新型电力系统负荷预测研究综述 [J]. 中国电机工程学报 , 2023 , 43 ( 22 ): 8569 - 8591 .
Han Fujia , Wang Xiaohui , Qiao Ji , et al . Review on artificial intelligence based load forecasting research for the new-type power system [J]. Proceedings of the CSEE , 2023 , 43 ( 22 ): 8569 - 8591 .
Powell S , Cezar G V , Rajagopal R . Scalable probabilistic estimates of electric vehicle charging given observed driver behavior [J]. Applied Energy , 2022 , 309 : 118382 .
Kreft M , Brudermueller T , Fleisch E , et al . Predictability of electric vehicle charging: explaining extensive user behavior-specific heterogeneity [J]. Applied Energy , 2024 , 370 : 123544 .
Cai H M , Wang J W , Li B L , et al . Understanding the daily operations of electric taxis from macro-patterns to micro-behaviors [J]. Transportation Research Part D: Transport and Environment , 2024 , 128 : 104079 .
黄南天 , 孙赫宏 , 王圣元 , 等 . 计及多公共充电站差异化耦合关联的电动汽车充电负荷时-空短期预测 [J]. 中国电机工程学报 , 2025 , 45 ( 4 ): 1424 - 1435 .
Huang Nantian , Sun Hehong , Wang Shengyuan , et al . Short-term spatial-temporal forecasting of electric vehicle charging load with differentiated spatial-temporal coupling correlation of multiple public charging stations [J]. Proceedings of the CSEE , 2025 , 45 ( 4 ): 1424 - 1435 .
Wang K , Wang H X , Yang Z H , et al . A transfer learning method for electric vehicles charging strategy based on deep reinforcement learning [J]. Applied Energy , 2023 , 343 : 121186 .
Yin W J , Ji J B . Research on EV charging load forecasting and orderly charging scheduling based on model fusion [J]. Energy , 2024 , 290 : 130126 .
毛建斌 , 杨少兵 , 杨湘彦 , 等 . 基于有限混合模型的规模化电动汽车充电负荷在线预测方法 [J]. 电网技术 , 2025 , 49 ( 5 ): 1931 - 1940 .
Mao Jianbin , Yang Shaobing , Yang Xiangyan , et al . Charging load online forecasting method based on finite mixture model for large-scale electric vehicles [J]. Power System Technology , 2025 , 49 ( 5 ): 1931 - 1940 .
朱永胜 , 常稳 , 武东亚 , 等 . 考虑充放储一体站与电动汽车互动的主从博弈优化调度策略 [J]. 电力系统保护与控制 , 2024 , 52 ( 7 ): 157 - 167 .
Zhu Yongsheng , Chang Wen , Wu Dongya , et al . A Stackelberg game optimization scheduling strategy considering the interaction between a charging-discharging-storage integrated station and an electric vehicle [J]. Power System Protection and Control , 2024 , 52 ( 7 ): 157 - 167 .
Callanan A , Samuelsson O , Márquez-fernández F J . A data-driven probabilistic framework for estimating grid impacts of EV charging at scale [J]. International Journal of Electrical Power & Energy Systems , 2025 , 172 : 111204 .
杨隆 , 张沛超 , 赵建立 , 等 . 基于出行大数据的电动汽车集群灵活性推演方法 [J]. 电力自动化设备 , 2025 , 45 ( 4 ): 84 - 91 .
Yang Long , Zhang Peichao , Zhao Jianli , et al . Flexibility inference method for electric vehicle cluster based on travel big data [J]. Electric Power Automation Equipment , 2025 , 45 ( 4 ): 84 - 91 .
Li X H , Wang Z P , Zhang L , et al . Electric vehicle charging flexibility assessment for load shifting based on real-world charging pattern identification [J]. ETransportation , 2025 , 23 : 100367 .
张美霞 , 孙铨杰 , 杨秀 . 考虑多源信息实时交互和用户后悔心理的电动汽车充电负荷预测 [J]. 电网技术 , 2022 , 46 ( 2 ): 632 - 641 .
Zhang Meixia , Sun Quanjie , Yang Xiu . Electric vehicle charging load prediction considering multi-source information real-time interaction and user regret psychology [J]. Power System Technology , 2022 , 46 ( 2 ): 632 - 641 .
盛裕杰 , 郭庆来 , 刘梦洁 , 等 . 多源数据融合的用户充电行为分析与充电设施规划实践 [J]. 电力系统自动化 , 2022 , 46 ( 12 ): 151 - 162 .
Sheng Yujie , Guo Qinglai , Liu Mengjie , et al . User charging behavior analysis and charging facility planning practice based on multi-source data fusion [J]. Automation of Electric Power Systems , 2022 , 46 ( 12 ): 151 - 162 .
Huang W X , Wang J G , Wang J P , et al . EV charging load profile identification and seasonal difference analysis via charging sessions data of charging stations [J]. Energy , 2024 , 288 : 129771 .
Cai H M , Li B L , Li W , et al . Heterogeneity in electric taxi charging behavior: association with travel service characteristics [J]. Travel Behaviour and Society , 2025 , 38 : 100917 .
韩林阳 , 叶承晋 , 朱超 , 等 . 高温天气下计及用户意愿的城市充电负荷空间引导策略 [J]. 电力系统自动化 , 2024 , 48 ( 10 ): 139 - 150 .
Han Linyang , Ye Chengjin , Zhu Chao , et al . Spatial guidance strategy for urban charging loads in high-temperature weather considering user willingness [J]. Automation of Electric Power Systems , 2024 , 48 ( 10 ): 139 - 150 .
Wang W H , Tang A H , Wei F , et al . Electric vehicle charging load forecasting considering weather impact [J]. Applied Energy , 2025 , 383 : 125337 .
Jiang C X , Jing Z X , Cui X R , et al . Multiple agents and reinforcement learning for modelling charging loads of electric taxis [J]. Applied Energy , 2018 , 222 : 158 - 168 .
Yu Q , Wang Z , Song Y C , et al . Potential and flexibility analysis of electric taxi fleets V2G system based on trajectory data and agent-based modeling [J]. Applied Energy , 2024 , 355 : 122323 .
Xu R , Wunsch D C Ⅱ . Clustering [M]. New York, USA : John Wiley & Sons , 2008 .
Murtagh F , Legendre P . Ward’s hierarchical agglomerative clustering method: which algorithms implement Ward’s criterion? [J]. Journal of classification , 2014 , 31 ( 3 ): 274 - 295 .
Nylund K L , Asparouhov T , Muthén B O . Deciding on the number of classes in latent class analysis and growth mixture modeling: a Monte Carlo simulation study [J]. Structural Equation Modeling: A Multidisciplinary Journal , 2007 , 14 ( 4 ): 535 - 569 .
上海市交通委员会 . 《上海市交通领域大规模设施设备更新专项工作方案(2024—2027年)》 [EB/OL].[ 2025-09-01 ]. https://jtw.sh.gov.cn/zxzfxx/20240807/bed10307ddbc461096c86ec51774721e.html https://jtw.sh.gov.cn/zxzfxx/20240807/bed10307ddbc461096c86ec51774721e.html .
Shanghai Municipal Transportation Commission . Special Work Plan for Large-Scale Facility and Equipment Upgrades in the Transportation Sector ( 2024 — 2027 )" [EB/OL]. [ 2025-09-01 ]. https://jtw.sh.gov.cn/zxzfxx/20240807/bed10307ddbc461096c86ec51774721e.html https://jtw.sh.gov.cn/zxzfxx/20240807/bed10307ddbc461096c86ec51774721e.html .
中国电动汽车充电基础设施促进联盟 . 《2024年全国电动汽车充换电基础设施运行情况》 [EB/OL].[ 2025-09-01 ]. https://www.evcipa.org.cn/newsinfo/8137834.html https://www.evcipa.org.cn/newsinfo/8137834.html .
China Electric Vehicle Charging Infrastructure Promotion Alliance . Operation of national electric vehicle charging and swapping infrastructure in 2024 [EB/OL]. [ 2025-09-01 ]. https://www.evcipa.org.cn/newsinfo/8137834.html https://www.evcipa.org.cn/newsinfo/8137834.html .
上海市交通委员会 . 《市交通委关于新能源出租车及其相关充电设施数据的答复》 [EB/OL].[ 2025-09-01 ]. https://jtw.sh.gov.cn/ysqgkzzdgk/20220914/014fd0fc14d14589a553373c7d40d73d.html https://jtw.sh.gov.cn/ysqgkzzdgk/20220914/014fd0fc14d14589a553373c7d40d73d.html .
Shanghai Municipal Transportation Commission . Reply of the municipal transportation commission on data of new energy taxis and related charging facilities [EB/OL]. [ 2025-09-01 ]. https://jtw.sh.gov.cn/ysqgkzzdgk/20220914/014fd0fc14d14589a553373c7d40d73d.html https://jtw.sh.gov.cn/ysqgkzzdgk/20220914/014fd0fc14d14589a553373c7d40d73d.html .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621