基于订单数据的网约车充电行为驱动因素及非线性效应

doi:10.16097/j.cnki.1009-6744.2024.06.015

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (6): 169-178.DOI: 10.16097/j.cnki.1009-6744.2024.06.015

基于订单数据的网约车充电行为驱动因素及非线性效应

尹超英¹，桂晨¹，邵春福²，王菁³，王晓全^*4

1. 南京林业大学，汽车与交通工程学院，南京210037；2.新疆大学，新疆交通基础设施绿色建养与智慧交通管控重点实验室，乌鲁木齐830017；3.北京交通大学，综合交通运输大数据应用技术交通运输行业重点实验室，北京100044；4.河海大学，土木与交通学院，南京210098

收稿日期:2024-07-05 修回日期:2024-09-26 接受日期:2024-10-16 出版日期:2024-12-25 发布日期:2024-12-18
作者简介:尹超英(1989- )，女，山西五寨人，副教授，博士。
基金资助:
国家自然科学基金 (52202388, 72204114)；教育部人文社科项目(22YJC630191)。

Impact Factors and Nonlinear Effects of Ride-hailing Charging Behavior Based on Order Data

YIN Chaoying¹,GUI Chen¹,SHAO Chunfu²,WANG Jing³,WANG Xiaoquan^*4

1. College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China; 2. Xinjiang Key Laboratory of Green Construction and Smart Traffic Control of Transportation Infrastructure, Xinjiang University, Urumqi 830017, China; 3. Key Laboratory of Transport Industry of Big DataApplication Technologies for Comprehensive Transport, Beijing Jiaotong University, Beijing 100044, China; 4. College of Civil and Transportation Engineering, Hohai University, Nanjing 210098, China

Received:2024-07-05 Revised:2024-09-26 Accepted:2024-10-16 Online:2024-12-25 Published:2024-12-18
Supported by:
NationalNaturalScienceFoundation of China (52202388, 72204114)；Humanities and Social Sciences Fund of Ministry of Education of China (22YJC630191)。

摘要/Abstract

摘要： 为探究建成环境对电动网约车的充电行为驱动因素和非线性效应，本文以南京市网约车为例，提出一种基于订单数据的电动网约车充电行为识别算法，从密度、多样性、设计、目的可达性和公交临近度这5个维度构建建成环境指标，利用XGBoost模型和SHAP(SHAPleyadditive explanatory)值算法，识别影响电动网约车充电行为的关键因素，分析各因素与网约车充电行为之间的潜在非线性关系。同时，本文将该模型拟合回归效果与随机森林(RF)和LightGBM进行比较，以验证XGBoost模型在拟合回归效果上的优势。结果表明：XGBoost模型的拟合效果优于其他模型，具有最小的预测误差波动和最高的R2值(0.446)。在影响网约车充电行为的建成环境因素中，餐馆数量、与市中心的距离和休闲娱乐设施数量对网约车充电行为影响最大，对充电行为的贡献度超过75%。此外，建成环境各因素对网约车充电行为均存在非线性效应，到市中心的距离对充电行为的影响呈现先正后负的反馈特征，其余变量对充电行为的影响则呈现先负后正的反馈特征。

关键词: 城市交通, 非线性效应, 机器学习, 网约车充电行为, 公共充电站规划

Abstract: This paper investigates the impact factors and nonlinear effects of charging behavior for electric ride-hailing vehicles in the built environment which is an important part of public charging station planning and operation. Based on the ride-hailing order data from Nanjing city, this paper develops an algorithm to identify charging behavior for electric ride-hailing vehicles and proposes ten built environment indicators from five dimensions: density, diversity, design, destination accessibility, and proximity to public transportation. The key impact factors on the charging behavior of electric ride-hailing vehicles are identified using the XGBoost model and Shapley additive explanation (SHAP) value algorithm, and the potential nonlinear relationships between these factors and charging behavior are further analyzed. Additionally, the model's fitting performance is compared with Random Forest (RF) and LightGBM to validate the effectiveness of the XGBoost model in regression fitting. The results show that the XGBoost model has better performance compared with traditional models, with smaller prediction error fluctuation and higher R2 (0.446) than the traditional models. The number of restaurants, distance from the city center, and the number of leisure and entertainment facilities are found to have the most significant impacts on charging behavior. Moreover, all built environment factors show nonlinear effects on the charging behavior, with the distance to the city center showing apositive impact at the beginning and then becomes negative, while other variables exhibit a negative impact at the beginning and then becomes positive.

Key words: urban traffic, nonlinear effects, machine learning, ride-hailing charging behavior, public charging station planning

中图分类号:

U121

尹超英, 桂晨, 邵春福, 王菁, 王晓全. 基于订单数据的网约车充电行为驱动因素及非线性效应[J]. 交通运输系统工程与信息, 2024, 24(6): 169-178.

YIN Chaoying, GUI Chen, SHAO Chunfu, WANG Jing, WANG Xiaoquan. Impact Factors and Nonlinear Effects of Ride-hailing Charging Behavior Based on Order Data[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 169-178.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.06.015

http://www.tseit.org.cn/CN/Y2024/V24/I6/169

参考文献

[1]马健霄,赵飞燕,尹超英,等.建成环境和出租车需求对网约车出行需求影响的时空间分异模式[J].交通运输系统工程与信息,2023, 23 (5): 136-145. [MA J X, ZHAO F Y, YIN C Y, et al. Spatiotemporal differentiation patterns of the influence of built environment and taxi demand on online car-hailing demand [J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23 (5): 136-145.]

[2] YANG X, ZHUGE C, SHAO C, et al. Characterizing mobility patterns of private electric vehicle users with trajectory data[J]. Applied Energy, 2022, 321: 119417.

[3] TAL G, CHAKRABORTY D, JENN A, et al. Factors affecting demand for plug-in charging infrastructure: An analysis of plug-in electric vehicle commuters[R]. Davis: University of California Institute of Transportation Studies, 2019.

[4] WU H, NIU D. Study on influence factors of electric vehicles charging station location based on ISM and FMICMAC[J]. Sustainability, 2017, 9(4): 484.

[5] YI T, ZHANG C, LIN T, et al. Research on the spatial temporal distribution of electric vehicle charging load demand: A case study in China[J]. Journal of Cleaner Production, 2020, 242: 118457.

[6]阎春利,刘嘉玲,陈爽.考虑空间分布的电动出租车中长期充电需求预测[J].武汉理工大学学报,2023, 45(11): 106-114, 131. [YAN C L, LIU J L, CHEN S. Medium-and long-term charging demand forecast of electric taxis considering spatial distribution [J]. Journal of Wuhan University of Technology, 2023, 45(11): 106 114, 131.]

[7]鲍琼,谭旭,屈琦凯,等.基于用户时空活动与模糊决策的电动汽车充电需求预测[J].东南大学学报(自然科学版), 2022, 52(6): 1209-1218. [BAO Q, TAN X, QU Q K, et al. Charging demand forecast of electric vehicles based on user spatiotemporal activities and fuzzy decision [J]. Journal of Southeast University (Natural Science Edition), 2022, 52(6): 1209-1218.]

[8] SHAHRIAR S, AL-ALI A R, OSMAN A H, et al. Machine learning approaches for EV charging behavior: Areview[J]. IEEE Access, 2020, 8: 168980-168993.

[9] MORTIMER B J, HECHT C, GOLDBECK R, et al. Electric vehicle public charging infrastructure planning using real-world charging data[J]. World Electric Vehicle Journal, 2022, 13(6): 94.

[10] ALMAGHREBI A, ALJUHESHI F, RAFAIE M, et al. Data-driven charging demand prediction at public charging stations using supervised machine learning regression methods[J]. Energies, 2020, 13(16): 4231.

[11] DING C, CAO X, WANG Y. Synergistic effects of the built environment and commuting programs on commute mode choice[J]. Transportation Research Part A: Policy and Practice, 2018, 118: 104-118.

[12] GUO C, JIANG Y, QIAO R, et al. The nonlinear relationship between the active travel behavior of older adults and built environments: A comparison between an inner-city area and a suburban area[J]. Sustainable Cities and Society, 2023, 99: 104961.

[13] CAI H, WU F, CHENG Z, et al. A large-scale empirical study on impacting factors of taxi charging station utilization[J]. Transportation Research Part D: Transport and Environment, 2023, 118: 103687.

[14] LEI T, GUO S, QIAN X, et al. Understanding charging dynamics of fully-electrified taxi services using large scale trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2022, 143: 103822.

[15] GUO Y, QIAN X, LEI T, et al. Modeling the preference of electric shared mobility drivers in choosing charging stations[J]. Transportation Research Part D: Transport and Environment, 2022, 110: 103399.

[16] LI J, LIU Z, WANG X. Public charging station location determination for electric ride-hailing vehicles based on an improved genetic algorithm[J]. Sustainable Cities and Society, 2021, 74: 103181.

[17] WANG G, LI W, ZHANG J, et al. Sharedcharging: Data driven shared charging for large-scale heterogeneous electric vehicle fleets[J]. Proceedings of the ACM on Interactive, Mobile, Wearable Technologies, 2019, 3(3): 1-25.

基于订单数据的网约车充电行为驱动因素及非线性效应

Impact Factors and Nonlinear Effects of Ride-hailing Charging Behavior Based on Order Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	翁剑成, 周慧缘, 张梦媛, 于江波. 考虑城市与群体异质的新能源车激励策略有效性研究[J]. 交通运输系统工程与信息, 2025, 25(1): 2-14.
[2]	李熙莹, 卢美燕, 何兆成, 苏淑妍, 庞淑敏. 基于车辆动态行为特征的交通状态识别研究[J]. 交通运输系统工程与信息, 2025, 25(1): 44-55.
[3]	王连震, 马志飞, 程国柱, 郑夫水. 城市道路智能网联汽车专用车道设置研究[J]. 交通运输系统工程与信息, 2025, 25(1): 56-66.
[4]	左忠义, 刘泽宇, 杨广川. 基于引力影响模型的轨道交通网络关键节点识别研究[J]. 交通运输系统工程与信息, 2025, 25(1): 102-112.
[5]	贾富强, 李恺强, 李引珍, 马成正, 冯子婷. 考虑碳交易的快慢车时刻表与停站方案综合优化[J]. 交通运输系统工程与信息, 2025, 25(1): 113-121.
[6]	杨雯雯, 孟学雷, 高如虎, 林立. 考虑运能利用和碳排放的绿色城轨开行方案研究[J]. 交通运输系统工程与信息, 2025, 25(1): 122-132.
[7]	田志强, 王付霞, 连惠, 靳欣妮, 孙国锋. 限定便乘位置的城轨乘务排班计划编制方法研究[J]. 交通运输系统工程与信息, 2025, 25(1): 133-145.
[8]	许得杰, 钟苗苗, 巩亮, 惠昌武, 曾俊伟. 基于动态安全间隔的城轨大小交路列车运行仿真研究[J]. 交通运输系统工程与信息, 2025, 25(1): 146-159.
[9]	龙科军, 邹道兴, 刘洋, 马昌喜, 马璐. 应急车路径与专用道协同优化的双层规划方法[J]. 交通运输系统工程与信息, 2025, 25(1): 202-211.
[10]	缪鸿志, 李嘉威, 李江晨, 贾洪飞, 李振福, 李歆蔚. 复杂度学习驱动的无人电卡集疏运路径优化[J]. 交通运输系统工程与信息, 2025, 25(1): 270-288.
[11]	王明智, 金敬东, 董春娇, 李鹏辉, 王菁, 王君悦. 出租车碳排放时空分布特征及减排潜力评估[J]. 交通运输系统工程与信息, 2025, 25(1): 311-318.
[12]	唐继孟, 张磊, 李建, 朱永祥, 蔡路, 余岳. 基于电子路票与连接道路的绕城高速缓解市区交通拥堵方案研究[J]. 交通运输系统工程与信息, 2025, 25(1): 331-344.
[13]	赵明玺, 马昌喜, 麻存瑞. 事件干扰下的城市轨道交通客流诱导优化研究[J]. 交通运输系统工程与信息, 2024, 24(6): 76-85.
[14]	梁金鹏, 赵莲芳, 李利鸣, 郑建风, 宋达宽. 兼顾效率与公平的城市轨道交通客流控制优化[J]. 交通运输系统工程与信息, 2024, 24(6): 102-112.
[15]	彭其渊, 江山, 刘思源, 石俊刚, 李登辉, 张永祥. 多干扰下地铁列车运行与车底周转一体化调整优化[J]. 交通运输系统工程与信息, 2024, 24(6): 113-125.