计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (12): 71-80.doi: 10.11896/jsjkx.250200010

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于智联电动车流量生成的跨区域换电站部署算法

陈佳怡1, 顾丞毅1, 周继华2, 赵涛2,3, 王双超4, 朱明星5, 向朝参1   

  1. 1 重庆大学计算机学院 重庆 401331
    2 西南大学计算机与信息科学学院软件学院 重庆 400715
    3 重庆大学微电子与通信工程学院 重庆 401331
    4 中移物联网有限公司 重庆 401121
    5 航天新通科技有限公司 重庆 401332
  • 收稿日期:2025-02-05 修回日期:2025-06-22 出版日期:2025-12-15 发布日期:2025-12-09
  • 通讯作者: 赵涛(zwindt@swu.edu.cn)
  • 作者简介:(jiayichen@stu.cqu.edu.cn)

Cross-regional Battery Swapping Station Deployment Algorithm Based on Intelligent E-scooterFlow Generation

CHEN Jiayi1, GU Chengyi1, ZHOU Jihua2, ZHAO Tao2,3, WANG Shuangchao4, ZHU Mingxing5, XIANG Chaocan1   

  1. 1 College of Computer Science, Chongqing University, Chongqing 401331, China
    2 School of Software, College of Computer and Information Science, Southwest University, Chongqing 400715, China
    3 School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 401331, China
    4 China Mobile IOT Company Limited, Chongqing 401121, China
    5 Aerospace New Generation Communications Company Limited, Chongqing 401332, China
  • Received:2025-02-05 Revised:2025-06-22 Published:2025-12-15 Online:2025-12-09
  • About author:CHEN Jiayi,born in 2000,postgra-duate.Her main research interests include urban computing and edge computing.
    ZHAO Tao,born in 1983,professor,master’s supervisor.His main research interests include IoT networks and broadband intelligent communications.

PDF (PC)

13

摘要： 随着换电模式的兴起,以智联电动车为主要交通工具的短途出行方式变得越来越流行,这促使提供换电服务的公司在城市中不断扩张业务规模。扩张时,公司倾向于在用户活跃度较高的区域设置换电站,活跃度水平可以通过智联电动车区域流量来体现。然而,在实际部署换电站之前,新区域的运营数据缺乏,使得依赖历史数据进行部署优化的数据驱动方法难以发挥作用,形成“数据缺失—难以部署—无法获取数据”的循环困境。对此,提出了一种基于智联电动车流量生成的跨区域换电站部署算法。首先,构建基于去噪扩散概率模型的区域流量生成模型,捕捉区域流量时空特征,利用已部署区域的数据来生成待部署区域的数据。然后,将区域流量纳入换电站部署问题,构建最大化换电站部署效益的优化模型。最后,基于自适应遗传特性做出跨区域换电站部署决策。基于四川省成都市真实换电数据集对所提算法进行了性能评估,实验结果验证了所提解决方案的有效性。

关键词: 换电模式, 换电站部署, 区域流量, 去噪扩散概率模型

Abstract: Battery swapping services are becoming increasingly popular as intelligent E-scooters emerge as a primary mode of short-distance transportation.As a result,companies providing battery swapping services are expanding their operations in urban regions.During expansion,companies prioritize deploying battery swapping stations in regions with higher user activity,as indicated by intelligent E-scooter flow.However,the lack of operational data in new regions makes data-driven deployment optimization approaches less effective,creating a dilemma of “data scarcity-deployment difficulty-lack of data acquisition”.To address this issue,this paper proposes a cross-regional battery swapping station deployment algorithm based on intelligent E-scooter flow ge-neration.Firstly,a regional flow generation model based on a denoising diffusion probabilistic model is constructed to capture the spatiotemporal characteristics of flow and generate synthetic flow data for target regions using data from already deployed regions.Then,the generated flow is incorporated into a deployment optimization problem,modeled to maximize the overall benefit of station deployment.Finally,a cross-regional deployment strategy is derived using an adaptive genetic algorithm.The proposed algorithm is evaluated using a real-world dataset from Chengdu,Sichuan Province.Experimental results demonstrate the effectiveness of the proposed solution.

Key words: Battery swapping model, Battery swapping station deployment, Regional flow, Denoising diffusion probabilistic model

中图分类号: 

  • TP393
[1]As social ownership reaches 350 million units, three ministries will jointly release a list of compliant e-scooter enterprises.[EB/OL].(2024-05-08) [2024-10-09].https://baijiahao.baidu.com/s?id=1798469716536620755&wfr=spider&for=pc.
[2]How much do you know about the fire safety risks of e-scooters?[EB/OL].(2024-12-20) [2024-10-20].https://baijiahao.baidu.com/s?id=1815601399691677843&wfr=spider&for=pc.
[3]ZHOU E,LI Z,LIU D,et al.Balancing Electric Scooter Battery Swapping Network by Spatio-Temporal Recommendation [J].IEEE Transactions on Intelligent Transportation Systems,2024,25(12):21315-21326.
[4]Gogoro Network upgrades battery swapping ecosystem,targe-ting 94% coverage across Taiwan by 2024.[EB/OL].(2023-10-04) [2025-03-10].https://baijiahao.baidu.com/s?id=1778807649215044254&wfr=spider&for=pc.
[5]WANG Y,ZHAO D,REN Y,et al.SPAP:Simultaneous demand prediction and planning for electric vehicle chargers in a new city [J].ACM Transactions on Knowledge Discovery from Data,2023,17(4):1-25.
[6]HO J,SALIMANS T,GRITSENKO A,et al.Video diffusionmodels [J].Advances in Neural Information Processing Systems,2022,35:8633-8646.
[7]BATZOLIS G,STANCZUK J,SCHÖNLIEB C B,et al.Conditional image generation with score-based diffusion models [J].arXiv:2111.13606,2021.
[8]LI X,THICKSTUN J,GULRAJANI I,et al.Diffusion-lm im-proves controllable text generation [C]//Proceedings of the 36th International Conference on Neural Information Processing System.2022:4328-4343.
[9]AUSTIN J,JOHNSON D D,HO J,et al.Structured denoising diffusion models in discrete state-spaces [C]//Proceedings of the 35th International Conference on Neural Information Processing Systems.2021:17981-17993.
[10]TASHIRO Y,SONG J,SONG Y,et al.Csdi:Conditional score-based diffusion models for probabilistic time series imputation [C]//NeurIPS 2021.2021:24804-24816.
[11]YAN T,ZHANG H,ZHOU T,et al.Scoregrad:Multivariateprobabilistic time series forecasting with continuous energy-based generative models [J].arXiv:2106.10121,2021.
[12]CHEN N,ZHANG Y,ZEN H,et al.Wavegrad:Estimating gradients for waveform generation [J].arXiv:2009.00713,2020.
[13]POPOV V,VOVK I,GOGORYAN V,et al.Grad-tts:A diffusion probabilistic model for text-to-speech[C]//Proceedings of International Conference on Machine Learning.PMLR,2021:8599-8608.
[14]HUANG H,SUN L,DU B,et al.Graphgdp:Generative diffusion processes for permutation invariant graph generation[C]//Proceedings of 2022 IEEE International Conference on Data Mining(ICDM).IEEE,2022:201-210.
[15]NIU C,SONG Y,SONG J,et al.Permutation invariant graphgeneration via score-based generative modeling[C]//Procee-dings of International Conference on Artificial Intelligence and Statistics.PMLR,2020:4474-4484.
[16]The battery swapping industry for e-scooters is poised formore intelligent and refined development[EB/OL].(2023-06-20) [2024-11-21].https://baijiahao.baidu.com/s?id=1769188866287918201&wfr=spider&for=pc.
[17]LI K,ZHANG Y,DU C,et al.Dynamic Programming-Based Optimal Charging Scheduling for Electric Vehicles[C]//Procee-dings of 2022 IEEE 7th International Conference on Intelligent Transportation Engineering(ICITE).IEEE,2022:545-550.
[18]XIONG Y,GAN J,AN B,et al.Optimal electric vehicle fast charging station placement based on game theoretical framework [J].IEEE Transactions on Intelligent Transportation Systems,2017,19(8):2493-2504.
[19]LI Y,LUO J,CHOW C Y,et al.Growing the charging station network for electric vehicles with trajectory data analytics[C]//Proceedings of 2015 IEEE 31st International Conference on Data Engineering.IEEE,2015:1376-1387.
[20]DU B,TONG Y,ZHOU Z,et al.Demand-aware charger plan-ning for electric vehicle sharing[C]//Proceedings of Proceedings of the 24th ACM SIGKDD International Conference on Know-ledge Discovery & Data Mining.2018:1330-1338.
[21]VON WAHL L,TEMPELMEIER N,SAO A,et al.Reinforcement learning-based placement of charging stations in urban road networks[C]//Proceedings of Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2022:3992-4000.
[22]BAE S,JANG I,GROS S,et al.A game approach for charging station placement based on user preferences and crowdedness [J].IEEE Transactions on Intelligent Transportation Systems,2020,23(4):3654-3669.
[23]WANG L,GENG X,MA X,et al.Cross-city transfer learningfor deep spatio-temporal prediction [J].arXiv:1802.00386,2018.
[24]ZHANG S,LI T,HUI S,et al.Deep transfer learning for city-scale cellular traffic generation through urban knowledge graph[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2023:4842-4851.
[25]RONG C,DING J,LIU Z,et al.Complexity-aware large scale origin-destination network generation via diffusion model [J].arXiv:2306.04873,2023.
[26]LI J,XIAO Y,WU J,et al.Attentive dual-head spatial-temporal generative adversarial networks for crowd flow generation[C]//Proceedings of 2022 IEEE 33rd Annual International Sympo-sium on Personal,Indoor and Mobile Radio Communications(PIMRC).IEEE,2022:800-806.
[27]Who are the main users of battery swapping services for e-scooters? What market needs do they address?[EB/OL].(2024-01-05) [2024-11-21].https://baijiahao.baidu.com/s?id=1787232553503955719&wfr=spider&for=pc.
[28]ZHOU Z,DING J,LIU Y,et al.Towards generative modeling of urban flow through knowledge-enhanced denoising diffusion[C]//Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems.2023:1-12.
[29]HO J,JAIN A,ABBEEL P.Denoising diffusion probabilisticmodels [J].arXiv.2006.11239,2020.
[30]HAN X,ZHENG H,ZHOU M.Card:Classification and regression diffusion models [J].arXiv:2206.07275,2022.
[31]LIU Y,DING J,FU Y,et al.Urbankg:An urban knowledgegraph system [J].ACM Transactions on Intelligent Systems and Technology,2023,14(4):1-25.
[32]BALAŽEVIĆI,ALLEN C,HOSPEDALES T M.Tucker:Tensor factorization for knowledge graph completion [J].arXiv:1901.09590,2019.
[33]KONG Z,PING W,HUANG J,et al.Diffwave:A versatile diffusion model for audio synthesis [J].arXiv:2009.09761,2020.
[34]HOCHBA D S.Approximation algorithms for NP-hard pro-blems [J].ACM Sigact News,1997,28(2):40-52.
[35]SRINIVAS M,PATNAIK L M.Adaptive probabilities of crossover and mutation in genetic algorithms [J].IEEE Transactions on Systems,Man,and Cybernetics,2002,24(4):656-667.
[36]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative adversarial networks [J].Communications of the ACM,2020,63(11):139-144.
[37]ELMAN J L.Finding structure in time [J].Cognitive Science,1990,14(2):179-211.
[38]HOCHREITER S,SCHMIDHUBER J.Long Short-term Me-mory [J].Neural Computation,1997,9(8):1735-1780.
[39]ZHAO L,SHEN S,ZHAO Z.Planning decentralized battery-swapping recharging facilities for e-bike sharing systems [J].Sustainable Cities and Society,2024,101:105118.
[40]KOOLMAN G,STECCA M,BAUER P.Optimal battery energy storage system sizing for demand charge management in ev fast charging stations[C]//Proceedings of 2021 IEEE Transportation Electrification Conference & Expo(ITEC).IEEE,2021:588-594.
[41]LIU Z,ZHENG G,YU Y.Cross-city few-shot traffic forecasting via traffic pattern bank[C]//Proceedings of the 32nd ACM International Conference on Information and Knowledge Management.2023:1451-1460.
[42]MO J,GONG Z.Cross-city multi-granular adaptive transferlearning for traffic flow prediction [J].IEEE Transactions on Knowledge and Data Engineering,2022,35(11):11246-11258.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发