广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (03): 1-7.doi: 10.12052/gdutxb.210158

• •    下一篇

GeoHash与KNN在共享单车停靠点优化选择中的应用

王小霞, 欧阳露, 郑诗琪, 胡三根, 韩霜   

  1. 广东工业大学 土木与交通工程学院, 广东 广州 510006
  • 收稿日期:2021-10-24 出版日期:2022-05-10 发布日期:2022-05-19
  • 通信作者: 胡三根(1989-),男,讲师,博士,主要研究方向为交通系统建模与仿真等,E-mail:husangen2010@163.com
  • 作者简介:王小霞(1981-)，女，副教授，博士，主要研究方向为土木水利与交通土建工程
  • 基金资助:
    国家自然科学基金青年基金资助项目(61803092，718010520)

Application of GeoHash and KNN in the Optimization Selection of Shared Bicycle Stops

Wang Xiao-xia, Ouyang Lu, Zheng Shi-qi, Hu San-gen, Han Shuang   

  1. School of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2021-10-24 Online:2022-05-10 Published:2022-05-19

HTML

PDF (PC)

2467

摘要： 针对共享单车停靠点供需时空失衡、潮汐效应明显、优化选择水平低的问题，本文把区域编码与分类学习方法相结合，提出一种基于GeoHash与K最近邻模型(K Nearest Neighbor model，KNN)的共享单车停靠点优化选择方法。首先，在分析现有共享单车停靠问题的基础上，利用GeoHash算法的区域编码分割，得到停靠点空间分布；然后，在停靠点可供选择数量和可容纳车辆数量的双重约束条件下，利用KNN聚类算法进行二次划分，完成共享单车停靠点的优化选择；最后，利用厦门市思明区和湖里区共享单车数据进行综合评价。研究结果表明，该方法具有一定的合理性，能够为缓解共享单车停靠点潮汐现象提供有益借鉴。

关键词: 共享单车, 停靠点优化, GeoHash编码, KNN算法, 潮汐现象

Abstract: To deal with the problems of time-space imbalance between supply and demand of shared bicycle stops, obvious tidal effect and low level of optimization selection, by combining region coding with classification learning method, an optimal selection method of shared bicycle stops is proposed based on GeoHash and KNN. Firstly, based on the analysis of the existing shared bicycle parking problem, the spatial distribution of parking points is obtained by using the region coding segmentation of GeoHash algorithm. Then, under the double constraints of the number of stops and the bicycles that can be accommodated, the KNN clustering algorithm is used for secondary division to complete the optimal selection of shared bicycle stops. Finally, a comprehensive evaluation is carried out based on the shared bicycle data of Siming District and Huli District in Xiamen. The result shows that this method is reasonable, which can provide a useful reference for alleviating the tide phenomenon of shared bicycle stops.

Key words: shared bicycle, optimization of stops, GeoHash encoding, KNN algorithm, tide phenomenon

中图分类号: 

  • U121
[1] 岳宇君, 胡汉辉. 城市共享单车治理问题的多理论视角解析[J]. 当代经济管理, 2019, 41(7): 68-72.
YUE Y J, HU H H. An analysis of the governance of sharing bicycles in cities from the perspective of multiple theories [J]. Contemporary Economy & Management, 2019, 41(7): 68-72.
[2] 孙卓, 李一鸣. 考虑多仓库的共享单车重新配置问题研究[J]. 运筹与管理, 2021, 30(1): 121-129.
SUN Z, LI Y M. Solving a static bike repositioning problem with multiple depots[J]. Operations Research and Management Science, 2021, 30(1): 121-129.
[3] 刘永贤, 牛占文. 共享单车造成的城市治理问题研究[J]. 城市发展研究, 2021, 28(5): 135-140.
LIU Y X, NIU Z W. Research on urban governance problems caused by shared bikes [J]. Urban Development Studies, 2021, 28(5): 135-140.
[4] SHUI C S, SZETO W Y. A review of bicycle-sharing service planning problems [J]. Transportation Research Part C:Emerging Technologies, 2020, 117(C): 102648.
[5] HE M J, MA X Y, JIN Y C. Station importance evaluation in dynamic bike-sharing rebalancing optimization using an entropy-based TOPSIS approach [J]. IEEE Access, 2021, 9: 38119-38131.
[6] LIN J R, YANG T H. Strategic design of public bicycle sharing systems with service level constraints [J]. Transportation Research Part E:Logistics and Transportation Review, 2011, 4(47): 284-294.
[7] 孙文霞, 赵晓娟, 马晓静. 基于复杂网络理论的互联网租赁自行车-公交系统站的优化配置[J]. 公路交通科技, 2018, 35(10): 111-116.
SUN W X, ZHAO X J, MA X J. Optimal configuration of station of internet rental bicycle-transit system based on complex network theory [J]. Highway and Transportation Research and Development, 2018, 35(10): 111-116.
[8] 靳爽, 庞明宝. 考虑共享单车的城市轨道交通社区接驳规划与公交调度综合优化[J]. 公路交通科技, 2020, 37(2): 123-129.
JIN S, PANG M B. Integrated optimization of community connection planning and bus dispatching for urban rail transit considering shared bicycle [J]. Highway and Transportation Research and Development, 2020, 37(2): 123-129.
[9] ERDOGAN G, BATTARRA M, CALVO R W. An exact algorithm for the static rebalancing problem arising in bicycle sharing systems [J]. European Journal of Operational Research, 2015, 245(3): 667-679.
[10] 刘嘉文, 代颖, 杨斐, 等. 共享单车停放点联合覆盖选址及车辆配置模型[J]. 工业工程与管理, 2020, 25(1): 127-135.
LIU J W, DAI Y, YANG F, et al. A cooperative covering model for location of bike sharing stations and its fleet deployment [J]. Industrial Engineering and Management, 2020, 25(1): 127-135.
[11] AHMED A, KADRE, IMDE K, et al. Lower and upper bounds for scheduling multiple balancing vehicles in bicycle-sharing systems [J]. Soft Computing, 2019, 23(14): 5945-5966.
[12] 靳爽, 庞明宝. 基于K-means的城市轨道交通社区接驳共享单车停靠点规划[J]. 科学技术与工程, 2019, 19(30): 343-347.
JIN S, PANG M B. Planning of shared bicycle stop for urban rail transit community connection based on K-means [J]. Science Technology and Engineering, 2019, 19(30): 343-347.
[13] HUANG K, LI G Q, WANG J. Rapid retrieval strategy for massive remote sensing metadata based on GeoHash coding [J]. Remote Sensing Letters, 2018, 9(11): 1070-1078.
[14] 金安, 程承旗, 宋树华, 等. 基于GeoHash的面数据区域查[J]. 地理与地理信息科学, 2013, 29(5): 31-35.
JIN A, CHENG C Q, SONG S H, et al. Regional query of area data based on GeoHash [J]. Geography and Geo-information Science, 2013, 29(5): 31-35.
[15] MA C C, DU X H, CAO L F. Improved KNN algorithm for fine-grained classification of encrypted network flow [J]. Electronics, 2020, 9(2): 324.
[16] NGUYEN G B, LE H H, TRAN H H. Improvement of K-nearest neighbors (KNN) algorithm for network intrusion detection using Shannon-Entropy [J]. Journal of Communications, 2021, 16(8): 347-354.
[1] 邹丽娜，凌捷. 一种基于特征提取的二级文本分类方法[J]. 广东工业大学学报, 2012, 29(4): 65-68.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发