Deployment of Bus Stop for Commuters in Medium-sized Cities Based on Signaling Data
-
摘要: 大中型城市之间的手机通信基站密度和通勤出行结构不同，公交站点布设呈现出显著差异。在此背景下，研究了基于改进Mean Shift聚类算法的中型城市通勤公交站点优化方法。该方法采用荆州市中心城区信令数据中的通勤记录，以系统总成本（包括运营成本和乘客步行时间成本）作为主要评价指标。根据中心城区早高峰的通勤出行需求，制定通勤公交站点优化方案。通过对比优化结果和现有公交站点布局，验证了优化方法的有效性；比较不同聚类算法，证明改进的Mean Shift聚类算法的性能优越性；考虑基站和等时圈的影响，对比不同场景，证明了考虑二者影响的必要性。结果表明：①针对荆州市研究区域的早高峰出行需求，优化方法共设置28个公交站，乘客步行时间成本下降51.98%，系统总成本下降17.82%，表明本方法能够得到系统总成本更优的站点布设方案，有效减少研究区域内乘客步行时间成本；②与不同聚类算法的比较中，改进Mean Shift算法得到的方案有明显提升，系统总成本比K-means聚类算法下降8.73%，比近邻传播聚类算法（af-finity propagation，AP）下降2.48%；③与未考虑基站和等时圈影响的情况相比，本算法步行时间成本有所下降。上述指标表明改进Mean Shift聚类方法在聚类质量上优于其他方法，可以获得更优的公交站点布设方案，为中型城市的公交线路规划提供基础。
-
关键词:
- 交通规划 /
- 中型城市 /
- 公交站点布设 /
- 改进Mean Shift算法 /
- 信令数据
Abstract: Due to significant differences in density of base stations and travel patterns of commuters between medium and larger-sized cities, the deployment of bus stops shows notable variations. Based on this fact, a method for optimizing the deployment of bus stops for commuting in medium-sized cities is proposed, utilizing an improved Mean Shift clustering algorithm. Next, this method is adopted and tested based on the commuting records from the signaling data in the central area of Jingzhou, in which the main evaluation criterion is total system cost that encompasses both operating cost and walking time of passengers. Based on the commuter travel demand during the morning peak in the central area, an optimization scheme about deployment of bus stops for commuters is formulated. By comparing the results of the optimization scheme to the existing deployment of bus stops, the effectiveness of the optimization method is validated. Through a comparative analysis for different clustering algorithms, the superior performance of the improved Mean Shift algorithm is demonstrated. Additionally, by considering the influence of base stations and isochrones, the necessity of evaluating both factors in various scenarios is proved. The results show that: ①Based on the travel demand in the morning peak in the research area of Jingzhou, 28 bus stops are ob-tained, which results in a remarkable reduction of 51.98% in passenger walking time and a 17.82% decrease in the total system cost. This indicates the effectiveness of the optimization method in achieving a deployment scheme of bus stops with reduced total system cost and walking time of passengers. ②In comparison with different clustering algorithms, the solution obtained from the improved Mean Shift algorithm shows a significant enhancement. Specifically, the total system cost is 8.73% lower than that achieved using the K-means clustering algorithm and 2.48% lower than the Affinity Propagation clustering algorithm. ③When comparing scenarios with and without the consideration of base stations and isochronous circles, the results that considering these factors results in reduced walking time. These analyses highlight the superiority of the optimization method in terms of clustering quality and can provide valuable insights for planning of bus lines in medium-sized cities. -
表 1 信令数据格式
Table 1. Signaling data formats
信令数据字段 描述 用户IMSI 脱敏后移动用户唯一识别码 时间 信令记录产生时间 基站 信令记录产生基站名称 经度 基站位置经度 纬度 基站位置纬度 事件 产生信令记录的通信事件类型 
下载: 导出CSV
表 2 信令整合数据格式
Table 2. Integrated signaling data formats
信令数据字段 描述 用户IMSI 脱敏后移动用户唯一识别码 记录出发时间 出发记录产生时间 出发点基站 出发记录产生基站名称 出发点经度 出发基站位置经度 出发点纬度 出发基站位置纬度 记录到达时间 到达记录产生时间 到达点基站 到达记录产生基站名称 到达点经度 到达基站位置经度 到达点纬度 到达基站位置纬度 距离 记录点间直线距离 持续时长 记录点间持续时间 信令速度 距离与时间之商
下载: 导出CSV
表 3 基站位置和需求生成量
Table 3. Base station location and demand
基站编号 经度/（°） 纬度/（°） 需求生成量/人 0 112.247 9 30.343 0 252 1 112.247 6 30.341 6 483 2 112.246 7 30.341 3 85 3 112.246 6 30.340 5 53 4 112.247 7 30.339 9 21 29 112.256 8 30.348 4 196 30 112.258 4 30.346 4 2 31 112.257 2 30.344 1 164 32 112.261 1 30.347 1 150 33 112.263 6 30.345 2 192 34 112.263 9 30.344 0 94
下载: 导出CSV
表 4 进出点位置和需求生成量
Table 4. Point location and demand
进出点编号 经度 纬度 需求生成量/人 0 112.2454 30.3414 23 1 112.2522 30.3370 16 2 112.2578 30.3414 688 3 112.2534 30.3333 53 4 112.2513 30.3446 154 34 112.256 6 30.342 18 12 35 112.260 3 30.339 61 15 36 112.259 7 30.342 73 14 37 112.251 9 30.343 08 24 38 112.247 6 30.340 47 642
下载: 导出CSV
表 5 公交站点及其服务需求点
Table 5. Bus stops and demand points
站点编号 经度/（°） 纬度/（°） 需求点编号 需求量/人 0 112.245 4 30.341 4 0，32 108 1 112.252 1 30.337 0 9，31 583 2 112.257 8 30.341 3 34 15 3 112.253 4 30.333 3 10，12 161 4 112.251 3 30.344 6 20，21 21 24 112.255 3 30.346 9 27 196 25 112.248 1 30.340 1 30 642 26 112.257 2 30.342 8 28 16 27 112.259 9 30.342 6 36，37 38
下载: 导出CSV
表 6 优化前后对比结果
Table 6. Comparison of results
参数 优化前 优化后 差值百分比/% 运营成本/元 8 954.40 9 104.40 -1.68 步行时间成本/元 5 109.02 2 453.40 51.98 系统总成本/元 14 063.42 11 557.80 17.82 平均步行距离/m 144.00 50.59 64.87 100 m覆盖率/% 47.37 89.47 88.87 300 m覆盖率/% 76.92 100.00 25.13
下载: 导出CSV
表 7 不同算法结果对比
Table 7. Comparison of different algorithm results
算法 站点数量/个 系统总成本/元 平均运算时间/s K-means聚类 26 12 663.31 15.0 AP聚类 20 11 851.72 19.1 改进Mean Shift聚类 28 11 557.80 45.9
下载: 导出CSV
表 8 对比结果
Table 8. Comparison of results
站点数量/个 运营成本/元 步行时间成本/元 系统总成本/元 未考虑基站范围 28 9 104.40 3 995.23 13 099.63 未考虑等时圈 25 8 639.40 3 252.56 11 891.96 考虑基站范围和等时圈 28 9 104.40 2 453.4 11 557.80
下载: 导出CSV
-
[1] CHIEN S, YANG Z. Optimal feeder bus routes on irregular street networks[J]. Journal of Advanced Transportation, 2000, 34(2): 213-248. doi: 10.1002/atr.5670340204 [2] CHIEN S, YANG Z, HOU E, A genetic algorithm approach for transit route planning and design[J]. Journal of Transportation Engineering, 2001, 127(3): 200-207. doi: 10.1061/(ASCE)0733-947X(2001)127:3(200) [3] CHIEN S I, QIN Z. Optimization of bus stop locations for improving transit accessibility[J]. Transportation planning and Technology, 2004, 27(3): 211-227. doi: 10.1080/0308106042000226899 [4] 杨昊. 灵活公交混合式站点选址方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.YANG H. Research on hybrid site selection of flexible transit[D]. Harbin: Harbin Institute of Technology, 2020. (in Chinese) [5] WANG F, YE M, ZHU H, et al. Optimization method for conventional bus stop placement and the bus line network based on the Voronoi diagram[J]. Sustainability, 2022, 14(13): 7918. doi: 10.3390/su14137918 [6] LYU Y, CHOW C Y, LEE V C, et al. T2CBS: Mining taxi trajectories for customized bus systems[C]. 2016 IEEE Conference on Computer Communications Workshops, San Francisco, USA: IEEE, 2016. [7] 孙悦. 基于平台需求数据的定制公交站点选址与线路设计方法研究[D]. 北京: 北京交通大学, 2019.SUN Y, Research on site selection and route design of customized bus based on platform demand data[D]. Beijing: Beijing JiaoTong University, 2019. (in Chinese) [8] REN Y, CHEN G, HAN Y, et al. Extracting potential bus lines of customized city bus service based on public transport big data[C]. In IOP Conference Series: Earth and Environmental Science, Beijing, China: IOP, 2016. [9] 雷永巍, 林培群, 姚凯斌. 互联网定制公交的网络调度模型及其求解算法[J]. 交通运输系统工程与信息, 2017, 17(1): 157-163. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201701024.htmLEI Y W, LIN P Q, YAO K B. A network scheduling model and its solution algorithm for Internet customized buses[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(1): 157-163. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201701024.htm [10] 彭理群, 罗明波, 卢赫, 等. 基于Q-learning的定制公交跨区域路径规划研究[J]. 交通运输系统工程与信息, 2020, 20 (1): 104-110. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202001018.htmPENG L Q, LUO M B, LU H, et al. Cross-regional customized bus path planning based on Q-learning[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 104-110. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202001018.htm [11] 靳文舟, 郭献超, 龚隽. 基于精英选择遗传算法的需求响应公交规划[J]. 公路工程, 2020, 45(2): 44-49. https://www.cnki.com.cn/Article/CJFDTOTAL-ZNGL202002008.htmJIN W Z, GUO X C, GONG J, Based on elitist selection genetic algorithm for demand responsive transit planning[J]. Highway Engineering, 2020, 45(2): 44-49. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZNGL202002008.htm [12] SUPANGAT K, SOELISTIO Y E. Bus stops location and bus route planning using mean shift clustering and ant colony in West Jakarta[C]. IOP Conference Series: Materials Science and Engineering, Yogyakarta, Indonesia: IOP, 2017. [13] CEDER A A, BUTCHER M, WANG L. Optimization of bus stop placement for routes on uneven topography[J]. Transportation Research Part B: Methodological, 2015, 74: 40-61. doi: 10.1016/j.trb.2015.01.006 [14] MOURA J L, ALONSO B, IBEAS Á, et al. A two-stage urban bus stop location model[J]. Networks and Spatial Economics, 2012, 12(3): 403-420. doi: 10.1007/s11067-011-9161-z [15] SHATNAWI N, AL-OMARI A A, AL-QUDAH H. Optimization of bus stops locations using GIS techniques and artificial intelligence[J]. Procedia Manufacturing, 2020, 44: 52-59. doi: 10.1016/j.promfg.2020.02.204 [16] MA J H, YANG Y, WEI G, et al. Large-scale demand driven design of a customized bus network: a methodological frame-work and Beijing case study[J/OL]. (2017-03)[2024-05-07]. https://www.hindawi.com/journals/jat/2017/3865701 .[17] TONG L, ZHOU L, LIU J, et al., Customized bus service design for jointly optimizing passenger-to-vehicle assignment and vehicle routing[J]. Transportation Research Part C: Emerging Technologies, 2017, 85: 451-475. doi: 10.1016/j.trc.2017.09.022 [18] BAGLOEEA S A, CEDER A A. Transit-network design methodology for actual-size road networks[J]. Transportation Research Part B: Methodological, 2011, 45(10): 1787-1804. doi: 10.1016/j.trb.2011.07.005 [19] MAHDI S M, et al. Designing large-scale bus network with seasonal variations of demand[J]. Transportation Research Part C: Emerging Technologies, 2014, 48: 322-338. doi: 10.1016/j.trc.2014.08.017 [20] 陈巍, 林涛. 基于多源大数据的常规公交站点优化[C]. 2020年中国城市交通规划年会. 北京: 中国城市规划学会城市交通规划学术委员会, 2020.CHEN W, LIN T. Conventional bus stop optimization based on multi-source big data[C]. The Annual Conference on Urban Transportation Planning in China 2020, Beijing: Academic Committee on Urban Transportation Planning, China Society of Urban Planning, 2020. (in Chinese) [21] YANG Y K, XIONG C, ZHUO J, et al. Detecting home and work locations from mobile phone cellular signaling data[J/OL]. (2021-03)[2024-05-07]. https://www.hindawi.com/journals/misy/2021/5546329 .[22] LI Z Y, SUN H, LI L., Analysis of intercity travel in the Yangtze river delta based on mobile signaling data[J]. Journal of Tsinghua University(Science and Technology), 2022, 62(7): 1203-1211. [23] LIU S, LONG Y, ZHANG L, et al. Semantic enhancement of human urban activity chain construction using mobile phone signaling data[J]. International Journal of Geo-Information, 2021, 10(8): 545. doi: 10.3390/ijgi10080545 [24] SUN H, CHEN Y, WANG Y, et al. Trip purpose inference for tourists by machine learning approaches based on mobile signaling data[J]. Journal of Ambient Intelligence and Humanized Computing, 2023(14): 923-937. [25] LAI Y, LYU Z, CHEN C, et al. Exploring employment spatial structure based on mobile phone signaling data: the case of Shenzhen, China[J]. Land, 2022, 11(7): 983. [26] 胡宝雨, 刘学. 基于手机信令数据的城市区域居民出行OD预测模型[J]. 交通运输系统工程与信息, 2013, 23(6): 296-306. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202306029.htmHU B Y, LIU X, The prediction model for residents travelling OD in urban areas based on mobile phone signaling data[J]. Journal of Transportation Systems Engineering and Information Technology, 2013, 23(6): 296-306. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202306029.htm [27] LOÏC B. TRANSIT: Fine-grained human mobility trajectory inference at scale with mobile network signaling data[J]. Transportation Research Part C: Emerging Technologies, 2021(130): 103257. [28] LI Z, CHEN H, YAN W. Exploring spatial distribution of urban park service areas in Shanghai based on travel time estimation: a method combining multi-source data[J]. ISPRS International Journal of Geo-Information, 2021, 10(9): 608. [29] WANG J Y, ZHANG M. Identifying the service areas and travel demand of the commuter customized bus based on mobile phone signaling data[J/OL]. (2021-10)[2024-05-07]. https://www.hindawi.com/journals/jat/2021/6934998 . -
点击查看大图
图(5) / 表(8)
计量
- 文章访问数: 196
- HTML全文浏览量: 125
- PDF下载量: 12
- 被引次数: 0