基于数据驱动的城市快速路段拥堵状态辨识及诱导对象选择方法

赵坡; 吴戈; 王翔; 汪思涵; 昝雨尧

doi:10.3963/j.jssn.1674-4861.2021.06.010

基于数据驱动的城市快速路段拥堵状态辨识及诱导对象选择方法

doi: 10.3963/j.jssn.1674-4861.2021.06.010

苏州大学轨道交通学院江苏苏州 215000

基金项目:

国家自然科学基金项目 52002262

详细信息

作者简介:
赵坡(1995—), 硕士研究生.研究方向: 车辆出行特征与路网交通状态识别.E-mail: 981102018@qq.com

通讯作者:
王翔(1987—), 博士, 副教授.研究方向: 交通大数据分析与智能交通.E-mail: wangxiang@suda.edu.cn

中图分类号: U491.4
计量
- 文章访问数: 867
- HTML全文浏览量: 390
- PDF下载量: 56
- 被引次数: 0
出版历程
- 收稿日期: 2021-03-06
- 网络出版日期: 2022-01-12

A Data-driven Method for Identifying Congestion State and Selecting Guided Vehicles for Urban Expressways

School of Rail Transportation, Soochow University, Suzhou 215000, Jiangsu, China

摘要

摘要: 交通诱导实施效果不佳的主要原因之一是具有差异性出行特征的出行者无法接受单一的诱导方案。针对城市快速路高峰时段拥堵问题, 研究了考虑车辆出行特征差异的交通诱导对象精准识别方法, 以保障诱导方案的实施效果。利用高德路况数据提取拥堵路段, 根据拥堵路段与相邻路段交通状态的相关性提出拥堵源路段识别方法; 利用车牌识别数据提取使用快速路车辆的出行特征, 包括快速路出行强度、地面道路出行强度、快速路出发时刻离散度和快速路路径选择多样性; 采用K-means++算法对车辆出行特征进行聚类, 识别出显著影响道路交通状态的出行者, 并为出行者推荐适合其出行特征的错峰或绕行诱导方案。以苏州快速路为例, 研究发现: 针对拥堵源路段的交通诱导能有效改善拥堵路段的交通状态; 类型3车辆(高频出行且易绕行)占单月工作日早高峰所有使用快速路车辆总数的14%, 却占单日早高峰总交通量的51%, 是重点诱导对象; 通过精准识别, 可推荐诱导车辆数占总车辆数的47%。
- 交通工程 /
- 出行者与快速路 /
- 精准识别 /
- K-means++算法 /
- 绕行诱导 /
- 错峰诱导
Abstract: The inefficient traffic guidance is that travelers are reluctant to accept a single guidance scheme due to heterogeneous travel characteristics. This work proposes an accurate selection method based on the travel characteristics to ensure guidance performance, thus alleviating the peak-hour congestion of the expressways. The congested sections are extracted from a traffic condition dataset of the Gaode map, and the original congested sections are identified according to the correlation of traffic conditions between the congested sections and its adjacent ones. Besides, the travel characteristics of vehicles passing on the expressways are extracted based on the license plate recognition data, including the travel intensity on the expressways, the travel intensity on the ground roads, the dispersion of expressway departure time, and the diversity of the expressway path selection. The travelers significantly affecting the traffic condition of the expressways are identified by the K-means++ clustering algorithm, and appropriate guidance(i.e. staggered shift and detour)is recommended to the identified travelers based on their traveling characteristics. Taking the Suzhou expressway as a case study, the traffic guidance for the original congested sections can improve the traffic condition of congested sections. Type-3 vehicles(high-intensity travel and easy to detour)are the key targets, accounting for only 14% of the total number of vehicles using expressways in the morning peak of working day in one month. However, they constitute 51% of the total traffic volume. There are 47% of vehicles that can be recommended with personalized traffic guidance after congestion-state identification and guided-object selection.
- traffic engineering /
- travelers and expressways /
- accurate identification /
- K-means++ algorithm /
- detour guidance /
- peak dislocation guidance

HTML全文

图 1 K-means++计算流程

Figure 1. Flow of K-means++algorithm calculation

下载: 全尺寸图片幻灯片

图 2 快速路研究范围

Figure 2. Study scope of the expressways

下载: 全尺寸图片幻灯片

图 3 拥堵源路段诱导对象识别流程

Figure 3. Identification process of induction targets in congested-source sections

下载: 全尺寸图片幻灯片

图 4 拥堵路段开始与消散时刻分布

Figure 4. Time distribution of beginning and ending of congested sections

下载: 全尺寸图片幻灯片

图 5 拥堵源路段与拥堵路段时空热力图

Figure 5. Spatio-temporal thermal map of the congested source section and congested section

下载: 全尺寸图片幻灯片

图 6 车辆出行特征分布

Figure 6. Distribution of vehicle-travel characteristics

下载: 全尺寸图片幻灯片

图 7 聚类参数确定示意图

Figure 7. Determination of clustering parameters

下载: 全尺寸图片幻灯片

图 8 聚类结果分布

Figure 8. Distribution of clustering results

下载: 全尺寸图片幻灯片

图 9 拥堵源路段各类型出行者时变交通量分布

Figure 9. Time-varying traffic volume distribution of different travelers in congested-source road sections

下载: 全尺寸图片幻灯片

表 1 高德数据字段表

Table 1. Fields of the traffic-condition dataset of the Gaode map

字段	中文名	示例
roadid	路段编号	5********9
roadname	路段名称	西环快速路
roadclass	道路等级	快速路
speed	速度/(km/h)	50
stat_time	检测时刻	2020-03-16 T20:38:00

下载: 导出CSV

表 2 卡口数据字段表

Table 2. Fields of license plate recognition data

字段	中文名	示例
hphm	号牌号码	苏E*****
dwbh	点位编号	3********7
hpys	号牌颜色	蓝色
jgsj	经过时刻	2020-03-16T12:30:07
cdbh	车道编号	1
sbbh	设备编号	3********1
clsd	速度/(km/h)	50

下载: 导出CSV

表 3 各路段与拥堵源路段交通状况相关系数

Table 3. Correlation coefficient of traffic conditions between each road section and congested-source road section

区域	路段编号	1	2	3	4	5	6	7	8
a	6	0.75	0.78	0.81	0.84	0.92	1.00	0.36	-
b	5	0.73	0.87	0.91	0.99	1.00	0.97	0.92	0.20
c	7	0.57	0.76	0.80	0.92	0.92	0.96	1.00	0.51
d	6	0.6	0.65	0.72	0.78	0.87	1.00	0.86	0.18

下载: 导出CSV

表 4 聚类结果统计

Table 4. Statistics of clustering results

类型	车辆数(占比/%)	出行强度/d	快速路出行强度/d	地面道路出行强度/d	快速路出发时刻离散度	快速路路径多样性/个	快速路总出行次数(占比/%)	地面道路总出行次数(占比/%)
1	155 229(17)	16.1	2.4	13.7	0.6	1.5	364 740(10)	2 132 801(54)
2	147 435(16)	9.9	4.9	5.0	3.6	3.6	721 800(20)	734 499(19)
3	121 396(14)	18.2	15.3	2.9	1.5	3.5	1 862 184(51)	346 732(9)
4	474 278(53)	3.1	1.5	1.6	0.2	1.2	711 848(19)	736 385(19)

下载: 导出CSV

参考文献(20)

[1]	郭继孚, 刁晶晶, 王倩, 等. 预约在城市交通中的应用: 北京市回龙观地区的预约出行实践[J]. 城市交通, 2020, 18(1): 75-82. https://www.cnki.com.cn/Article/CJFDTOTAL-CSJT202001013.htm GUO Jifu, DIAO Jingjing, WANG Qian, et al. Reservation in urban transportation system: travel reservation practice in Huilongguan area, Beijing[J]. Urban Transport of China, 2020, 18(1): 75-82. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CSJT202001013.htm
[2]	张卫华, 杨朝辉, 李军, 等. 高速公路交通事件下可变限速诱导研究[J]. 广西大学学报(自然科学版), 2021, 46(3): 737-746. https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ202103023.htm ZHANG Weihua, YANG Zhaohui, LI Jun, et al. Study on variable speed limit induction under freeway traffic accident[J]. Journal of Guangxi University(Natural Science Edition), 2021, 46(3): 737-746. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ202103023.htm
[3]	白紫秀, 焦朋朋, 陈越, 等. 预约出行条件下私家车通勤客流分配方法[J]. 交通信息与安全, 2021, 39(4): 117-124. doi: 10.3963/j.jssn.1674-4861.2021.04.015 BAI Zixiu, JIAO Pengpeng, CHEN Yue, et al. An assignment method of commuter flow of private cars under travel reservation[J]. Journal of Transport Information and Safety, 2021, 39(4): 117-124. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2021.04.015
[4]	XIONG Chenfeng, SHAHABI M, ZHAO Jun, et al. An integrated and personalized traveler information and incentive scheme for energy efficient mobility systems[J]. Transportation Research Part C: Emerging Technologies, 2020, 113(4): 57-73.
[5]	LI Linchao, ZHANG Jian, WANG Yonggang, et al. Missing value imputation for traffic-related time series data based on a multi-view learning method[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(8): 2933-2943. doi: 10.1109/TITS.2018.2869768
[6]	ZHANG Wenliang, JI Xinkai, ZHANG Jian, et al. Freeway traffic state estimation and prediction based on ETC-based path identification toll system[C]. 17^thCOTA International Conference of Transportation Professionals, Shanghai, China: COTA, 2017.
[7]	刘治彦, 岳晓燕, 赵睿. 我国城市交通拥堵成因与治理对策[J]. 城市发展研究, 2011, 18(11): 90-96. doi: 10.3969/j.issn.1006-3862.2011.11.018 LIU Zhiyan, YUE Xiaoyan, ZHAO Rui. The cause of urban traffic congestion and countermeasures in China[J]. Urban Development Studies, 2011, 18(11): 90-96. (in Chinese) doi: 10.3969/j.issn.1006-3862.2011.11.018
[8]	王振坡, 张馨芳, 宋顺锋. 我国城市交通拥堵成因分析及政策评价: 以天津市为例[J]. 城市发展研究, 2017, 24(4): 118-124. doi: 10.3969/j.issn.1006-3862.2017.04.017 WANG Zhenpo, ZHANG Xinfang, SONG Shunfeng. Cause analysis and policy evaluation of urban traffic congestion in China: A case study of Tianjin[J]. Urban Development Studies, 2017, 24(4): 118-124. (in Chinese) doi: 10.3969/j.issn.1006-3862.2017.04.017
[9]	闫学东, 刘晓冰, 刘炀, 等. 基于浮动车大数据与网格模型的城市交通拥堵识别和评价研究[J]. 北京交通大学学报, 2019, 43(1): 104-113. doi: 10.11860/j.issn.1673-0291.2019.01.012 YAN Xuedong, LIU Xiaobing, LIU Yang. Identification and evaluation of urban traffic congestion based on the big data of floating vehicles and grid modeling[J]. Journal of Beijing Jiaotong University, 2019, 43(1): 104-113. (in Chinese) doi: 10.11860/j.issn.1673-0291.2019.01.012
[10]	WANG Jiechen, WU Jiayi, NI Jianhua, et al. Relationship between urban road traffic characteristics and road grade based on a time series clustering model: A case study in Nanjing, China[J]. Chinese Geographical Science, 2018, 28(6): 1048-1060. doi: 10.1007/s11769-018-0982-2
[11]	张扬. 上海市快速路拥堵关键节点成因溯源案例分析[J]. 交通与运输, 2020, 36(5): 19-23. https://www.cnki.com.cn/Article/CJFDTOTAL-YSJT202005006.htm ZHANG Yang. Shanghai urban expressway congestion source in key locations[J]. Traffic & Transportation, 2020, 36(5): 19-23. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSJT202005006.htm
[12]	何兆成, 周亚强, 余志. 基于数据可视化的区域交通状态特征评价方法[J]. 交通运输工程学报, 2016, 16(1): 133-140. doi: 10.3969/j.issn.1671-1637.2016.01.016 HE Zhaocheng, ZHOU Yaqiang, YU Zhi. Regional traffic state evaluation method based on data visualization[J]. Journal of Traffic and Transportation Engineering, 2016, 16(1): 133-140. (in Chinese) doi: 10.3969/j.issn.1671-1637.2016.01.016
[13]	张溪, 孙建平, 温慧敏. 城市快速路常发拥堵路段及拥堵瓶颈点识别方法研究[C]. 第十二届中国智能交通年会, 江苏, 常熟: 中国智能交通协会, 2017. ZHANG Xi, SUN Jianping, WEN Huimin. Research on the recognition methods of frequent congested road and bottleneck for urban expressway[C]. 12^thAnnual Conference of ITS China, Changshu, Jiangsu: China Intelligent Transportation Systems Association, 2017. (in Chinese)
[14]	张建旭, 郭力玮. 基于在线地图交通态势分析的路网拥堵状态识别[J]. 交通运输系统工程与信息, 2018, 18(5): 75-81. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201805012.htm ZHANG Jianxu, GUO Liwei. Congestion status recognition of road network based on traffic situation analysis of online map[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 75-81. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201805012.htm
[15]	CHEN Huiyu, CHAO Yang, XU Xiangdong. Clustering vehicle temporal and spatial travel behavior using license plate recognition data[J]. Journal of Advanced Transportation, 2017(2017): 1-14.
[16]	畅玉皎, 杨东援. 基于车牌照数据的通勤特征车辆识别研究[J]. 交通运输系统工程与信息, 2016, 16(2): 77-82+112. doi: 10.3969/j.issn.1009-6744.2016.02.014 CHANG Yujiao, YANG Dongyuan. Recognition of vehicles with commuting property using license plate data[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(2): 77-82+112. (in Chinese) doi: 10.3969/j.issn.1009-6744.2016.02.014
[17]	吕亮, 钟添翼, 王世彬, 等. RFID数据驱动下出行路径选择方法研究[J]. 公路与汽运, 2021(1): 16-20+37. doi: 10.3969/j.issn.1671-2668.2021.01.005 LYU Liang, ZHONG Tianyi, WANG Shibin, et al. Research on travel path selection method driven by RFID data[J]. Highways & Automotive Applications, 2021(1): 16-20+37. (in Chinese) doi: 10.3969/j.issn.1671-2668.2021.01.005
[18]	XIE Yifei, DANAF M, AZEVEDO C L, et al. Behavioral modeling of on-demand mobility services: general framework and application to sustainable travel incentives[J]. Transportation, 2019, 46(6): 2017-2039. doi: 10.1007/s11116-019-10011-z
[19]	李颖, 赵莉, 赵祥模, 等. 基于大货车GPS数据的轨迹相似性度量有效性研究[J]. 中国公路学报, 2020, 33(2): 146-157. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202002014.htm LI Ying, ZHAO Li, ZHAO Xiangmo, et al. Effectiveness of trajectory similarity measures based on truck GPS data[J]. China Journal of Highway and Transport, 2020, 33(2): 146-157. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202002014.htm
[20]	YODER J Y, PRIEBE C E. Semi-supervised K-means++[J]. Journal of Statistical Computation and Simulation, 2017, 87(13): 2597-2608. doi: 10.1080/00949655.2017.1327588