Journal of Jilin University(Engineering and Technology Edition) ›› 2023, Vol. 53 ›› Issue (11): 3104-3112.doi: 10.13229/j.cnki.jdxbgxb.20211391

Previous Articles     Next Articles

Urban road network short-term traffic flow prediction model based on associated road chain group

Jian-cheng WENG1(),Rui-cong WEI1,2,Han-mei HE3,Hai-hui XU4(),Jing-jing WANG5,6   

  1. 1.The Key Laboratory of Transportation Engineering,Beijing University of Technology,Beijing 100124,China
    2.Fujian Expressway Network Operation Co. ,Ltd. ,Fuzhou 350019,China
    3.Beijing Baidu Zhixing Technology Co. ,Ltd. ,Beijing 100085,China
    4.Beijing Municipal Commission of Transport,Beijing 100161,China
    5.Beijing Municipal Transportation Operations Coordination Center,Beijing 100161,China
    6.Beijing Key Laboratory of Integrated Traffic Operation Monitoring and Service,Beijing 100161,China
  • Received:2021-12-16 Online:2023-11-01 Published:2023-12-06
  • Contact: Hai-hui XU E-mail:youthweng@bjut.edu.cn;xuhaihui@jtw.beijing.gov.cn

Abstract:

In order to divide the associated road chains of urban road network and accurately predict the traffic operation state, calculate the importance of each road section and the shortest distance path length to represent the spatial characteristics of the road section, this paper proposes the density peak clustering algorithm to identify the correlation road chain set with strong temporal and spatial correlation of traffic flow. A traffic flow prediction model is constructed by the long short-term memory neural network based on road chain groups division(RCGD-LSTMNN),and takes the spatiotemporal two-dimensional matrix of all sections in the same road chain as the model input. In Beijing road network, for example, the fourth ring road in the backbone network is divided into eight associated road chain group, the model accuracy can reach more than 95%, and is superior to the traditional LSTM and BP model predicted results, show that the presented model has good applicability and accuracy of stability, applicable to different spatial and temporal patterns of road traffic state forecasting chain group.

Key words: engineering of communications and transportation system, road chain groups division, traffic prediction, density peak clustering, long short-term memory neural network, temporal-spatial correlation

CLC Number: 

  • U491.14

Table 1

Road grade weight"

道路等级道路名称道路权值
1快速路10
2主干路8
3次干路6
4支路3

Table 2

Information entropy and weight value of importance evaluation index"

指标道路等级Y1路段长度Y2路段连接度Y3
信息熵0.860.960.95
指标权重0.640.140.21

Fig.1

Schematic diagram of road segment hierarchy in road network"

Fig.2

Prediction structure diagram of long and short time memory neural network based on road chain groups division"

Table 3

Model evaluation of different parameter combinations"

n_epochbatch_size=1batch_size=32batch_size=64
MRERMSEMRERMSEMRERMSE
3004.6552.7054.5182.4464.5582.424
3204.8312.7214.5392.4534.5852.431
3404.7422.6944.4752.2644.6052.436
3604.6032.6584.5132.4384.6342.437

Fig.3

Determination cluster central point"

Fig.4

Spatial distribution of cluster centers"

Table 4

Clustering results of road chain groups"

类别路段名称数量
第1组

东三环北路、东三环北路(辅路)、北三环东路(主路)、东四环北路(主路)、北四环东路(主路)、北四环东路(辅路)、

京密路

7
第2组

东二环(建国门桥-广渠门桥)、东二环(朝阳门桥-建国门桥)、东二环(首都机场高速公路-东四十条桥)、

东二环(东四十条桥-朝阳门立交)、东二环(广渠门桥-光明桥)、东二环(光明桥-左安门桥)、东三环中路(主路)、

东三环中路(辅路)、东四环中路(主路)、朝阳门外大街、建国门内大街、建国门北大街、建国门南大街、

建国门外大街、广渠门外大街、广渠路、广渠门内大街、珠市口东大街

18
第3组

南二环(左安门桥-玉蜓桥)、东三环南路(主路)、东三环南路(辅路)、南三环中路(主路)、南三环东路、

南三环东路(辅路)、东四环南路、东四环南路(辅路)、南四环东路、南四环东路(辅路)、京沪高速、松榆南路、双龙路

13
第4组南四环西路、南四环西路(辅路)、南四环中路、南四环中路(辅路)、京开高速5
第5组

南二环(右安门桥-菜户营桥)、南二环(玉蜓桥-陶然桥)、南二环(右安门桥-陶然桥)、

西二环(广安门桥-菜户营桥)、南三环西路、南三环西路(辅路)、西三环中路(主路)、西三环中路(辅路)、

西三环南路、西三环南路(辅路)、西四环南路、西四环南路(辅路)、丽泽路、京港澳高速、丰台北路

15
第6组西二环(复兴门桥-阜成门桥)、西二环(官园桥-阜成门桥)、西二环(复兴门桥-广安门桥)、复兴门内大街、广安门外大街、广安门内大街、三里河路、广安路、复兴路、东长安街、西长安街、骡马市大街、珠市口西大街、复兴门外大街14
第7组

西三环北路、西三环北路(辅路)、西四环北路(主路)、西四环北路(辅路)、西四环中路(主路)、

西四环中路(辅路)、阜成路

7
第8组

西二环(西直门桥-官园桥)、北二环(安定门桥-首都机场高速公路)、北二环(德胜门桥-西直门桥)、

北三环西路(主路)、北三环中路、北三环中路(辅路)、北四环西路(主路)、北四环西路(辅路)、北四环中路、

北四环中路(辅路)、西直门南大街、安定门外大街、京藏高速公路、安定路

14

Fig.5

Precision analysis of prediction models of various models"

Table 5

Accuracy verification results of Various prediction models"

不同预测模型性能实验(a)实验(b)
MRERMSEMRERMSE
RCGD-LSTMNN4.2911.9354.9702.246
BP-NN6.0584.1856.8654.972
LSTM NN7.1204.2808.0415.164
1 邱世崇, 陆百川, 马庆禄, 等. 基于时空特性分析和数据融合的交通流预测[J] . 武汉理工大学学报: 信息与管理工程版, 2015, 37(2): 156-160.
Qiu Shi-chong, Lu Bai-chuan, Ma Qing-lu, et al. Traffic flow forecasting based on spatio-temporal characteristic analysis and data fusion[J]. Journal of Wuhan University of Technology(Information& Management Engineering), 2015, 37(2): 156-160.
2 Liu L, Zhen J, Li G, et al. Dynamic spatial-temporal representation learning for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 7169-7183.
3 陆百川, 李玉莲, 舒芹. 基于时空相关性和遗传小波神经网络的路网短时交通流预测[J]. 重庆理工大学学报: 自然科学版, 2020, 34(5): 25-34.
Lu Bai-chuan, Li Yu-lian, Shu Qin. Short term traffic flow prediction of road network based on spatiotemporal correlation and genetic wavelet neural network[J]. Journal of Chongqing University of Technology (Natural Science), 2020, 34(5): 25-34.
4 刘钊, 杜威, 闫冬梅, 等. 基于K近邻算法和支持向量回归组合的短时交通流预测[J]. 公路交通科技, 2017, 34(5): 126-132.
Liu Zhao, Du Wei, Yan Dong-mei, et al. Short-term traffic flow forecast based on combination of k nearest neighbor algorithm and support vector regression[J]. Journal of Highway and Transportation Research and Development, 2017, 34(5): 126-132.
5 陈华伟, 邵毅明, 敖谷昌, 等. 面向在线地图的GCN-LSTM神经网络速度预测[J]. 交通运输工程学报, 2021, 21(4): 183-196.
Chen Hua-wei, Shao Yi-ming, Ao Gu-chang, et al. Speed prediction by online map-based GCN-LSTM neural network[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 183-196.
6 蒲悦逸, 王文涵, 朱强, 等. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
Pu Yue-yi, Wang Wen-han, Zhu Qiang, et al. Urban short-term traffic flow prediction algorithm based on CNN-ResNet-LSTM model[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 9-14.
7 陈丹蕾, 陈红, 任安虎. 考虑时空影响下的图卷积网络短时交通流预测[J]. 计算机工程与应用, 2021, 57(13): 269-275.
Chen Dan-lei, Chen Hong, Ren An-hu. Short term traffic flow prediction based on graph convolution network considering the influence of time and space[J]. Computer Engineering and Application, 2021, 57(13): 269-275.
8 谷远利, 张源, 芮小平, 等. 基于免疫算法优化LSSVM的短时交通流预测[J]. 吉林大学学报: 工学版, 2019, 49(6): 1852-1857.
Gu Yuan-li, Zhang Yuan, Rui Xiao-ping, et al. Short⁃term traffic flow prediction based on LSSVM optimized by immune algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(6): 1852-1857.
9 .城市道路工程设计规范 [S].
10 赵建东, 贾卓瑾, 梁营力, 等. 基于浮动车数据的城市区域路网关键路段识别[J]. 北京交通大学学报, 2021, 45(4): 54-60.
Zhao Jian-dong, Jia Zhuo-jin, Liang Ying-li, et al. Identification of key road sections in urban road network based on floating car data[J]. Journal of Beijing Jiaotong University, 2021, 45(4): 54-60.
11 Zhao Z. A density-peak-based clustering method for multiple densities dataset[J]. ISPRS International Journal of Geo-Information, 2021, 10(9): 10090589.
12 Yang J M, Peng Z R, Lin L. Real-time spatiotemporal prediction and imputation of traffic status based on LSTM and graph laplacian regularized matrix factorization[J]. Transportation Research Part C: Emerging Technologies, 2021, 129: 1-23.
13 贾洪飞, 孟品超, 李学源, 等. 基于滑动平均法的轨道交通短时客流实时预测[J]. 吉林大学学报: 工学版, 2018, 48(2): 448-453.
Jia Hong-fei, Meng Pin-chao, Li Xue-yuan, et al. Short-time rail transit passenger flow real-time prediction based on moving average[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(2): 448-453.
14 Ryu U, Wang J, Kim T, et al. Construction of traffic state vector using mutual information for short-term traffic flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2018, 96(11): 55-71.
15 Li Y F, Chen M N, Zhao W Z. Investigating long-term vehicle speed prediction based on BP‐LSTM algorithms[J]. IET Intelligent Transport Systems, 2019, 13(8): 1281-1290.
[1] Zhi ZHENG,Pei YUAN,Xuan-hui JIN,Si-si WEI,Bo GENG. Experimental on composite flexible anti⁃collision fender of bridge pier [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2581-2590.
[2] Guo-zhu CHENG,Lin SHENG,Hao ZHAO,Tian-jun FENG. Exclusive phase setting condition of signalized intersection based on risk analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1962-1969.
[3] Yong-ming HE,Shi-sheng CHEN,Jia FENG,Ya-nan WAN. Superhighway virtual track system based on high precision map [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 2016-2028.
[4] Zhi-jia XUE,Zhao-yang WANG,Jiu-peng ZHANG,Chang-gen YAN,Zi-kai XU,Ying-li ZHANG,Xiao-ming Huang,Tao Ma. Toughness analysis and improvement of road structure under action of debris flow [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(6): 1773-1781.
[5] Rong-han YAO,Wen-tao XU,Wei-wei GUO. Drivers' takeover behavior and intention recognition based on factor and long short⁃term memory [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 758-771.
[6] Xue XIAO,Ke-ping LI,Bo PENG,Man-wei CHANG. Integrated lane⁃changing model of decision making and motion planning for autonomous vehicles [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 746-757.
[7] Min MA,Da-wei HU,Lan SHU,Zhuang-lin MA. Resilience assessment and recovery strategy on urban rail transit network [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 396-404.
[8] Jing WANG,Feng WAN,Chun-jiao DONG,Chun-fu SHAO. Modelling on catchment area and attraction intensity of urban rail transit stations [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 439-447.
[9] Lu WEI,Lei GAO,Jin-hong LI,Jian YANG,Yu-lin TIAN. Traffic sub⁃area division method based on density peak clustering [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(1): 124-131.
[10] Song FANG,Jian-xiao MA,Gen LI,Ling-hong SHEN,Chu-bo XU. Traffic risk analysis of moving work zone on right lane of city expressway [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1786-1791.
[11] Song-xue GAI,Xiao-qing ZENG,Xiao-yuan YUE,Zi-hao YUAN. Parking guidance model based on user and system bi⁃level optimization algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1344-1352.
[12] Hong-feng XU,Hong-jin CHEN,Dong ZHANG,Qian-hui LU,Na AN,Xian-cai Geng. Fully⁃actuated signal timing technique for isolated signalized intersections in connected vehicle environment [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1324-1336.
[13] Guo-zhu CHENG,Qiu-yue SUN,Yue-bo LIU,Ji-long CHEN. Cut⁃in behavior model based on game theoretic approach on urban roads [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(12): 2839-2844.
[14] Heng-yan PAN,Wen-hui ZHANG,Bao-yu HU,Zun-yan LIU,Yong-gang WANG,Xiao ZHANG. Construction and robustness analysis of urban weighted subway⁃bus composite network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(11): 2582-2591.
[15] Zhuang-lin MA,Shan-shan CUI,Da-wei HU. Urban residents' low⁃carbon travel intention after implementation of driving restriction policy [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(11): 2607-2617.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] LI Shoutao, LI Yuanchun. Autonomous Mobile Robot Control Algorithm Based on Hierarchical Fuzzy Behaviors in Unknown Environments[J]. 吉林大学学报(工学版), 2005, 35(04): 391 -397 .
[2] Liu Qing-min,Wang Long-shan,Chen Xiang-wei,Li Guo-fa. Ball nut detection by machine vision[J]. 吉林大学学报(工学版), 2006, 36(04): 534 -538 .
[3] Li Hong-ying; Shi Wei-guang;Gan Shu-cai. Electromagnetic properties and microwave absorbing property
of Z type hexaferrite Ba3-xLaxCo2Fe24O41
[J]. 吉林大学学报(工学版), 2006, 36(06): 856 -0860 .
[4] Zhang Quan-fa,Li Ming-zhe,Sun Gang,Ge Xin . Comparison between flexible and rigid blank-holding in multi-point forming[J]. 吉林大学学报(工学版), 2007, 37(01): 25 -30 .
[5] Yang Shu-kai, Song Chuan-xue, An Xiao-juan, Cai Zhang-lin . Analyzing effects of suspension bushing elasticity
on vehicle yaw response character with virtual prototype method
[J]. 吉林大学学报(工学版), 2007, 37(05): 994 -0999 .
[6] . [J]. 吉林大学学报(工学版), 2007, 37(06): 1284 -1287 .
[7] Che Xiang-jiu,Liu Da-you,Wang Zheng-xuan . Construction of joining surface with G1 continuity for two NURBS surfaces[J]. 吉林大学学报(工学版), 2007, 37(04): 838 -841 .
[8] Liu Han-bing, Jiao Yu-ling, Liang Chun-yu,Qin Wei-jun . Effect of shape function on computing precision in meshless methods[J]. 吉林大学学报(工学版), 2007, 37(03): 715 -0720 .
[9] Li Yue-ying,Liu Yong-bing,Chen Hua . Surface hardening and tribological properties of a cam materials[J]. 吉林大学学报(工学版), 2007, 37(05): 1064 -1068 .
[10] Feng Hao,Xi Jian-feng,Jiao Cheng-wu . Placement of roadside traffic signs based on visibility distance[J]. 吉林大学学报(工学版), 2007, 37(04): 782 -785 .