基于神经网络的小时间粒度交通流预测模型

交通运输系统工程与信息 ›› 2017, Vol. 17 ›› Issue (1): 67-73.

• 智能交通系统与信息技术 • 上一篇下一篇

基于神经网络的小时间粒度交通流预测模型

姚志洪1a, 1b, 蒋阳升*1a, 1b , 韩鹏1a, 1b，罗孝羚1a, 1b, 徐韬2

1. 西南交通大学a. 交通运输与物流学院；b. 综合交通运输智能化国家地方联合工程实验室，成都610031； 2. 重庆交通大学交通运输学院，重庆400074

收稿日期:2016-07-06 修回日期:2016-08-21 出版日期:2017-02-25 发布日期:2017-02-27
作者简介:姚志洪（1991-），男，安徽安庆人，博士生.
基金资助:
国家自然科学基金/ National Natural Science of China（51578465，71402149）；西南交通大学拔尖创新人才培育/ Outstanding Innovative Talents Fostering Fund of Southwest Jiaotong University（2016-2017）.

Traffic Flow Prediction Model Based on Neural Network in Small Time Granularity

YAO Zhi-hong1a, 1b, JIANG Yang-sheng1a, 1b, HAN Peng1a, 1b, LUO Xiao-ling1a, 1b, XU Tao2

1a. School of Transportation and Logistics; 1b. National United Engineering Laboratory of Integrated and Intelligent Transportation, Southwest Jiaotong University, Chengdu 610031, China; 2. School of Transportation, Chongqing Jiaotong University, Chongqing 400074, China

Received:2016-07-06 Revised:2016-08-21 Online:2017-02-25 Published:2017-02-27

摘要/Abstract

摘要：

为解决传统车队离散模型基于概率分布假设和现有交通流预测时间粒度过大不能应用于自适应信号配时优化等问题.在车队离散模型的建模思路上，先分析了下游交叉口车辆到达与上游交叉口车辆离去之间的关系，基于此构建了基于神经网络的小时间粒度交通流预测模型.该模型以上游交叉口离去流量分布为输入，下游交叉口到达流量分布为输出，时间粒度为5 s.最后，通过实际调查数据标定模型参数并应用模型预测下游交叉口到达流量.结果表明，与Robertson 模型相比，本文模型预测结果能够更好地反映交通流的变化特征，平均预测误差减少了8.3%.成果可用于信号配时优化.

关键词: 交通工程, 交通流预测, 神经网络, 车队离散, 信号配时优化

Abstract:

The traditional platoon dispersion model is based on the hypothesis of probability distribution, and the time granularity of the existing traffic flow prediction is too big to be applied to the adaptive signal timing optimization. In order to solve these problems, from the view of the platoon dispersion model, the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection is analyzed, then, a traffic flow prediction model based on neural network in small time granularity is proposed. The departure flow at the upstream is taking as the input and the arrival flow at the downstream intersection is taking as the output in this model, which has the time granularity of 5 s. Finally, the proposed model parameters are calibrated by the actual survey data, and this model is applied to predict the arrival flow of the downstream intersection. The results show that the proposed model can better reflects the fluctuant characteristics of traffic flow compared with Robertson model, and the prediction error is reduced by 8.3%. As a result, this result provides theoretical support for signal timing optimization.

Key words: traffic engineering, traffic flow prediction, neural network, platoon dispersion, signal timing optimization

中图分类号:

U491.5

姚志洪, 蒋阳升, 韩鹏，罗孝羚徐韬. 基于神经网络的小时间粒度交通流预测模型[J]. 交通运输系统工程与信息, 2017, 17(1): 67-73.

YAO Zhi-hong, JIANG Yang-sheng, HAN Peng, LUO Xiao-ling, XU Tao. Traffic Flow Prediction Model Based on Neural Network in Small Time Granularity[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(1): 67-73.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19345.shtml

http://www.tseit.org.cn/CN/Y2017/V17/I1/67

参考文献

[1] ROBERTSON D I. Transyt: A traffic network study tool [J]. Road Research Laboratory Report Lr, 1996, 1969(1969): 1-30. [2] HUNT P B, ROBERTSON D I, BRETHERTON R D, et al. SCOOT- a traffic responsive method of coordinating signals[R]. Crowthorne: Transport and Road Research Laboratory, 1981. [3] PACEY G M. The progress of a bunch of vehicles released from a traffic signal[J]. Road Research Laboratory Note RN/2665/GMP, 1956, 1956(1956): 36- 50. [4] HALL M, WILLUMSEN L G. SATURN-a simulationassignment model for the evaluation of traffic management schemes[J]. Traffic Engineering & Control, 1980, 21(4): 81-94. [5] LIEBERMAN E B, ANDREWS B J. TRAFLO: A new tool to evaluate transportation system management strategies[M]. Washington: Transportation Research Board, 1980. [6] WEI M, JIN W Z, SHEN L O. A platoon dispersion model based on a truncated normal distribution of speed[J]. Journal of Applied Mathematics, 2012, 2012 (1): 155-172. [7] WU W W, JIN W Z, SHEN L O. Mixed platoon flow dispersion model based on speed- truncated gaussian mixture distribution[J]. Journal of Applied Mathematics, 2013, 2013(39): 415-425. [8] WU W W, SHEN L O, JIN W Z, et al. Density-based mixed platoon dispersion modelling with truncated mixed gaussian distribution of speed[J]. Transportmetrica B: Transport Dynamics, 2015, 3(2): 114-130. [9] 姚志洪，蒋阳升，吴云霞，等. 基于速度服从混合PH分布的车队离散模型[J]. 交通运输系统工程与信息, 2016, 16(3): 133-140. [YAO Z H, JIANG Y S, WU Y X, et al. Platoon dispersion model based on mixed phase distribution of speed[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3): 133-140.] [10] JIANG Y S, YAO Z H, DING X, et al. Mixed platoon flow dispersion model based on truncated mixed phase distribution of speed[C]. Transportation Research Board of the National Academies, Washington, D.C., 2016. [11] LAM W H K, TANG Y F, TAM M L. Comparison of two non-parametric models for daily traffic forecasting in Hong Kong[J]. Journal of Forecasting, 2006, 25(3): 173- 192. [12] GHOSH B, BASU B, OMAHONY M. Bayesian timeseries model for short- term traffic flow forecasting[J]. Journal of Transportation Engineering, 2007, 133(3): 180-189. [13] DIMITRIOU L, TSEKERIS T, STATHOPOULOS A. Adaptive hybrid fuzzy rule-based system approach for modeling and predicting urban traffic flow[J]. Transportation Research Part C Emerging Technologies, 2008, 16(5): 554-573. [14] GHOSH B, BASU B, OMAHONY M. Random process model for urban traffic flow using a wavelet- bayesian hierarchical technique[J]. Computer-Aided Civil and Infrastructure Engineering, 2010, 25(8): 613-624. [15] HONG W C, DONG Y, ZHENG F, et al. Hybrid evolutionary algorithms in a SVR traffic flow forecasting model[J]. Applied Mathematics & Computation, 2011, 217(15): 6733-6747. [16] TCHRAKIAN T T, BASU B, OMAHONY M. Real-time traffic flow forecasting using spectral analysis[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 519-526. [17] GUO F C, KRISHNAN R, POLAK J. A computationally efficient two-stage method for short-term traffic prediction on urban roads[J]. Transportation Planning & Technology, 2013, 36(1): 62-75. [18] MAI T, GHOSH B, WILSON S. Short-term traffic-flow forecasting with auto- regressive moving average models[J]. Transport, 2014, 167(4): 232-239. [19] JLINT J W C V, HOOGENDOORN S P, ZUYLEN H J V. Accurate freeway travel time prediction with statespace neural networks under missing data[J]. Transportation Research Part C Emerging Technologies, 2005, 13(5-6): 347-369. [20] HODGE V J, KRISHNAN R, AUSTIN J, et al. Shortterm prediction of traffic flow using a binary neural network[J]. Neural Computing & Applications, 2014, 25 (25): 1639-1655. [21] 廖瑞辉, 周晶. 基于云— 自组织神经网络的交通流预测模型[J]. 交通运输系统工程与信息, 2014, 14 (4): 154-159. [LIAO R H, ZHOU J. Traffic flow forecasting model based on cloud- self-organizing neural network[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(4): 154-159.] [22] 吕进，赵祥模，樊海玮，等. 基于生长自组织神经网络群的交通流预测[J]. 交通运输系统工程与信息, 2013, 13(3): 33-39. [LV J, ZHAO X M, FAN H W, et al. Traffic flow forecasting based on growing self-organized neural network group[J]. Journal of Transportation Systems Engineering and Information Technology, 2013, 13(3): 33-39.] [23] 杨兆升, 王媛, 管青. 基于支持向量机方法的短时交通流量预测方法[J]. 吉林大学学报(工学版), 2006, 36 (6): 881-884. [YANG Z S, WANG Y, GUAN Q. Shortterm traffic flow prediction method based on SVM[J]. Journal of Jilin University, 2006, 36(6): 881-884.] [24] YANG Y N, LU H P. Short-term traffic flow combined forecasting model based on SVM[C]. International Conference on Computational and Information Sciences. Chengdu, China: IEEE Computer Society, 2010. [25] XIE Y C, ZHANG Y, YE Z. Short-term traffic volume forecasting using kalman filter with discrete wavelet decomposition[J]. Computer-Aided Civil and Infrastructure Engineering, 2007, 22(5): 326-334. [26] OJEDA L L, KIBANGOU A Y, DEWIT C C. Adaptive kalman filtering for multi- step ahead traffic flow prediction[C]. Washington: IEEE, 2013. [27] WALLACE C E, COURAGE K G, REAVES D P, et al. TRANSYT-7F user's manual[R]. Gainesville: University of Florida, 1984. [28] MAKRIDAKIS S G. Forecasting: methods and applications[J]. Journal of the Operational Research Society, 1984, 35(1): 79.

基于神经网络的小时间粒度交通流预测模型

Traffic Flow Prediction Model Based on Neural Network in Small Time Granularity

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	林建新, 刘博, 赵霞, 张蕾. 基于混合约束自编码器的机动车工况智能构建方法[J]. 交通运输系统工程与信息, 2022, 22(2): 109-116.
[2]	戢晓峰, 耿昭师. 山区双车道公路货车碰撞预测的双变量冲突极值模型[J]. 交通运输系统工程与信息, 2022, 22(2): 230-238.
[3]	张建波, 孙建平, 徐春玲, 郭镜霞, 温慧敏, 宋国华. 考虑交通运行条件影响的驾驶员特征聚类[J]. 交通运输系统工程与信息, 2022, 22(2): 330-336.
[4]	马景峰, 任刚, 李豪杰, 曹奇, 杜建玮. 电动自行车与机动车事故严重性影响因素分析[J]. 交通运输系统工程与信息, 2022, 22(2): 337-348.
[5]	宗芳, 王猛, 贺正冰. 考虑多车影响的分子动力学智能网联跟驰模型[J]. 交通运输系统工程与信息, 2022, 22(1): 37-48.
[6]	马小龙, 余强, 刘建蓓. 基于路侧毫米波雷达的车辆碰撞概率计算方法[J]. 交通运输系统工程与信息, 2022, 22(1): 57-66.
[7]	廖鹏, 唐铁桥. 基于车辆动力传动和转向系统的换道轨迹优化策略[J]. 交通运输系统工程与信息, 2022, 22(1): 98-105.
[8]	刘永红, 罗霞, 胡剑鹏. 考虑临时和预约需求的共享泊位动态分配方法[J]. 交通运输系统工程与信息, 2022, 22(1): 171-181.
[9]	袁振洲, 郭曼泽, 彭泳鑫, 杨洋. 基于梯度关联规则的老年行人交通事故风险识别[J]. 交通运输系统工程与信息, 2022, 22(1): 195-208.
[10]	张玉婷, 陈波佑, 张双焱, 闫学东, 李晓梦. 抵近信控交叉口分心驾驶识别模型[J]. 交通运输系统工程与信息, 2022, 22(1): 217-224.
[11]	宋浪, 王健, 杨滨毓, 安实. 连续流交叉口左转非机动车交通组织创新设计[J]. 交通运输系统工程与信息, 2022, 22(1): 225-233.
[12]	赵建东, 陈溱, 焦彦利, 张凯丽, 韩明敏. 重点营运车辆的异常驾驶行为识别研究[J]. 交通运输系统工程与信息, 2022, 22(1): 282-291.
[13]	白婧荣, 唐伯明, 孙宗元, 毕辉云, 向恬君. 毗邻互通立交特长隧道驾驶负荷研究[J]. 交通运输系统工程与信息, 2022, 22(1): 301-310.
[14]	郭彦茹, 罗志雄, 王家川, 何方. 数据驱动的共享单车停放区规划方法研究[J]. 交通运输系统工程与信息, 2021, 21(6): 9-16.
[15]	李君羡, 沈宙彪, 童文聪, 吴志周. 基于分类车头时距的城市道路大型车影响分析[J]. 交通运输系统工程与信息, 2021, 21(6): 55-62.