城市路网实时动态交通信息预测方法的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
智能交通系统(Intelligent Transportation Systems,ITS)是目前国际公认的缓解城市交通拥挤的最佳途径。道路交通信息是所有ITS项目不可缺少的前提和主要内容。如何在短时间内得到这些信息,以及如何根据这些信息快速确定出最佳行驶路径,已成为ITS领域的一个前沿问题,交通路网短时交通信息预测理论、模型与算法的优劣直接影响整个ITS的实施。交通状况信息中最基本的参数就是通过路段的交通流量和旅行时间,它们代表着路段的物理属性和交通特性,也是用户所关心的最直接指标。短时交通信息预测可以通过城市交通信息发布平台为出行者提供实时的交通信息,帮助他们进行路径的选择及诱导。
     人工神经网络由于其良好的非线性映射能力,已在交通预测中得到广泛应用。训练神经网络常采用BP(Back Propagation)算法,但BP算法具有收敛速度慢,易陷入局部最小的缺点。为了加快神经网络的学习速率,许多并行学习算法被相继提出,本文采用一种并行非线性优化技术训练神经网络,实现有检测器路段的交通流预测。利用并行变尺度拟牛顿法(Self-Scaling Parallel Quasi-Newton,SSPQN)改进BP算法,每次迭代时产生多个搜索方向,各并行子任务在不同的方向上执行非精确线性搜索以寻找最优点。并在MPICH并行环境下对上述算法进行测试分析。实验结果表明在达到相同训练精度的前提下,SSPQN算法有效提高了收敛速度,预测效果优于BP算法,基本达到实测路况交通流预测的要求。
     为了实现路网中任意路段的流量预测,针对无检测器路段,使用多元统计分析中的多维标度法对城市路网相关性进行分析,实现对整个路网的划分,借助同类交叉口的有检测器路段的流量对无检测器路段的流量进行预测。
     最后采用旅行时间函数模型经过参数标定,建立适用于国内城市的旅行时间估计模型,进而建立短时旅行时间的预测模型,并在VISSIM仿真平台上对该模型进行验证,实验结果表明满足动态交通诱导的要求。
Intelligent Transportation Systems (ITS) is the internationally recognized best way to relieve urban traffic congestion. Road traffic information is an indispensable prerequisite and main content for all ITS projects. The problem that how to get these messages in a short time and how to use these informations to determine quickly the optimal driving path has become a cutting-edge issues in the field of ITS, traffic network short-time traffic information prediction theory, the pros and cons of model and algorithm directly affect the whole ITS implementation. The traffic flow and travel time through section is the most basic parameters of traffic information. It not only represents the physical properties and transport properties of some section, but also is the most direct interest concerned by users. Short-term traffic information prediction can provide real-time traffic information through urban traffic information release platform for the trip, also help them to the path selection and induction.
     The artificial neural network is a new method of maths modeling. Because of better adaptability, it has been widely applied in traffic forecasting. Back-propagation (BP) algorithm is usually used to train the neural network, but it converges slowly and easily gets into local minimum. To speed up learning of neural network, many parallel learning algorithms are proposed. This thesis uses a kind of parallel nonlinear optimization technique to train networks, realizing parallelism based on learning algorithm. BP algorithm is improved by parallel self-scaling quasi-Newton (SSPQN) algorithm. In each iteration, a set of search directions is generated. Each subtask carries out inexact linear search along each direction to find the optimal point. This thesis tests and analyses the above algorithm in the MPICH parallel environment. The experimental result shows that with the same training precision the SSPQN parallel algorithm effectively improves the convergence speed, has better forecast effects than traditional BP neural network, and meets the requirement of traffic flow forecasting.
     In order to achieve a prediction of traffic volume in arbitrary section of the network, the thesis use multivariate statistical analysis of the multidimensional scaling of urban road network correlation analysis for non-detector section, it achieves the division of the entire network, and predictions the flow of the non-detector section by using the flow rate of the same intersection with a detector section.
     Finally, the thesis estimates the travel time using travel model time after the parameter calibration, meanwhile it establishs a short-term travel time prediction model, and validates the model in the VISSIM simulation platform. Experimental results show that it meets the dynamic traffic-induced demand.
引文
[1]杨兆升.智能运输系统概论(第二版)[M].北京:人民交通出版社,2009.
    [2]张赫,杨兆升,李贻武.无检测器交叉口交通流量预测方法综合研究[J].公路交通科技,2002,19(1):91-95.
    [3]刘静,关伟.交通流预测方法综述[J].公路交通科技,2004,21(3):82-85.
    [4]HuangKun,ChenSenfa,ZhouZhenguo,et al.Research on a non-linear chaotic prediction model for urban traffic flow[J].Journal of Southeast University (English Edition),Vol.19,No.4,2003:410-413.
    [5]SUN S L,ZHANG C S,YU G Q.A bayesian network approach to traffic flow prediction [J].IEEE Transactions on Intelligent Transportation Systems,2006,7(1):124-132.
    [6]BRIAN L.SMITH,MICHAEL J.DEMESTSKY.Traffic flow forecasting:Comparision of modeling approaches[J].Journal of Transportation Engineering,1997,Vol.123,No.4:281-266.
    [7]HONGBIN YIN,S C WONG,JIANMIN XU,et al.Urban traffic flow prediction using a fuzzy-neural approach[J].Transportation Research Part C,2002,(10):85-98.
    [8]杨立才,贾磊.粗神经网络及其在交通流预测中的应用[J].公路交通科技,2004,21(10):95-98.
    [9]赵建玉,贾磊,杨立才等.基于粒子群优化的RBF神经网络交通流预测[J].公路交通科技,2006(7):116-119.
    [10]YUANCHANG XIE,YUNLONG ZHANG,ZHIRUI YE.Short-term traffic volume forecasting using Kalman filter with discrete wavelet decomposition[J].Computer-Aided Civil and Infrastructure Engineering,22(2007):326-334.
    [11]YUN S Y,NAMKOONG S.A performance evaluation of neural network models in traffic volume forecasting[J].Mathematical and Computer Modeling,1998,27(6):293-310.
    [12]YASUNAGA M,YOSHIDA E.Optimization of parallel BP implementation:training speed of 1056 MCUPS on the massively parallel computer CP-PACS[C].IEEE International Joint Conference on Neural Networks Proceedings,Hawaii,1998:563-568.
    [13]LI JUN,LI YUANXIANG,XU JINGWEN,et al.Parallel training algorithm of BP neural networks[C].Proceedings of the 3rd World Congress on Intelligent Control and Automation,Vol.2,2000:872-876.
    [14]PAUl K.H.PHUA,DAOHUA MING.Parallel nonlinear optimization techniques for training neural metworks[J].IEEE Transactions on Neural Networks,2003,14(6):1460-1468.
    [15]GUOZHEN TAN,QINGING DENG,TIAN ZHU,et al.A dish parallel BP for traffic flow forecasting[C].International Conference on Computational Intelligence and Security.Harbin.2007:546-549.
    [16]王志建.基于遗传回归分析的无检测器交叉口流量预测研究[D](博士学位论文).长春:吉林大学.2008.
    [17]KISGYORGY,L.,RILETT,L.R.Travel time prediction by advanced neural network [J].Periodic Polytechnica Series in Civil Engineering,2002,46(1):15-32.
    [18]CHUN-HSIN WU,JAN-MING HO,D.T.Lee.Travel-time prediction with support vector regression[J].IEEE Transactions on Intelligent Transportation Systems,VOL.5,NO.4,2004:276-281.
    [19]SEN,A.,LIU,N.,THAKURIAH,P.,et al.Short-term forecasting of link travel times:A preliminary proposal[J].ADVANCE Working Paper Series,Number 7,Illinois,Chicago,1991:98-103.
    [20]JULA,n.,DESSOUKY,M.,IOANNOU,P.A.Real-time estimation of travel times along the arcs and arrival times at the nodes of dynamic stochastic networks[J].IEEE Tansactions on Intelligent Transportation System,2008,9(1):97-110.
    [21]X.ZHANG,J.A.Rice.Short-term travel time prediction[J].Transp.Res.,vol.11C,NO.3/4,2003:187-210.
    [22]CHIEN-HUNG Wei,YING Lee.Development of freeway travel time forecasting models by integrating different sources of traffic data[J].IEEE Transactios on Vehicular Technology,VOL.56,NO.6,2007:110-118.
    [23]D.Park,L.Rilett.Forecasting multiple-period freeway link travel times using modular neural networks[J].Transportation Research Record 1617,Washington,DC:TRB,Nat.Res.Council,1998:163-170.
    [24]Park D,Rilett L R,Han G.Spectral basis neural networks for real-time travel time forecasting[J].Journal of Transportation Engineering,1999,125(6):515-523.
    [25]A.Kotsialos,M.Papageorgiou,C.Diakaki,et al.Traffic flow modeling of large-scale motorway networks using the macroscopic modeling tool METANET[C].IEEE Trans.Intell.Transport Syst.,vol.3,2002:282-292.
    [26]R.Cayford,W.H.Lin,C.F.Daganzo.The NETCELL simulation package:Technical description[R].Univ.California,Berkeley,CA PATH Res.Rep.UCB-ITS-PRR-97-23,1997.
    [27]杨兆升,朱中.基于BP神经网络的路径旅行时间实时预测模型[J].系统工程理论与实践,1999,19(8):59-64.
    [28]杨兆升,保丽霞,朱国华.基于Fuzzy回归的快速路行程时间预测模型研究[J].公路交通科技,2004,21(3):78-81.
    [29]贺国光,徐岩宇.车辆线路引导系统的行驶时间预测模型研究[J].中国公路学报,1998,11(3):79-86.
    [30]杨昊,钟雁,钱大琳.城市交通流路段旅行时间预测模型[J].北方交通大学学报,2001,25(2):65-69.
    [31]姚智胜,邵春福,熊志华.支持向量机在路段行程时间预测中的应用研究[J].公路交通科技,2007,24(9):96-99.
    [32]杨晓光,蔡润林,庄斌.基于车牌自动识别系统的城市道路行程时间预测算法[J].交通与计算机,2005,23(3):29-32.
    [33]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
    [34]王进,史其信.短时交通流预测模型综述[J].中国公共安全学术卷,2005,6(1):92-98.
    [35]范佳妮,王振雷,钱锋.BP人工神经网络隐层结构设计的研究进展[J].控制工程,2005,12(增刊):105-109.
    [36]唐焕文,秦学志.实用最优化方法(第三版)[M].大连:理工大学出版社,2004.
    [37]袁亚湘.非线性规划数值方法[M].上海:上海科学技术出版社,1993.
    [38]R Fletcher著.游兆永,徐成贤,吴振国等译.实用最优化方法[M].天津:天津科技翻译出版公司,1990.
    [39]Li J,Li Y,Xu J,et al.Parallel training algorithm of BP neural networks[C].Proceedings of the 3rd World Congress on Intelligent Control and Automation,Hefei,China,2000:872-876.
    [40]陈国良.并行算法实践[M].北京:高等教育出版社,2004.
    [41]朱建平.应用多元统计分析[M].北京:科学出版社,2006.
    [42]宋现敏.城市交叉口信号协调控制方法研究[D](博士学位论文).吉林:吉林大学交通学院,2008.
    [43]S.TURNER,W.EISELE,R.BENZ,and D.HOLDENER.Travel time data collection handbook FHWA-PL-98-035[R].Texas Transportation Institute,College Station,Texas,1998.
    [44]LELITHA DEVI VANAJAKSHI.Estimation and prediction of travel time from loop detector data for intelligent transportation systems applications[D].Texas A&M University,2004.
    [45]Bureau of Public Roads.Traffic assignment manual[R].US Department of Commerce.P.,1964.
    [46]陆化谱.交通规划理论与方法[M].北京:清华大学出版社,1998.
    [47]杨佩昆,钱林波.交通分配中路段旅行时间函数研究[J].同济大学学报.1994,22(1):27-32.
    [48]肖秋生,郭占金,林秉良等.旅行时间随交通流量变化规律的研究[J].中国公路学报.1991,4(3):41-46.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700