基于隐Markov模型的短时交通崩溃事件预测

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

清华大学辅仁网/2017-07-07

周浩, 胡坚明, 张毅, 沈映真

清华大学自动化系, 北京 100084

Short-term traffic breakdown prediction using a hidden Markov model

ZHOU Hao, HU Jianming, ZHANG Yi, SHEN Yingzhen

Department of Automation, Tsinghua University, Beijing 100084, China

摘要:

输出: BibTeX | EndNote (RIS)

摘要交通崩溃事件会造成道路通行能力下降，成为导致城市快速路拥堵的主要原因之一，精准的短时交通崩溃事件预测在交通管理与控制中具有重要意义。该文以美国加州高速公路性能评估系统（PeMS）提供的交通流数据为基础，对道路的崩溃状态进行了分级定义，并以道路崩溃状态为隐状态、道路占有率为显状态，结合二者之间的联系，建立了隐Markov模型。通过数理统计，对模型参数进行了学习，最后采用Viterbi算法对该模型进行了求解，实现了快速路交通崩溃事件的预测。预测结果与实际数据的对比表明：该方法能预测大部分的交通崩溃事件。

关键词 ：交通崩溃,PeMS,隐Markov模型,Viterbi算法

Abstract：Traffic breakdown reduces road capacity as one of the main factors causing congestion on urban expressways. Accurate short-term traffic breakdown predictions on urban expressways are becoming more and more important because of their vital role in traffic management and control. Traffic flow data was obtained from the Caltrans performance measurement system (PeMS) with traffic breakdown states classified by a lane-based method. A Hidden Markov model (HMM) is then established with the traffic breakdown state as the hidden state and the road occupancy as the observed state with the Viterbi algorithm to solve the problem. The traffic breakdowns were successfully predicted to show that the HHM accurately predicts short-term traffic breakdowns.

Key words：traffic breakdown PeMS hidden Markov model Viterbi algorithm

收稿日期: 2016-03-15 出版日期: 2016-12-20

ZTFLH:

U491.1+4

通讯作者:胡坚明,副教授,E-mail:hujm@mail.tsinghua.edu.cnE-mail: hujm@mail.tsinghua.edu.cn

引用本文:

周浩, 胡坚明, 张毅, 沈映真. 基于隐Markov模型的短时交通崩溃事件预测[J]. 清华大学学报（自然科学版）, 2016, 56(12): 1333-1340.
ZHOU Hao, HU Jianming, ZHANG Yi, SHEN Yingzhen. Short-term traffic breakdown prediction using a hidden Markov model. Journal of Tsinghua University(Science and Technology), 2016, 56(12): 1333-1340.

链接本文:

http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2016.25.043或 http://jst.tsinghuajournals.com/CN/Y2016/V56/I12/1333

图表:

图1 路段所在位置

图2 路段结构示意图(单位:km)

图3 v_t－δ_t 关系图

表1 单车道崩溃状态

表2 多车道崩溃状态分级设置

表3 隐状态转移概率矩阵

表4 两态对应概率矩阵

图4 交通崩溃事件预测流程

图5 交通崩溃事件预测结果

表5 交通崩溃事件预测与实测统计

图6 不同临界速度时的预测效果

表6 不同临界速度下的预测效果对比

图7 10min交通崩溃预测结果

参考文献:

[1]	Dong J, Mahmassani H S. Stochastic modeling of traffic flow breakdown phenomenon:Applimtion to predicting travel time reliability[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(4):1803-1809.
[2]	陈喜群. 交通流动态随机演化模型研究[D]. 北京:清华大学, 2012.CHEN Xiqun. Modeling Traffic Flow Dynamic and Stochastic Evolutions[D]. Beijing:Tsinghua University, 2012. (in Chinese)
[3]	Treiber M, Hennecke A, Helbing D. Congested traffic states in empirical observations and microscopic simulations[J]. Physical Review E, 2009, 62(2):1805-1824.
[4]	Sugiyama Y, Fukui M, Kikuchi M, et al. Traffic jams without bottlenecks-Experimental evidence for the physical mechanism of the formation of a jam[J]. New Journal of Physics, 2008, 10(3):033001.
[5]	Daniel J G, Glaister S. Road traffic demand elasticity estimates:A review[J]. Transport Reviews, 2004, 24(3):261-274.
[6]	Lee H K, Barlovic R, Schreckenberg M, et al. Mechanical restriction versus human overreaction triggering congested traffic states[J]. Physical Review Letters, 2004, 92(23):238702/1-4.
[7]	Okamura H, Watanabe S, Watanabe T. An empirical study on the capacity of bottlenecks on the basic suburban expressway sections in Japan[J]. Transportation Research Circular, 2000(E-C018):120-129.
[8]	Murashige Y. Countermeasure strategies against traffic congestion on motorways in Japan[J]. Procedia Social and Behavioral Sciences, 2011, 16:110-119.
[9]	Lorenz M R, Elefteriadou L. A probabilistic approach to defining freeway capacity and breakdown[J]. Transportation Research Circular, 2000(E-C018):84-95.
[10]	Evans J, Elefteriadou L, Gautam N. Probability of breakdown at freeway merges using Markov chains[J]. Transportation Research Part B, 2001, 35(3):237-254.
[11]	WANG Haizhong, Rudy K, LI Jia, et al. Calculation of traffic flow breakdown probability to optimize link throughput[J]. Applied Mathematical Modeling, 2010, 34(11):3376-3389.
[12]	Chow A, Lu X, Qiu T. Empirical analysis of traffic breakdown probability distribution with respect to speed an occupancy[C]//12th IFAC Symposium on Control in Transportation Systems. Berkeleys California, USA:Elsevier Science Direct-IFAC Papers Online, 2009, 42(15):472-477.
[13]	Blain L. Calculating delay on congested links using a state variable[C]//Proceedings of the 7th TRB Conference on the Application of Transportation Planning Methods. Boston, Massachusetts:Transportation Research Board Business Office, 2002:350-355.
[14]	CHEN Xiqun, LI Meng, ZHANG Liping, et al. Comparison of highway traffic breakdown features between U.S. and China using discrete wavelet transform:An empirical study[C]//Proceedings of the 12th COTA International Conference of Transportation Professionals. Reston, VA:American Society of Civil Engineers, 2012:545-556.
[15]	Ma D P, Nakamura H, Asano M. Lane based breakdown identification method at diverge sections for modeling breakdown probability[J]. Journal of the Transportation Research Record, 2013, 2395(1):83-92.

No related articles found!