2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

考虑交通流非线性特性的交通信号迭代学习控制策略

闫飞 李浦 阎高伟 任密蜂

闫飞, 李浦, 阎高伟, 任密蜂. 考虑交通流非线性特性的交通信号迭代学习控制策略. 自动化学报, 2021, 47(9): 2238−2249 doi: 10.16383/j.aas.c190183
引用本文: 闫飞, 李浦, 阎高伟, 任密蜂. 考虑交通流非线性特性的交通信号迭代学习控制策略. 自动化学报, 2021, 47(9): 2238−2249 doi: 10.16383/j.aas.c190183
Yan Fei, Li Pu, Yan Gao-Wei, Ren Mi-Feng. An iterative learning control strategy for traffic signals considering nonlinear characteristics of traffic flow. Acta Automatica Sinica, 2021, 47(9): 2238−2249 doi: 10.16383/j.aas.c190183
Citation: Yan Fei, Li Pu, Yan Gao-Wei, Ren Mi-Feng. An iterative learning control strategy for traffic signals considering nonlinear characteristics of traffic flow. Acta Automatica Sinica, 2021, 47(9): 2238−2249 doi: 10.16383/j.aas.c190183

考虑交通流非线性特性的交通信号迭代学习控制策略

doi: 10.16383/j.aas.c190183
基金项目: 国家自然科学基金(61703300), 中国博士后科学基金(2019M651082), 山西省应用基础研究项目(201801D221191)资助
详细信息
    作者简介:

    闫飞:太原理工大学电气与动力工程学院副教授. 主要研究方向为迭代学习控制, 城市交通信号控制, 智能交通系统. 本文通信作者. E-mail: yanfei@tyut.edu.cn

    李浦:太原理工大学电气与动力工程学院硕士研究生. 主要研究方向为迭代学习控制, 城市交通信号控制. E-mail: lipu12281@163.com

    阎高伟:太原理工大学电气与动力工程学院教授. 主要研究方向为复杂工业控制系统, 智能控制理论及其应用, 智能信息处理. E-mail: yangaowei@tyut.edu.cn

    任密蜂:太原理工大学电气与动力工程学院副教授. 主要研究方向为随机控制, 性能评价, 故障诊断. E-mail: renmifeng@126.com

An Iterative Learning Control Strategy for Traffic Signals Considering NonlinearCharacteristics of Traffic Flow

Funds: Supported by National Natural Science Foundation of China (61703300), China Postdoctoral Science Foundation (2019M651082), and Applied Basic Research Program of Shanxi Province (201801D221191)
More Information
    Author Bio:

    YAN Fei Associate professor at the College of Electrical and Power Engineering, Taiyuan University of Technology. His research interest covers iterative learning control, urban traffic signal control, and intelligent traffic system. Corresponding author of this paper

    LI Pu Master student at the College of Electrical and Power Engineering, Taiyuan University of Technology. His research interest covers iterative learning control and urban traffic signal control

    YAN Gao-Wei Professor at the College of Electrical and Power Engineering, Taiyuan University of Technology. His research interest covers complex industrial control system, intelligent control theory and application, and intelligent information processing

    REN Mi-Feng Associate professor at the College of Electrical and Power Engineering, Taiyuan University of Technology. Her research interest covers stochastic control, control performance assessment, and fault diagnosis

  • 摘要: 现实中城市交通流的运行具有很强的非线性特性, 采用简单的线性模型难以全面描述交通流的实际运行过程. 本文在考虑城市交通流非线性动态特性的基础上, 提出了一种非线性交通流排队模型, 并基于宏观交通流固有的周期性特征, 设计了交叉口信号的迭代学习控制策略. 通过对交叉口信号的迭代学习控制, 使交叉口各进口道的车辆排队长度尽可能趋于均衡, 提高交叉口信号有效绿灯时间的利用率, 从而提高路网的通行效率. 最后通过严格的数学推导证明了该方法的收敛性, 仿真研究及实验结果验证了所提方法的有效性.
  • 图  1  交叉口相位示意图与路段交通流模型

    Fig.  1  The intersection phase and road traffic flow model

    图  2  太原市某区域路网结构简图

    Fig.  2  The road network structure of one region in Taiyuan

    图  3  三种控制方案下各交叉口相位车辆排队长度差值

    Fig.  3  The differences of queue lengths at different phases of each intersection for the three control schemes

    图  4  三种控制方案下交叉口4各相位的车辆排队情况

    Fig.  4  The queue lengths at Intersection 4 for the three control schemes

    图  5  三种控制方案下交叉口9各相位的车辆排队情况

    Fig.  5  The queue lengths at Intersection 9 for the three control schemes

    图  6  平均车辆排队长度差值随迭代次数的变化情况

    Fig.  6  The average difference of queue lengths of allintersections after each iteration

    图  7  三种控制方案下路网的平均延迟时间

    Fig.  7  The average delay time of road network for thethree control schemes

    图  8  三种控制方案下路网的平均停车次数

    Fig.  8  The average number of stops for the threecontrol schemes

    图  9  三种控制方案下路网内车辆的平均速度

    Fig.  9  The average speed of vehicles for the threecontrol schemes

    表  1  各路段车道数

    Table  1  The number of lanes in each link

    道路情况道路编号
    双向 3 车道道路$x_{1},x_{2},x_{3},x_{4},x_{9},x_{10},x_{11},x_{14},x_{17},x_{20},x_{23}$
    双向 4 车道道路$x_{12},x_{13},x_{15},x_{16},x_{18},x_{19},x_{21},x_{22}$
    双向 7 车道道路$x_{5},x_{6},x_{7},x_{8}$
    下载: 导出CSV

    表  2  路网的输入流量(veh/h)

    Table  2  The inflows of the road network (veh/h)

    时段/min$x_{1},x_{4},x_{9},x_{12},x_{14},x_{21},x_{23}$$x_{13},x_{22}$$x_{5},x_{8}$
    $0\sim20$1 6003 0002 000
    $20\sim40$2 0003 4002 400
    $40\sim60$1 8003 2002 200
    下载: 导出CSV

    表  3  交叉口的迭代学习增益

    Table  3  The iterative learning gains at different intersections

    交叉口编号学习增益值
    1, 2, 3, 4, 5, 6, 7, 8, 90.1
    下载: 导出CSV
  • [1] Genders W, Razavi S. Asynchronous n-step Q-learning adaptive traffic signal control. Journal of Intelligent Transportation Systems, 2019, 23(4): 319-331 doi: 10.1080/15472450.2018.1491003
    [2] van de Weg G S, Vu H L, Hegyi A, Hoogendoorn S P. A hierarchical control framework for coordination of intersection signal timings in all traffic regimes. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(5): 1815-1827 doi: 10.1109/TITS.2018.2837162
    [3] Zhang Y N, Zhou Y H. Distributed coordination control of traffic network flow using adaptive genetic algorithm based on cloud computing. Journal of Network and Computer Applications, 2018, 119: 110-120 doi: 10.1016/j.jnca.2018.07.001
    [4] 赵欢. 单信号交叉口绿灯时间无模型自适应控制 [硕士学位论文]. 北京交通大学, 中国, 2009.

    Zhao Huan. Model-free adaptive control of green light time at single signalized intersection [Master thesis], Beijing Jiaotong University, China, 2009.
    [5] Hao J G, Hou Z S, Bu X H. The iterative learning approach for vehicle queuing length balanced-control of the signalized isolated intersection. In: Proceedings of the 30th Chinese Control Conference. Yantan, China: IEEE, 2011. 5556−5561
    [6] 齐驰, 侯忠生, 贾琰. 基于排队长度均衡的交叉口信号配时优化策略. 控制于决策, 2012, 27(8): 1191-1194

    Qi Chi, Hou Zhong-Sheng, Jia Yan. Optimal signal timing strategy based on the equilibrium of queue length. Control and Decision, 2012, 27(8): 1191-1194
    [7] Hou Z S, Xu J X, Yan J W. An iterative learning approach for density control of freeway traffic flow via ramp metering. Transportation Research Part C, 2008, 16(1): 71-97 doi: 10.1016/j.trc.2007.06.007
    [8] Arimoto S, Kawamura S, Miyazaki F. Bet-tering operation of robots by learning. Journal of Robotic Systems, 1984, 1(2): 123-140 doi: 10.1002/rob.4620010203
    [9] 池荣虎, 侯忠生, 黄彪. 间歇过程最优迭代学习控制的发展: 从基于模型到数据驱动. 自动化学报, 2017, 43(6): 917-932

    Chi Rong-Hu, Hou Zhong-Sheng, Huang Biao. Optimal iterative learning control of batch processes: from model-based to data-driven. Acta Automatica Sinica, 2017, 43(6): 917-932
    [10] Hou Z S, Xu J X. Freeway traffic density control using iterative learning control approach. In: Proceedings of the 6th International conference on Intelligent Transportation Systems. Shanghai, China: IEEE, 2003. 1081−1086
    [11] 侯忠生, 宴静文. 带有迭代学习前馈的快速路无模型自适应入口匝道控制. 自动化学报, 2009, 35(5): 588-595

    Hou Zhong-Sheng, Yan Jing-Wen. Model free adaptive control based freeway ramp metering with feedforward iterative learning controller. Acta Automatica Sinica, 2009, 35(5): 588-595
    [12] Hou Z S, Xu X, Yan J W, Xu J W, Xiong G. A complementary modularized ramp metering approach based on iterative learning control and ALINE. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(4): 1305-1318 doi: 10.1109/TITS.2011.2157969
    [13] Hou Z S, Xu X, Yan J W, Xu J W, Li Z J. Modified iterative-learning-control-based ramp metering strategies for freeway traffic control with iteration-dependent factors. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(3): 606-618
    [14] 郑一辰, 张毅, 胡坚明. 一种基于迭代学习的自适应交通信号控制方法. 交通运输系统工程与信息, 2010, 10(6): 34-40 doi: 10.3969/j.issn.1009-6744.2010.06.005

    Zheng Yi-Chen, Zhang Yi, Hu Jian-Ming. Iterative learning based adaptive traffic signal contral. Journal of Transporation Systems Engineering and Information Technology, 2010, 10(6): 34-40 doi: 10.3969/j.issn.1009-6744.2010.06.005
    [15] Huang W, Viti F, Tampère C. An iterative learning approach for signal control in urban traffic networks. In: Proceedings of the 16th Internaing conference on Intelligent Transportation Systems. Hague, the Netherland: IEEE, 2013. 468−473
    [16] Yan F, Tian F L, Shi Z K. An iterative learning approach for traffic signal control of urban road networks. IET Control Theory and Applications, 2017, 11(4): 466-475 doi: 10.1049/iet-cta.2016.0376
    [17] Yan F, Tian F L, Shi Z K. An extended signal control strategy for urban network traffic flow. Physica A: Statistical Mechanics and its Applications, 2016, 445: 117-127 doi: 10.1016/j.physa.2015.10.047
    [18] Yan F, Tian F L, Shi Z K. Effects of iterative learning based signal control strategies on macroscopic fundamental diagrams of urban road networks. International Journal of Modern Physics C, 2016, 27(4): 1650045 doi: 10.1142/S0129183116500455
    [19] Yan F, Yan G W, Ren M F, Tian J Y, Shi Z K. A novel control strategy for balancing traffic flow in urban traffic network based on iterative learning control. Physica A: Statistical Mechanics and its Applications, 2018, 508: 519-531 doi: 10.1016/j.physa.2018.05.134
    [20] Gazis D C, Potts R B. The oversaturated intersection. In: Proceedings of the 2nd International Symposium on the Theory of Road Traffic Flow. London, UK: 1963: 231−237
    [21] Liu Y, Chang G L. An arterial signal optimization model for intersections experiencing queue spillback and lane blockage. Transportation Research Part C, 2011, 19(1): 130-144
    [22] Sun M X, Wang D W. Initial shift issues on discrete-time iterative learning control with system relative degree. IEEE Transactions on Automatic Control, 2003, 48(1): 144-148. doi: 10.1109/TAC.2002.806668
    [23] 严求真, 孙明轩, 蔡建平. 迭代学习控制的参考信号初始修正方法. 自动化学报, 2017, 43(8): 1470-1477

    Yan Qiu-Zhen, Sun Ming-Xuan, Cai Jian-Ping. Reference-signal rectifying method of iterative learning control. Acta Automatica Sinica, 2017, 43(8): 1470-1477
    [24] Shim J, Yeo J, Lee S, Hamdar S H, Jang K. Empirical evaluation of influential factors on bifurcation in macroscopic fundamental diagrams. Transportation Research Part C, 2019, 102: 509-520 doi: 10.1016/j.trc.2019.03.005
  • 加载中
图(9) / 表(3)
计量
  • 文章访问数:  1067
  • HTML全文浏览量:  144
  • PDF下载量:  208
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-03-19
  • 录用日期:  2019-08-15
  • 刊出日期:  2021-10-13

目录

    /

    返回文章
    返回