Dynamic programming - neural network real-time traffic adaptive signal control algorithm

被引:16
|
作者
Teodorovic, D [1 ]
Varadarajan, V
Popovic, J
Chinnaswamy, MR
Ramaraj, S
机构
[1] Virginia Polytech Inst & State Univ, Dept Civil & Environm Engn, Falls Church, VA 22043 USA
[2] Univ Belgrade, Fac Transport & Traff Engn, Belgrade 11000, Serbia Monteneg
[3] PB Farradyne, Rockville, MD 20852 USA
[4] Oklahoma State Univ, Sch Ind Engn & Management, Stillwater, OK 74078 USA
[5] Virginia Polytech Inst & State Univ, Dept Comp Sci, Falls Church, VA 22043 USA
关键词
real time traffic adaptive control; neural networks; dynamic programming;
D O I
10.1007/s10479-006-7376-z
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
In this paper, an "intelligent" isolated intersection control system was developed. The developed "intelligent" system makes "real time" decisions as to whether to extend (and how much) current green time. The model developed is based on the combination of the dynamic programming and neural networks. Many tests show that the outcome (the extension of the green time) of the proposed neural network is nearly equal to the best solution. Practically negligible CPU times were achieved, and were thus absolutely acceptable for the "real time" application of the developed algorithm.
引用
收藏
页码:123 / 131
页数:9
相关论文
共 50 条
  • [31] An efficient adaptive search algorithm for scheduling real-time traffic
    Xie, GG
    Lam, SS
    [J]. 1996 INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS, PROCEEDINGS, 1996, : 14 - 22
  • [32] Double Deep Q-Network with Dynamic Bootstrapping for Real-Time Isolated Signal Control: A Traffic Engineering Perspective
    Zheng, Qiming
    Xu, Hongfeng
    Chen, Jingyun
    Zhang, Dong
    Zhang, Kun
    Tang, Guolei
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (17):
  • [33] Real-time dynamic traffic assignment and path-based signal coordination: Application to network traffic management
    Abdelghany, Khaled F.
    Valdes, Didier M.
    Abdelfatah, Akmal S.
    Mahmassani, Hani S.
    [J]. Transportation Research Record, (1667): : 67 - 76
  • [34] Real-time dynamic traffic assignment and path-based signal coordination: Application to network traffic management
    Department of Civil Engineering, ECJ 6.2, University of Texas at Austin, Austin, TX 78712, United States
    [J]. Transp Res Rec, 1667 (67-76):
  • [35] REAL-TIME CONTROL USING A NEURAL NETWORK
    WOOD, D
    [J]. BT TECHNOLOGY JOURNAL, 1992, 10 (03): : 69 - 76
  • [36] Neural-network-based cycle length design for real-time traffic control
    Kim, Jin-Tae
    Lee, Jeongyoon
    Chang, Myungsoon
    [J]. CANADIAN JOURNAL OF CIVIL ENGINEERING, 2008, 35 (04) : 370 - 378
  • [37] Integrated transit priority and rail/emergency preemption in real-time traffic adaptive signal control
    Mirchandani, PB
    Lucas, DE
    [J]. ITS JOURNAL, 2004, 8 (02): : 101 - 115
  • [38] A recurrent neural network for real-time computation of semidefinite programming
    Jiang, DC
    Wang, J
    [J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1640 - 1645
  • [39] A dynamic inter-vehicle communication network for the support of real-time traffic control
    Bolla, R
    Davoli, F
    Nobile, C
    [J]. TRANSPORTATION SYSTEMS 1997, VOLS 1-3, 1997, : 1051 - 1055
  • [40] Real-time traffic signal control with swarm optimization methods
    Celtek, Seyit Alperen
    Durdu, Akif
    Ali, Muzamil Eltejani Mohammed
    [J]. MEASUREMENT, 2020, 166 (166)