区域交通控制的分析与研究
|
摘要
当前,随着我国经济的快速发展,城市化进程的加快、车辆保有数量迅速增加。随之而来的交通问题成为严重制约我国城市发展和居民生活质量的重要瓶颈。面对急剧增加的汽车数量和有限的交通资源,如何缓解大范围的交通拥堵,提高路网的通行能力,减少交通事件的发生数量、避免宝贵资源的浪费成为城市交通路网管理迫切需要解决的问题。区域交通控制作为智能交通系统研究的关键技术,因其可以显著的缓解以上交通问题,具有著的社会意义和经济价值,必将是未来智能交通研究领域的热点和关键。
本文以区域路网中的交叉口为研究对象,以实现交通流的有效疏导为目的,在广泛阅读相关资料的基础上,在以下几方面的做了深入的研究工作:
(1)总结了当前交通控制领域的研究现状,其中包括单路口交通控制研究与发展,干线交通控制研究与发展,区域交通控制研究与发展。特别就智能计算在交通控制中的研究发展进行了介绍,就常用的智能计算方法:模糊控制、进化计算、神经网络分别阐述了其在交通领域的应用研究现状,同时作为后续章节的必要准备,概述了交通控制过程中交通控制的重要参数和概念。
(2)以典型区域单路口为控制对象,构造了一个单路口离散化交通模型。该模型以车辆的放行流量和车辆到达率为输入常量,以排队长度为系统的状态变量,通过程序设计实现了交通模型的建模,采用爬山法优化了绿灯时间,减少了排队长度,从而验证了该模型模拟仿真交叉口通行状况的有效性,为后续研究提供了合适的参数尺度。
(3)针对固定相位单路口交通流的有效控制问题,提出包含相位转换模糊控制器和延时模糊控制器的两级模糊控制方法,其中相位转换模糊控制器实现相位转换的判断,延时模糊控制器判定延时的绿灯时间,文中就两级模糊控制器的实现给出了设计过程,通过仿真与感应控制比较得出,此方法达到了缩短绿灯延时时间,减少延误,使通行更为畅通的目的,但适应效果受车流饱和情况的影响。
(4)针对多路口区域交通控制具有复杂、随机、离散性强、受干扰因素多的特点,提出一种基于多智能体技术搭建的松散耦合关系的多智能体区域控制结构,并分别就其路口级控制多智能体结构设计、区域控制多智能体结构设计、中心控制多智能体结构设计给出了详细的描述。在具体的仿真过程中,以一个区域级交通智能体控制的路口单元为研究范围,重点研究了两路口在出现交通拥堵状况时的协调解决过程,在区域级智能体应对路口级智能体协调请求时,采用遗传算法优化控制参数,以实现对区域交通流的整体优化。结果表明,同等条件下,与传统的定时控制比较,各项指标性能有较大的提高,此方法有效可行。
At present, with the rapid economic development, accelerating the urbanization process, the number of vehicles maintains rapid growth in traffic. Therefore traffic problems as the important bottleneck seriously constrain urban development and quality of life for residents. The face of rapid increases in vehicle traffic volume and limited resources, how to relieve a wide range of traffic congestion, improve road network capacity, reduce the number of traffic incidents to avoid the waste of valuable resources into Urban Road Network Management urgently needs to be resolved problem. Regional Traffic Control as Intelligent Transportation System key technology, as it can significantly alleviate these traffic problems, with the social significance and economic value, will be the next hot field of intelligent transportation and key.
In this paper, in order to achieve effective to ease traffic flow for the purpose of information in a wide range of reading, the intersection of the regional road network in this study, based on the following aspects of the work done in-depth study:
(1)Summarize the current status of research in the field of traffic control, including the intersection traffic control research and development, Route Traffic Control research and development, regional traffic control research and development. Particularly on Intelligent Computing in research and development of traffic control were introduced, the commonly used methods of computational intelligence: fuzzy control, evolutionary computation, neural networks are described in the application of traffic sector Research. At the same time as the necessary preparations for the follow-up section, an overview is given about traffic control important parameters and concepts in the process of traffic control.
(2)To a typical single-intersection region as the control object, construct a single intersection discrete traffic model. In this model, the release of vehicle traffic and vehicles enter the constant arrival rate to queue length for the system state variables, through program design and implementation of traffic modeling, using small step test method optimized green time, reduce the queuing length, thereby validate the model simulation of the effectiveness of intersection conditions.
(3)for a fixed phase isolated intersection traffic flow control problem, including phase change proposed fuzzy controller and fuzzy controller for two-stage fuzzy control method, in which the phase transformation of fuzzy controller to judge the phase transition, delay fuzzy controller determine the delay of the green time, the text on the two fuzzy controller to achieve given the design process, the simulation compared with the sensor control obtained, this method achieved the green light to shorten the delay time, reduce delays, make access more the purpose of smooth, but the adaptation effect of saturation by the traffic situation.
(4)Considering multi-junction area traffic control complex, stochastic, discrete strong interference characteristics of many factors, the multi-agent control structure of the region is proposed based on multi-agent technology built of loosely coupled relationship and their control structure design of Intersection-level multi-agent, control structure design of regional multi-agent, structure design of the center control multi-agent are given a detailed description. In particular the simulation process to a regional multi-agent controller on the intersection traffic unit as the research scope, focus on the two junctions in the traffic jam situation of appears to coordinate the solution process. When the regional level agent faces intersection level agent coordination request, the genetic algorithm is used an important tool to optimize control parameters to achieve the overall regional traffic flow optimization. The results show that under the same conditions, compared with the traditional timing control, the index performance is greatly improved and this method is effective and feasible.
本文以区域路网中的交叉口为研究对象,以实现交通流的有效疏导为目的,在广泛阅读相关资料的基础上,在以下几方面的做了深入的研究工作:
(1)总结了当前交通控制领域的研究现状,其中包括单路口交通控制研究与发展,干线交通控制研究与发展,区域交通控制研究与发展。特别就智能计算在交通控制中的研究发展进行了介绍,就常用的智能计算方法:模糊控制、进化计算、神经网络分别阐述了其在交通领域的应用研究现状,同时作为后续章节的必要准备,概述了交通控制过程中交通控制的重要参数和概念。
(2)以典型区域单路口为控制对象,构造了一个单路口离散化交通模型。该模型以车辆的放行流量和车辆到达率为输入常量,以排队长度为系统的状态变量,通过程序设计实现了交通模型的建模,采用爬山法优化了绿灯时间,减少了排队长度,从而验证了该模型模拟仿真交叉口通行状况的有效性,为后续研究提供了合适的参数尺度。
(3)针对固定相位单路口交通流的有效控制问题,提出包含相位转换模糊控制器和延时模糊控制器的两级模糊控制方法,其中相位转换模糊控制器实现相位转换的判断,延时模糊控制器判定延时的绿灯时间,文中就两级模糊控制器的实现给出了设计过程,通过仿真与感应控制比较得出,此方法达到了缩短绿灯延时时间,减少延误,使通行更为畅通的目的,但适应效果受车流饱和情况的影响。
(4)针对多路口区域交通控制具有复杂、随机、离散性强、受干扰因素多的特点,提出一种基于多智能体技术搭建的松散耦合关系的多智能体区域控制结构,并分别就其路口级控制多智能体结构设计、区域控制多智能体结构设计、中心控制多智能体结构设计给出了详细的描述。在具体的仿真过程中,以一个区域级交通智能体控制的路口单元为研究范围,重点研究了两路口在出现交通拥堵状况时的协调解决过程,在区域级智能体应对路口级智能体协调请求时,采用遗传算法优化控制参数,以实现对区域交通流的整体优化。结果表明,同等条件下,与传统的定时控制比较,各项指标性能有较大的提高,此方法有效可行。
At present, with the rapid economic development, accelerating the urbanization process, the number of vehicles maintains rapid growth in traffic. Therefore traffic problems as the important bottleneck seriously constrain urban development and quality of life for residents. The face of rapid increases in vehicle traffic volume and limited resources, how to relieve a wide range of traffic congestion, improve road network capacity, reduce the number of traffic incidents to avoid the waste of valuable resources into Urban Road Network Management urgently needs to be resolved problem. Regional Traffic Control as Intelligent Transportation System key technology, as it can significantly alleviate these traffic problems, with the social significance and economic value, will be the next hot field of intelligent transportation and key.
In this paper, in order to achieve effective to ease traffic flow for the purpose of information in a wide range of reading, the intersection of the regional road network in this study, based on the following aspects of the work done in-depth study:
(1)Summarize the current status of research in the field of traffic control, including the intersection traffic control research and development, Route Traffic Control research and development, regional traffic control research and development. Particularly on Intelligent Computing in research and development of traffic control were introduced, the commonly used methods of computational intelligence: fuzzy control, evolutionary computation, neural networks are described in the application of traffic sector Research. At the same time as the necessary preparations for the follow-up section, an overview is given about traffic control important parameters and concepts in the process of traffic control.
(2)To a typical single-intersection region as the control object, construct a single intersection discrete traffic model. In this model, the release of vehicle traffic and vehicles enter the constant arrival rate to queue length for the system state variables, through program design and implementation of traffic modeling, using small step test method optimized green time, reduce the queuing length, thereby validate the model simulation of the effectiveness of intersection conditions.
(3)for a fixed phase isolated intersection traffic flow control problem, including phase change proposed fuzzy controller and fuzzy controller for two-stage fuzzy control method, in which the phase transformation of fuzzy controller to judge the phase transition, delay fuzzy controller determine the delay of the green time, the text on the two fuzzy controller to achieve given the design process, the simulation compared with the sensor control obtained, this method achieved the green light to shorten the delay time, reduce delays, make access more the purpose of smooth, but the adaptation effect of saturation by the traffic situation.
(4)Considering multi-junction area traffic control complex, stochastic, discrete strong interference characteristics of many factors, the multi-agent control structure of the region is proposed based on multi-agent technology built of loosely coupled relationship and their control structure design of Intersection-level multi-agent, control structure design of regional multi-agent, structure design of the center control multi-agent are given a detailed description. In particular the simulation process to a regional multi-agent controller on the intersection traffic unit as the research scope, focus on the two junctions in the traffic jam situation of appears to coordinate the solution process. When the regional level agent faces intersection level agent coordination request, the genetic algorithm is used an important tool to optimize control parameters to achieve the overall regional traffic flow optimization. The results show that under the same conditions, compared with the traditional timing control, the index performance is greatly improved and this method is effective and feasible.
引文
[1]卢伟真.城市交通废弃污染现状及其预测方法[J].力学与实践,2008,30(4):1-7.
[2]杜长海.计算智能及其在城市交通诱导系统中的应用研究[D].重庆:重庆大学图书馆,2009.
[3]王红.城市道路交通信号控制与优化算法的研究[D].济南:山东大学,2005.
[4]区域交通信号控制与交通诱导协同理论与关键技术研究[D].长春:吉林大学,2009.
[5] Pippis C P, Mandani E H. A fuzzy logic controller for a traffic junction[J]. IEEE Trans on SMC,1977,7(10):707-717.
[6] Gazis,D.C. Optimum control of a system of oversalrated interseetions[J]. OP.or.Res., 1964, 12(6): 815-831.
[7] Dunne,M.C,Potts,R.B. Algorithm for traffic control[J].OPer.Res.,1964,12(6):870-881.
[8] Miyata, S., M. Noda and T. Usami. STREAM-Strategic Realtime Control for Megalopolis-traffic[A].In: Proc. Of the 2nd World Congress on Intelligent Transport Systems[C]. London: CrossRef , 1996.
[9] Azura Che Soh,Mohammad Hamiruce Marhaban, Marzuki Khalid,etal. Modelling and optimization of a traffic intersection based on queue theory and markov decision control methods[A]. In: proceedings of the first Asia international conference on modeling &simulation[C]. Phuket: IEEE Computer Society, 2007.
[10] Xiao-Hua Yu.an integrated model for signalized traffic intersection control[A]. In: proceedings of the 2005 IEEE conference on control applications WB3.1[C]. Christchurch: IEEE Computer Society, 2005.
[11] Yun Wei,Qing Shao,Yin Han,etal. Intersection Signal Control Approach based on PSO and Simulation[A]. In: the Second International Conference on Genetic and Evolutionary Computing[C]. San Mateo : IEEE Computer Society,2008.
[12] Yafeng Yin. Robust optimal traffic signal timing[J]. Transportation Research Part B: Methodological, 2008, 42 (10):911-924.
[13] Hongchao Liu,Kevin N.BalK,Wei-Hua Lin. A reverse causal-effect modeling approach for signal control of an oversaturated intersection. Transportation Research Part C : Emerging Technologies[J], 2008,16 (6) 742-754.
[14]陈静,黄崇超.交通信号实时优化模型的算法研究[J].武汉大学学报,2006,39(6):93-95.
[15]肖业伟等.基于蚁群算法的交叉路口多相位信号配时优化[J].计算机工程与应用, 2008, 44(19):241-244.
[16]黄荣等.拥堵状态下信号交叉口通行能力计算方法[J].交通运输系统工程与信息, 2008, 8(3): 59-65.
[17]曲昭伟,刘士序,王殿海等.模拟电路的信号交叉口交通流模型[J].吉林大学学报, 2008, 38(1): 49-52.
[18]王海起,王劲峰.一种基于粒子群的交通信号离线配时优化方法[J].计算机工程与应用,2008,44(11):13-22.
[19]谢赛,魏武,江岸等.一种基于模糊逻辑-遗传算法的城市单交叉口交通信号控制方法[J].交通与计算机,2007,25(134):75-78.
[20] Jee-Hyong Lee, Keon-Myung Lee and Hyung Leekwang. Fuzzy Controller for Intersection Group[A]. In: Proceedings of 1995 IEEE/IAS International Conference on Industrial Automation and Control: Emerging Technologies[C]. Piscataway: IEEE Computer Society, 1995.
[21]陈森发,毛岚.城市交通信号灯模糊线控制及其仿真[J].系统仿真学报,2000,12(6):668-670 .
[22]沈国江,孙优贤.城市交通干线递阶模糊控制及神经网络实现[J].系统工程理论与实践, 2004, 12(4):100-105.
[23]史强,贾磊.基于模糊神经网络的交通干线分层递阶控制[J].控制工程,2006,13(6):543-546
[24]李灵犀,高海军,王飞跃.两相邻路口交通信号的协调控制[J].自动化学报,2003,29(6):948-952.
[25]马伟凤,刘智勇.城市交通干线的Q-学习控制算法[J].五邑大学学报(自然科学版), 2007, 21(3): 16-22.
[26] Haruko Fuji,Hikaru Shimizu. Development of a Signal Control System along the Route 2 in Hiroshima City[A]. In: Proceedings of the SICE Annual Conference[C]. Kagawa: IEEE Computer Society,2008.
[27]王正武,罗大庸,黄中祥等.线性系统协调优化模型及其改进粒子群算法研究[J].系统工程理论与实践,2007,5(10):165-171.
[28]李伟,李彦,何东之.基于线性规划的干线模糊补偿控制[J].公路交通科技,2007,24(8):110-114.
[29] Singh M.G.,DrewA.W.,CoalosJ.F.ComParison of Practical hierarchical control methods For intereonnected dynamical systems[J].Automatiea,1975(11):331-350.
[30] Kashii H.R,Saredi G.N.A learning algolrithm for adaptation to traffic’s dynamic variation[A].In: 6th IFAC sym.On Identificaton and System Parameter Estimation[C]. Washington : IEEE ComputerSociety,1982.
[31] Menga G, Patracco P. Area Traffic Control: decentralized approach[A]. In: Proc.European Conf.on applied Information Technology of IFIP[C]. Netherlands: IEEE Computer Society ,1979.
[32] Mavleod G.J,McCartney. Muti-level control of road traffic networks using microprocessor[J]. IEEE trends on on-line computer control system,1979,13(5):126-131.
[33] Asim ,AI-Khalili Urban. Traffic control: a general approach[J].IEEE Trans. OnSMC, 1985, 15(2): 260-271.
[34]李立源,曹大铸.道路交通流量最优预测与交叉口最优控制[J].控制理论与应用, 1993, 10(1): 67-72.
[35] Hong K.Lo,Elbert Chang,Yiu Cho Cang. Dynamic network traffic control[J]. Transportation Research Part A: Policy and Practice, 2001, 35(8):721-724.
[36] Feng Chen and Hao Pang. Study of multi-agent area coordination control for urban traffic[A]. In: proceeding of the 7thworld congress on intelligent control and automation[C].Chongqing: IEEE Computer Society, 2008.
[37] Fei-Yue Wang.Agent-Based Control for Networked Traffic Management Systems[J]. IEEE Intelligent Systems, 2005, 20(5):92-96.
[38] Li Xiaohong, Ren Shuhua, Shen Lan. A new traffic signal coordinated control method based on mobile technology[A]. In: proceeding of the 27th Chinese control conference[C]. Kunming : IEEE Computer Society ,2008.
[39] Dipti Srinivasan, Chee Choy, Ruey Long Cheu. Neural Networks for Real-Time Traffic Signal Control[J].IEEE transactions on intelligent transportation systems,2006,7(3):261-272.
[40] kazunori Mizuno, ukio Fukui, Seiichi, Nishihara. Urban Traffic Signal Control Based on Distributed Constraint Satisfaction[A].In: proceedings of the 41st Hawaii International conference on system science[C]. Waikoloa : IEEE Computer Society ,2008.
[41] Yi-Sheng Huang,Ta-Hsiang and Jenn-Huei Lin. A timed coloured Petrinet supervisor for urban traffic networks[A]. In:The Proceedings of the Multiconference on computational engineering in system applications[C].Beijing: IEEE Computer Society,2006.
[42] Junhua Wei, Anlin Wang and Nianci Du. Study of self-organizing control of traffic signals in an urban network based on cellular automata[J].IEEE transactions on vehicular technology, 2005, 54(2): 744-748.
[43] FYAN,M DRIDI, MOUDNI. Control of traffic lights intersection: a new branch and bound approach[A]. In: 2008 International Conference on Service Systems and Service Management[C]. Melbourne : IEEE Computer Society,2008.
[44] Suh-Wen Chuiou. An efficient computation algorithm for area traffic control problem with link capacity expansions[J]. Applied mathematics and computation, 2007 ,188(2):1094-1102.
[45] Yuan Wang, Zhaosheng Yang, Qing Guan. Novel traffic control system & its coordination model based on Large-scale systems hierarchical optimization theory[A]. In: Proceedings of the IEEE International conference on automation and logistics[C]. Jinan : IEEE Computer Society ,2007.
[46] Marco Ciccia Davide Giglio, Riccardo Minciardi and Matteo Viarengo. A queue-based macroscopic model for performance evaluation of congested urban traffic networks[A]. In: Proceeding of the 2007 IEEE intelligent transportation systems conference[C]. Seattle: IEEE Computer Society, 2007.
[47] Zhenjiang Li, Feng He, QingmingYao and Fei-Yue Wang. Signal controller design for agent-based traffic control system[A]. In: proceedings of the 2007IEEE international conference on networking, sensing and control[C]. London : IEEE Computer Society ,2007.
[48] Mei-Fang Chen, Gwo-Hshiung Tzeng, and Tzung-I Tang. Fuzzy MCDM Approach for Evaluation of Expatriate Assignments[J]. International Journal of Information Technology & Decision Making, 2005,4(2):277-296.
[49] kelsey. R, K.Bisset, M.Jamshidi. A simulation environment for fuzzy control of traffic systems[A].In: Proceedings of the Twelfth world congress of IFAC[C].Sydney: Pergamon Press,1993.
[50] J.Favilla, A.Machion, F.Gomide. Fuzzy traffic control: adaptive strategies[A].In: Proceedings of the intelligent Vehicles Symposium[C].San Francisco: IEEE Inc,1993.
[51] Nakatsuyama.M, H.Nagahashi, M.Nishizura. Fuzzy logic phase controller for traffic junctions in the one-way arterial road[A]. In: Proceedings of the Ninth Triennial World Congress of IFAC[C].Oxford:Pergamon Press,1985.
[52] Chiu.S, Chand.S. Adaptive traffic signal control using fuzzy logic[A].In: Proceedings of the intelligent Vehicles Symposium[C]. Detroit:1992.
[53] R.Hoyer,U.Jumar. An advanced fuzzy controller for traffic lights[A].In: Proceedings of the 1994 IFAC Artificial intelligence in Real Time Control[C]. New York: Pergamon Press Inc,1994.
[54] Mohamed B.Trabia, Mohamed S.Kaseko, Murali Ande. A two stage fuzzy logic controller fortraffic signals[J]. Transportation Research Part C: Emerging Technologies,1999,7(6):353-367.
[55] Jee-Hyong Lee, H Lee-Kwang. Distributed and cooperative fuzzy controllers for traffic intersections group[J]. IEEE transactions on systems, man, and cybernetics. Part C: Applications and reviews,1999,29(2): 263-271.
[56]徐冬玲,方建安,邵世煌.交通系统的模糊控制及其神经网络实现[J].信息与控制,1992,21(2):74-79.
[57]徐勋倩,黄卫.单路口交通信号多相位实时控制模型及其算法[J].控制理论与应用,2005, 22(3):413-416.
[58]陈洪,陈森发.单路口交通实时模糊控制的一种方法[J].信息与控制,1997,26(3):227-233.
[59]温慧英,尹宏宾,徐建闽.一种信号交叉口模糊交通控制方法[J].华南理工大学学报, 2000,28(6):1-5.
[60]刘智勇.单交叉口的多相位模糊控制[J].信息与控制,1999,28(6):453-458.
[61] Ella Bingham. Reinforcement learning in neuron-fuzzy traffic signal control[J]. European Journal of Operational Research,2001,131(2):232-241.
[62] T.H.Heng, T.K.Ko. Hierarchical fuzzy logic traffic control at a junction using genetic algorithm[A]. In: Proceedings of the 1998 IEEE International Conference on Fuzzy Systems[C]. Anchorage : IEEE Inc ,1998.
[63] Wu Wei, Mingjun Wang. Traffic signal control using fuzzy and neural network[A].IEEE International Conference on Systems, Man, and Cybernetics[C].Istanbul: IEEE Inc,2001.
[64]尹志宇.基于L-M神经网络的道路交通噪声预测研究[J].中国环境检测,2009,25(4):85-87.
[65]潘昱,张晶.基于城市路口相关性的交通流量预测[J].交通与计算机,2005,23(1):31-33.
[66]温惠英,周玮明.基于S型函数预处理的RBF神经网络交通流量预测[J].交通信息与安全.2009,27(4):22-25.
[67]严丽军,项湜伍.基于模糊神经网络的交通灯智能系统[J].上海师范大学学报(自然科学版),2009,38(4):384-387.
[68]唐少先,黄志辉,阳春华.基于模糊神经网络的车辆跟驰决策的研究[J].人工智能,2009,25(2):195-197.
[69]王明亮,郑建立.基于模糊神经网络的智能超车系统安全性预测的研究[J].信息安全,2007,23(3):59-60.
[70]梁军,陈小波,程显毅,等.基于动态神经网络集成的驾驶员行为学习算法[J].计算机应用研究,2009,26(11):4088-4090.
[71]王建强,邱红桐,王运霞,陆振益.基于BP神经网络的双车道公路运行车速预测模型[J].公路与汽运.2009, 1(5):56-59.
[72]李宏.求解几类复杂优化问题的进化算法及其应用[D].西安:西安电子科技大学,2009.
[73]肖健梅,李军军,王锡淮.梯度微粒群优化算法及其收敛性分析[J].控制与决策.2009,24(4):561-564.
[74]罗毅,张晓辉.基于遗传算法的机车周转优化模型[J].上海铁道科技,2005,2(3):24-36.
[75]李铭.公交枢纽内始发线路优化配置模型及其模拟退火算法[J].数学的实践与认识,2008,38(7):85-89.
[76]黎明,张国华,王静霞等.公交通行能力约束的智能调度优化模型[J].城市交通,2008,6(5):90-93.
[77]孙中悦,关忠良,郭春芳.基于改进自适应遗传算法的车辆路径问题研究[J].物流技术.2009, 28(11):83-86.
[78]周鹏,史忠科,陈小锋.城市交通联网控制及其多目标优化实现[J].控制理论与应用,2002,19(2):216-219.
[79]孙剑,刘好德,李克平.城市干道交通信号协调控制仿真优化[J].同济大学学报(自然科学版),2009,37(11):1468-1471.
[80]吴恩,杨晓光,吴震等.基于遗传算法的干线协调控制参数共同优化[J].同济大学学报(自然科学版),2008,36(7):922-926.
[81]周辉仁,唐万生,牛犇.基于递阶遗传算法的一类多旅行商问题优化[J].系统工程与电子技术,2009,31(11):2631-2633.
[82]肖华.武汉城市道路交通拥堵问题及对策研究[D].武汉:武汉理工大学,2007.
[83]李铁鑫.高速公路改扩建时机决策研究[D].武汉:武汉理工大学,2007.
[84]刘智勇.智能交通控制理论及其应用[M].北京:科学出版社,2003.
[85]王殿海,李凤,宋现敏.干线协调控制中公共周期优化方法研究[J].交通信息与安全,2009,27(5):10-13.
[86]谢维信,高新波.基于聚类有效性神经网络的模糊规则提取方法[J].深圳大学(理工版),1997,14(1):15-21.
[87]李娜.城市交通信号模糊控制方法研究[D].北京:北京交通大学,2009.
[88]刘征.基于Agent技术的设备智能监测与诊断维护的研究[D].武汉:武汉理工大学,2009.
[89]刘杰.基于强化学习的多机器人围捕策略的研究[D].长春:东北师范大学,2009.
[90]杨晓敏.基于多智能体的城市交通控制系统研究[D].西安:长安大学,2009.
[91]程婉燕.基于多智能体的城市交通信号控制的协调与优化[D].福州:福建农林大学,2009.
[2]杜长海.计算智能及其在城市交通诱导系统中的应用研究[D].重庆:重庆大学图书馆,2009.
[3]王红.城市道路交通信号控制与优化算法的研究[D].济南:山东大学,2005.
[4]区域交通信号控制与交通诱导协同理论与关键技术研究[D].长春:吉林大学,2009.
[5] Pippis C P, Mandani E H. A fuzzy logic controller for a traffic junction[J]. IEEE Trans on SMC,1977,7(10):707-717.
[6] Gazis,D.C. Optimum control of a system of oversalrated interseetions[J]. OP.or.Res., 1964, 12(6): 815-831.
[7] Dunne,M.C,Potts,R.B. Algorithm for traffic control[J].OPer.Res.,1964,12(6):870-881.
[8] Miyata, S., M. Noda and T. Usami. STREAM-Strategic Realtime Control for Megalopolis-traffic[A].In: Proc. Of the 2nd World Congress on Intelligent Transport Systems[C]. London: CrossRef , 1996.
[9] Azura Che Soh,Mohammad Hamiruce Marhaban, Marzuki Khalid,etal. Modelling and optimization of a traffic intersection based on queue theory and markov decision control methods[A]. In: proceedings of the first Asia international conference on modeling &simulation[C]. Phuket: IEEE Computer Society, 2007.
[10] Xiao-Hua Yu.an integrated model for signalized traffic intersection control[A]. In: proceedings of the 2005 IEEE conference on control applications WB3.1[C]. Christchurch: IEEE Computer Society, 2005.
[11] Yun Wei,Qing Shao,Yin Han,etal. Intersection Signal Control Approach based on PSO and Simulation[A]. In: the Second International Conference on Genetic and Evolutionary Computing[C]. San Mateo : IEEE Computer Society,2008.
[12] Yafeng Yin. Robust optimal traffic signal timing[J]. Transportation Research Part B: Methodological, 2008, 42 (10):911-924.
[13] Hongchao Liu,Kevin N.BalK,Wei-Hua Lin. A reverse causal-effect modeling approach for signal control of an oversaturated intersection. Transportation Research Part C : Emerging Technologies[J], 2008,16 (6) 742-754.
[14]陈静,黄崇超.交通信号实时优化模型的算法研究[J].武汉大学学报,2006,39(6):93-95.
[15]肖业伟等.基于蚁群算法的交叉路口多相位信号配时优化[J].计算机工程与应用, 2008, 44(19):241-244.
[16]黄荣等.拥堵状态下信号交叉口通行能力计算方法[J].交通运输系统工程与信息, 2008, 8(3): 59-65.
[17]曲昭伟,刘士序,王殿海等.模拟电路的信号交叉口交通流模型[J].吉林大学学报, 2008, 38(1): 49-52.
[18]王海起,王劲峰.一种基于粒子群的交通信号离线配时优化方法[J].计算机工程与应用,2008,44(11):13-22.
[19]谢赛,魏武,江岸等.一种基于模糊逻辑-遗传算法的城市单交叉口交通信号控制方法[J].交通与计算机,2007,25(134):75-78.
[20] Jee-Hyong Lee, Keon-Myung Lee and Hyung Leekwang. Fuzzy Controller for Intersection Group[A]. In: Proceedings of 1995 IEEE/IAS International Conference on Industrial Automation and Control: Emerging Technologies[C]. Piscataway: IEEE Computer Society, 1995.
[21]陈森发,毛岚.城市交通信号灯模糊线控制及其仿真[J].系统仿真学报,2000,12(6):668-670 .
[22]沈国江,孙优贤.城市交通干线递阶模糊控制及神经网络实现[J].系统工程理论与实践, 2004, 12(4):100-105.
[23]史强,贾磊.基于模糊神经网络的交通干线分层递阶控制[J].控制工程,2006,13(6):543-546
[24]李灵犀,高海军,王飞跃.两相邻路口交通信号的协调控制[J].自动化学报,2003,29(6):948-952.
[25]马伟凤,刘智勇.城市交通干线的Q-学习控制算法[J].五邑大学学报(自然科学版), 2007, 21(3): 16-22.
[26] Haruko Fuji,Hikaru Shimizu. Development of a Signal Control System along the Route 2 in Hiroshima City[A]. In: Proceedings of the SICE Annual Conference[C]. Kagawa: IEEE Computer Society,2008.
[27]王正武,罗大庸,黄中祥等.线性系统协调优化模型及其改进粒子群算法研究[J].系统工程理论与实践,2007,5(10):165-171.
[28]李伟,李彦,何东之.基于线性规划的干线模糊补偿控制[J].公路交通科技,2007,24(8):110-114.
[29] Singh M.G.,DrewA.W.,CoalosJ.F.ComParison of Practical hierarchical control methods For intereonnected dynamical systems[J].Automatiea,1975(11):331-350.
[30] Kashii H.R,Saredi G.N.A learning algolrithm for adaptation to traffic’s dynamic variation[A].In: 6th IFAC sym.On Identificaton and System Parameter Estimation[C]. Washington : IEEE ComputerSociety,1982.
[31] Menga G, Patracco P. Area Traffic Control: decentralized approach[A]. In: Proc.European Conf.on applied Information Technology of IFIP[C]. Netherlands: IEEE Computer Society ,1979.
[32] Mavleod G.J,McCartney. Muti-level control of road traffic networks using microprocessor[J]. IEEE trends on on-line computer control system,1979,13(5):126-131.
[33] Asim ,AI-Khalili Urban. Traffic control: a general approach[J].IEEE Trans. OnSMC, 1985, 15(2): 260-271.
[34]李立源,曹大铸.道路交通流量最优预测与交叉口最优控制[J].控制理论与应用, 1993, 10(1): 67-72.
[35] Hong K.Lo,Elbert Chang,Yiu Cho Cang. Dynamic network traffic control[J]. Transportation Research Part A: Policy and Practice, 2001, 35(8):721-724.
[36] Feng Chen and Hao Pang. Study of multi-agent area coordination control for urban traffic[A]. In: proceeding of the 7thworld congress on intelligent control and automation[C].Chongqing: IEEE Computer Society, 2008.
[37] Fei-Yue Wang.Agent-Based Control for Networked Traffic Management Systems[J]. IEEE Intelligent Systems, 2005, 20(5):92-96.
[38] Li Xiaohong, Ren Shuhua, Shen Lan. A new traffic signal coordinated control method based on mobile technology[A]. In: proceeding of the 27th Chinese control conference[C]. Kunming : IEEE Computer Society ,2008.
[39] Dipti Srinivasan, Chee Choy, Ruey Long Cheu. Neural Networks for Real-Time Traffic Signal Control[J].IEEE transactions on intelligent transportation systems,2006,7(3):261-272.
[40] kazunori Mizuno, ukio Fukui, Seiichi, Nishihara. Urban Traffic Signal Control Based on Distributed Constraint Satisfaction[A].In: proceedings of the 41st Hawaii International conference on system science[C]. Waikoloa : IEEE Computer Society ,2008.
[41] Yi-Sheng Huang,Ta-Hsiang and Jenn-Huei Lin. A timed coloured Petrinet supervisor for urban traffic networks[A]. In:The Proceedings of the Multiconference on computational engineering in system applications[C].Beijing: IEEE Computer Society,2006.
[42] Junhua Wei, Anlin Wang and Nianci Du. Study of self-organizing control of traffic signals in an urban network based on cellular automata[J].IEEE transactions on vehicular technology, 2005, 54(2): 744-748.
[43] FYAN,M DRIDI, MOUDNI. Control of traffic lights intersection: a new branch and bound approach[A]. In: 2008 International Conference on Service Systems and Service Management[C]. Melbourne : IEEE Computer Society,2008.
[44] Suh-Wen Chuiou. An efficient computation algorithm for area traffic control problem with link capacity expansions[J]. Applied mathematics and computation, 2007 ,188(2):1094-1102.
[45] Yuan Wang, Zhaosheng Yang, Qing Guan. Novel traffic control system & its coordination model based on Large-scale systems hierarchical optimization theory[A]. In: Proceedings of the IEEE International conference on automation and logistics[C]. Jinan : IEEE Computer Society ,2007.
[46] Marco Ciccia Davide Giglio, Riccardo Minciardi and Matteo Viarengo. A queue-based macroscopic model for performance evaluation of congested urban traffic networks[A]. In: Proceeding of the 2007 IEEE intelligent transportation systems conference[C]. Seattle: IEEE Computer Society, 2007.
[47] Zhenjiang Li, Feng He, QingmingYao and Fei-Yue Wang. Signal controller design for agent-based traffic control system[A]. In: proceedings of the 2007IEEE international conference on networking, sensing and control[C]. London : IEEE Computer Society ,2007.
[48] Mei-Fang Chen, Gwo-Hshiung Tzeng, and Tzung-I Tang. Fuzzy MCDM Approach for Evaluation of Expatriate Assignments[J]. International Journal of Information Technology & Decision Making, 2005,4(2):277-296.
[49] kelsey. R, K.Bisset, M.Jamshidi. A simulation environment for fuzzy control of traffic systems[A].In: Proceedings of the Twelfth world congress of IFAC[C].Sydney: Pergamon Press,1993.
[50] J.Favilla, A.Machion, F.Gomide. Fuzzy traffic control: adaptive strategies[A].In: Proceedings of the intelligent Vehicles Symposium[C].San Francisco: IEEE Inc,1993.
[51] Nakatsuyama.M, H.Nagahashi, M.Nishizura. Fuzzy logic phase controller for traffic junctions in the one-way arterial road[A]. In: Proceedings of the Ninth Triennial World Congress of IFAC[C].Oxford:Pergamon Press,1985.
[52] Chiu.S, Chand.S. Adaptive traffic signal control using fuzzy logic[A].In: Proceedings of the intelligent Vehicles Symposium[C]. Detroit:1992.
[53] R.Hoyer,U.Jumar. An advanced fuzzy controller for traffic lights[A].In: Proceedings of the 1994 IFAC Artificial intelligence in Real Time Control[C]. New York: Pergamon Press Inc,1994.
[54] Mohamed B.Trabia, Mohamed S.Kaseko, Murali Ande. A two stage fuzzy logic controller fortraffic signals[J]. Transportation Research Part C: Emerging Technologies,1999,7(6):353-367.
[55] Jee-Hyong Lee, H Lee-Kwang. Distributed and cooperative fuzzy controllers for traffic intersections group[J]. IEEE transactions on systems, man, and cybernetics. Part C: Applications and reviews,1999,29(2): 263-271.
[56]徐冬玲,方建安,邵世煌.交通系统的模糊控制及其神经网络实现[J].信息与控制,1992,21(2):74-79.
[57]徐勋倩,黄卫.单路口交通信号多相位实时控制模型及其算法[J].控制理论与应用,2005, 22(3):413-416.
[58]陈洪,陈森发.单路口交通实时模糊控制的一种方法[J].信息与控制,1997,26(3):227-233.
[59]温慧英,尹宏宾,徐建闽.一种信号交叉口模糊交通控制方法[J].华南理工大学学报, 2000,28(6):1-5.
[60]刘智勇.单交叉口的多相位模糊控制[J].信息与控制,1999,28(6):453-458.
[61] Ella Bingham. Reinforcement learning in neuron-fuzzy traffic signal control[J]. European Journal of Operational Research,2001,131(2):232-241.
[62] T.H.Heng, T.K.Ko. Hierarchical fuzzy logic traffic control at a junction using genetic algorithm[A]. In: Proceedings of the 1998 IEEE International Conference on Fuzzy Systems[C]. Anchorage : IEEE Inc ,1998.
[63] Wu Wei, Mingjun Wang. Traffic signal control using fuzzy and neural network[A].IEEE International Conference on Systems, Man, and Cybernetics[C].Istanbul: IEEE Inc,2001.
[64]尹志宇.基于L-M神经网络的道路交通噪声预测研究[J].中国环境检测,2009,25(4):85-87.
[65]潘昱,张晶.基于城市路口相关性的交通流量预测[J].交通与计算机,2005,23(1):31-33.
[66]温惠英,周玮明.基于S型函数预处理的RBF神经网络交通流量预测[J].交通信息与安全.2009,27(4):22-25.
[67]严丽军,项湜伍.基于模糊神经网络的交通灯智能系统[J].上海师范大学学报(自然科学版),2009,38(4):384-387.
[68]唐少先,黄志辉,阳春华.基于模糊神经网络的车辆跟驰决策的研究[J].人工智能,2009,25(2):195-197.
[69]王明亮,郑建立.基于模糊神经网络的智能超车系统安全性预测的研究[J].信息安全,2007,23(3):59-60.
[70]梁军,陈小波,程显毅,等.基于动态神经网络集成的驾驶员行为学习算法[J].计算机应用研究,2009,26(11):4088-4090.
[71]王建强,邱红桐,王运霞,陆振益.基于BP神经网络的双车道公路运行车速预测模型[J].公路与汽运.2009, 1(5):56-59.
[72]李宏.求解几类复杂优化问题的进化算法及其应用[D].西安:西安电子科技大学,2009.
[73]肖健梅,李军军,王锡淮.梯度微粒群优化算法及其收敛性分析[J].控制与决策.2009,24(4):561-564.
[74]罗毅,张晓辉.基于遗传算法的机车周转优化模型[J].上海铁道科技,2005,2(3):24-36.
[75]李铭.公交枢纽内始发线路优化配置模型及其模拟退火算法[J].数学的实践与认识,2008,38(7):85-89.
[76]黎明,张国华,王静霞等.公交通行能力约束的智能调度优化模型[J].城市交通,2008,6(5):90-93.
[77]孙中悦,关忠良,郭春芳.基于改进自适应遗传算法的车辆路径问题研究[J].物流技术.2009, 28(11):83-86.
[78]周鹏,史忠科,陈小锋.城市交通联网控制及其多目标优化实现[J].控制理论与应用,2002,19(2):216-219.
[79]孙剑,刘好德,李克平.城市干道交通信号协调控制仿真优化[J].同济大学学报(自然科学版),2009,37(11):1468-1471.
[80]吴恩,杨晓光,吴震等.基于遗传算法的干线协调控制参数共同优化[J].同济大学学报(自然科学版),2008,36(7):922-926.
[81]周辉仁,唐万生,牛犇.基于递阶遗传算法的一类多旅行商问题优化[J].系统工程与电子技术,2009,31(11):2631-2633.
[82]肖华.武汉城市道路交通拥堵问题及对策研究[D].武汉:武汉理工大学,2007.
[83]李铁鑫.高速公路改扩建时机决策研究[D].武汉:武汉理工大学,2007.
[84]刘智勇.智能交通控制理论及其应用[M].北京:科学出版社,2003.
[85]王殿海,李凤,宋现敏.干线协调控制中公共周期优化方法研究[J].交通信息与安全,2009,27(5):10-13.
[86]谢维信,高新波.基于聚类有效性神经网络的模糊规则提取方法[J].深圳大学(理工版),1997,14(1):15-21.
[87]李娜.城市交通信号模糊控制方法研究[D].北京:北京交通大学,2009.
[88]刘征.基于Agent技术的设备智能监测与诊断维护的研究[D].武汉:武汉理工大学,2009.
[89]刘杰.基于强化学习的多机器人围捕策略的研究[D].长春:东北师范大学,2009.
[90]杨晓敏.基于多智能体的城市交通控制系统研究[D].西安:长安大学,2009.
[91]程婉燕.基于多智能体的城市交通信号控制的协调与优化[D].福州:福建农林大学,2009.