城市交通信号优化控制方法的研究
|
摘要
交通信号控制是管理运输网络的一种基本手段，人们普遍意识到交通信号
控制系统的作用还未得到完全发挥。随着智能运输系统（Intelligent Transportation
System，简记为ITS）的发展，交通信号控制的研究远未完善，交通信号控制
依然是最重要的研究和发展项目之一。到目前为止，已经研究出许多交通信号
控制模型。尽管这些模型差别很大，但主要可分成两大类。一类主要针对交通
流未饱和的情形进行研究；另一类主要是针对拥挤与过饱和交通流条件进行研
究，其中排队一直存在且不能完全清除，排队形成和离散的动力学研究变得极
为重要。本文针对交通信号优化控制问题进行了智能优化的理论分析和应用方
法的研究，得出了一些有益的结论，解决了一些实际问题：
1.本文首先提出了基于智能优化的交通信号控制原理，主要介绍了遗传算
法优化方法和混沌优化方法的基本思想。通过对城市单交叉路口的交通流分析，
建立了单交叉口以车辆排队长为目标函数的四相位交通信号方案实时控制模
型。采用遗传算法优化方法对该模型中相位绿灯持续时间进行优化仿真试验，
通过与传统优化方法的仿真试验进行比较，证明这种遗传算法优化方法的优越
性。遗传算法搜索适应于单交叉路口配时优化，可获得最优性能指标。
2.本文提出了改善遗传算法搜索方法的一种混合搜索算法，并从理论上
证明了这种混合算法的收敛性。这种混合算法把梯度法的区间最优搜索以及遗
传算法的遍历性结合起来，既利用了遗传算法全局优化的特点，也利用了梯度
法的最速下降的特点，从而保证系统既避免了遗传算法要遍历几乎所有的状态、
搜索时间过长的缺点，又避免了梯度法的易于陷入局部最优的缺点，提高了优
化效率。仿真试验表明这种新的混合搜索方法的有效性。
3.本文建立了单交叉路口以车辆平均延误为性能指标的实时交通模型，
提出了基于混沌优化的周期与绿信比综合优化方法。在一定的绿信比下，交叉
口的延误指标随周期变化具有单峰性。对于周期的优化采用了变步长单向搜索
方法；对于绿信比的优化，采用了混沌搜索方法；整个优化过程采用了周期、
绿信比顺序优化的方法。仿真试验表明本文方法优于文献[12]及OSCADY的方
法。此外，还进行了多个时间段的性能指标优化方法的研究。
4.本文针对网络细胞模型建立了基于细胞传播模型（CTM）的交通动力
学模型，推导了交通信号控制的一般公式，提出了基于混沌优化的周期与绿信
比综合优化方法。以具有多个交叉口的主干道为对象，针对轻度、中度、重度
三种不同的交通需求进行仿真试验，仿真结果表明本文方法优于文献[5]的方
2 西北工业大学博士学位论文
一
法。获得了较好的性能指标。
5．本文最后讨论了智能交通信号机的研制，参考目前国内外交通信号机
的功能特点，介绍了所研制的智能交通信号机的结构原理及程序设计实现方法，
并着重讨论了交通信号机的感应控制方式的控制原理、联网方式下的通讯协议
以及联网控制的实现方法。”最后，简耍介绍了新的交通信号机的特点。
Traffic signal is an essential element to manage the transportation network.
Nevertheless, it is widely accepted that the benefits of traffic control signal systems
are not being fully realized. Along with the movement of Intelligent Transportation
System (ITS), traffic signal control remains one of the most heavily funded research
and developmeiii. iL~ins. i ne research on traffic signal control is by no means
complete. A number of models of the traffic signal control have been developed in the
past. Despite substantial differences among them, they can be roughly classified by
two approaches. One is developed mainly for unsaturated traffic flow. The other is
developed mainly for congested or over-saturated traffic conditions where queues
exist in the whole period and can not be cleared. The dynamics of queue formation
and dissipation becomes very important.
In this dissertation, the principle of the traffic signal control based on intelligent
optimization, the basic optimal theories and the methods based on Genetic Algorithm
as well as Chaos theory are proposed. Through the study and the analysis of traffic
streams in an intersection, the real-time control model of four-phase signal plan
according to the objective function of vehicle queue length in an intersection is
established. The simulation tests of phase green duration in the model are conducted
using Genetic Algorithm method. The simulation results show that the optimal
method of Genetic Algorithm is superior to tradition methods, and it is suitable for
determining the green split in a single intersection.
Based on Genetic Algorithm, a hybrid optimal method is provided. It combines
the advantage of global optimization in Genetic Algorithm with the advantage of the
fastest dropping in Gradient method. It can also ensure to avoid much time in Genetic
Algorithm and to escape from local optimization of Gradient method. The simulation
results indicate that this new method increases the search efficiency.
With regard to performance index of the average vehicle delay in an intersection,
the traffic stream model and a new optimal method based on Chaos theory according
to cycle length and green split are developed. Under a given green split, the
performance index of average delay in an intersection varies with the cycle in a
convex curve. During optimizing, the search step is changed according to the cycle
length, an optimal method based on Chaos theory is used according to green split, and
a sequential optimal method is used according to cycle length and green split. The
simulation results show that the method is superior to those in OSCADY and
reference 12. In addition, the optimization of performance index for a series of period
is also conducted.
A traffic stream dynamics based on Cell Transmission Model (CTM) is
established. An optimal method based on Chaos theory according to cycle length and
green split for CTM of a network is developed. The simulation tests are conducted in
three cases of light, moderate and heavy traffic streams with arterial road of several
4
intersections. The simulation results show that this method is superior to the method
of reference 5. The better performance index can be obtained in the new method.
After the function characteristics of domestic and foreign traffic signal control
machines being known, a new intelligent machine of traffic signal control is studied
and manufactured. The constitution of the machine of traffic signal control and its
method of programming are
控制系统的作用还未得到完全发挥。随着智能运输系统（Intelligent Transportation
System，简记为ITS）的发展，交通信号控制的研究远未完善，交通信号控制
依然是最重要的研究和发展项目之一。到目前为止，已经研究出许多交通信号
控制模型。尽管这些模型差别很大，但主要可分成两大类。一类主要针对交通
流未饱和的情形进行研究；另一类主要是针对拥挤与过饱和交通流条件进行研
究，其中排队一直存在且不能完全清除，排队形成和离散的动力学研究变得极
为重要。本文针对交通信号优化控制问题进行了智能优化的理论分析和应用方
法的研究，得出了一些有益的结论，解决了一些实际问题：
1.本文首先提出了基于智能优化的交通信号控制原理，主要介绍了遗传算
法优化方法和混沌优化方法的基本思想。通过对城市单交叉路口的交通流分析，
建立了单交叉口以车辆排队长为目标函数的四相位交通信号方案实时控制模
型。采用遗传算法优化方法对该模型中相位绿灯持续时间进行优化仿真试验，
通过与传统优化方法的仿真试验进行比较，证明这种遗传算法优化方法的优越
性。遗传算法搜索适应于单交叉路口配时优化，可获得最优性能指标。
2.本文提出了改善遗传算法搜索方法的一种混合搜索算法，并从理论上
证明了这种混合算法的收敛性。这种混合算法把梯度法的区间最优搜索以及遗
传算法的遍历性结合起来，既利用了遗传算法全局优化的特点，也利用了梯度
法的最速下降的特点，从而保证系统既避免了遗传算法要遍历几乎所有的状态、
搜索时间过长的缺点，又避免了梯度法的易于陷入局部最优的缺点，提高了优
化效率。仿真试验表明这种新的混合搜索方法的有效性。
3.本文建立了单交叉路口以车辆平均延误为性能指标的实时交通模型，
提出了基于混沌优化的周期与绿信比综合优化方法。在一定的绿信比下，交叉
口的延误指标随周期变化具有单峰性。对于周期的优化采用了变步长单向搜索
方法；对于绿信比的优化，采用了混沌搜索方法；整个优化过程采用了周期、
绿信比顺序优化的方法。仿真试验表明本文方法优于文献[12]及OSCADY的方
法。此外，还进行了多个时间段的性能指标优化方法的研究。
4.本文针对网络细胞模型建立了基于细胞传播模型（CTM）的交通动力
学模型，推导了交通信号控制的一般公式，提出了基于混沌优化的周期与绿信
比综合优化方法。以具有多个交叉口的主干道为对象，针对轻度、中度、重度
三种不同的交通需求进行仿真试验，仿真结果表明本文方法优于文献[5]的方
2 西北工业大学博士学位论文
一
法。获得了较好的性能指标。
5．本文最后讨论了智能交通信号机的研制，参考目前国内外交通信号机
的功能特点，介绍了所研制的智能交通信号机的结构原理及程序设计实现方法，
并着重讨论了交通信号机的感应控制方式的控制原理、联网方式下的通讯协议
以及联网控制的实现方法。”最后，简耍介绍了新的交通信号机的特点。
Traffic signal is an essential element to manage the transportation network.
Nevertheless, it is widely accepted that the benefits of traffic control signal systems
are not being fully realized. Along with the movement of Intelligent Transportation
System (ITS), traffic signal control remains one of the most heavily funded research
and developmeiii. iL~ins. i ne research on traffic signal control is by no means
complete. A number of models of the traffic signal control have been developed in the
past. Despite substantial differences among them, they can be roughly classified by
two approaches. One is developed mainly for unsaturated traffic flow. The other is
developed mainly for congested or over-saturated traffic conditions where queues
exist in the whole period and can not be cleared. The dynamics of queue formation
and dissipation becomes very important.
In this dissertation, the principle of the traffic signal control based on intelligent
optimization, the basic optimal theories and the methods based on Genetic Algorithm
as well as Chaos theory are proposed. Through the study and the analysis of traffic
streams in an intersection, the real-time control model of four-phase signal plan
according to the objective function of vehicle queue length in an intersection is
established. The simulation tests of phase green duration in the model are conducted
using Genetic Algorithm method. The simulation results show that the optimal
method of Genetic Algorithm is superior to tradition methods, and it is suitable for
determining the green split in a single intersection.
Based on Genetic Algorithm, a hybrid optimal method is provided. It combines
the advantage of global optimization in Genetic Algorithm with the advantage of the
fastest dropping in Gradient method. It can also ensure to avoid much time in Genetic
Algorithm and to escape from local optimization of Gradient method. The simulation
results indicate that this new method increases the search efficiency.
With regard to performance index of the average vehicle delay in an intersection,
the traffic stream model and a new optimal method based on Chaos theory according
to cycle length and green split are developed. Under a given green split, the
performance index of average delay in an intersection varies with the cycle in a
convex curve. During optimizing, the search step is changed according to the cycle
length, an optimal method based on Chaos theory is used according to green split, and
a sequential optimal method is used according to cycle length and green split. The
simulation results show that the method is superior to those in OSCADY and
reference 12. In addition, the optimization of performance index for a series of period
is also conducted.
A traffic stream dynamics based on Cell Transmission Model (CTM) is
established. An optimal method based on Chaos theory according to cycle length and
green split for CTM of a network is developed. The simulation tests are conducted in
three cases of light, moderate and heavy traffic streams with arterial road of several
4
intersections. The simulation results show that this method is superior to the method
of reference 5. The better performance index can be obtained in the new method.
After the function characteristics of domestic and foreign traffic signal control
machines being known, a new intelligent machine of traffic signal control is studied
and manufactured. The constitution of the machine of traffic signal control and its
method of programming are
引文
[1]Michael G. H. Bell, Future Direction in Traffic Signal Control, Transpn. Res. -A, Vol.26A, No.4, pp.303-313, 1992.
[2]Dirk Heidemann, Queue Length and Delay Distribution at Traffic Signal, Transpn.Res. -B, Vol.28B, No.5, pp.377-389, 1994.
[3]M. G. H. Bell, et al., Discrete Time-Adaptive Singal Control: the Calculation of Expected Selays and Stop, Transpn. Res. -C, Vol. 1C, No. 1, pp.43-55, 1993.
[4]G. K. S. Mung, et al., Distribution of Length at Fixed Time Traffic Signal,Transpn. Res. -B, Vol.30, No.6, pp.421-439, 1996.
[5]Hong K. Lo, A Novel Traffic:Signal Control Formulation, Transpn. Rese. Part A,33,433-448, 1999.
[6]E. Kwon, et al., Development of an Adaptive Control Strategy in a Live Intersection Laboratory, Transportation Research Record Paper No. 98-0991.
[7]Bin Han, Optimizing Traffic Signal Setting for Periods of Time-Varying Demand,Transpn. Res. -A, Vol.30, No.3, pp.207-230, 1996.
[8]Jean-Louis Gallego, Jean-Loup Farges and Jean-Jacques, Design by Petri Nets of an Intersection Signal Control, Transpn. Res. -C, Vol.4, No.4, pp.231-248, 1996.
[9]Hal Yang and Sam Yagar, Traffic Assignment and Signal Control in Saturated Road Networks, Transpn. Res. -A, Vol.29A, No.2, pp.125-139, 1995.
[10]J. P. Silcock, Design Signal-Controlled Junctions for Group-Based Operation, Transpn. Res. -A, Vol.31, No.2, pp.157-173, 1997.
[11]Chiu Liu, Robert Herman, Denos C. Gazis, A Review of the Yellow Interval Dilemma, Transpn. Res. -A, Vol.30, No.5, pp.333-348, 1996.
[12]Bin Han, A New Comprehensive Sheared Delay Formula for Traffic Signal Optimization, Transpn. Res. -A, Vol.30, No.2, pp. 155-171, 1996.
[13]Fen-Bor Lin, Modeling Average Cycle Lengths and Green Intervals of Semi-Actuated Signal Operations with Exclusive Pedestrain-Actuated Phase, Transpn.Res. -B, Vol.26B, No.3, pp.221-240, 1992.
[14]G. E. Cantarella et al., Capacity Factor or Cycle Time Optimization for Signalized Junction: A Graph Theory Approach, Transpn. Res. -B, Vol.22B, No. 1,pp.1-23, 1988.
[15]David Mahalel and Alfred S. Hakkert, Time-Series Model for Vehicle Speed Transpn. Res. -B, Vol. 19B, No. 3, pp.217-225, 1985.
[16]Julian Benjamin, A Time Series Forecast of Average Daily Traffic Volune, Transpn. Res. -A, Vol.20A, No. 1, pp.51-60, 1986.
[17]Peter Joyce and Sam Yagar, Representing Stochastic Transit Dwell Times in Traffic Signal Optimization, Transpn. Res. -A, Vol.24A, No.2, pp.87-98, 1990.
[18]Benjamin Heydecker, Uncertainty and Variability in Traffic Signal Calculation, Transpn. Res. -B, Vol.21B, No.1, pp.79-85, 1987.
[19]Masaki Koshi, Cycle Time Optimization in Traffic Signal Coordination, Transpn. Res. -A, Vol.23A, No.1, pp.29-34, 1989.
[20]Yoshitsugu Hayashi, Issue in Financing Urban Rail Transit Project and Value Capture, Transpn. Res. -A, Vol.23A, No.1, pp.35-44, 1989.
[21]G. E. Cantarella, et al., Iterative Procedure for Equilibrium Network Traffic Signal Setting, Transpn. Res. -A, Vol.25A, No.5, pp.241-249 1991.
[22]David Leiser and Eliahu Stern, Determination of Subjective Time Estimates in Simulated Urban Drive, Transpn. Res. -A, Vol.22A, No.3, pp. 175-182, 1988.
[23]David A. Hensher, Electronic Toll Collection, Transpn. Res. -A, Vol.25A, No. 1, pp.9-16, 1991.
[24]Maurizio Bielli, Artificial Intelligence Techniques for Urban Traffic Control,Transpn. Res. -A, Vol.25A, No.5, pp.319-325, 1991.
[25]M. A. Tumquist, Research Opportunities in Transportation System Characteristics and Operations, Transpn. Res. -A, Vol.19A, No.5/6, pp.357-366,1985.
[26]Chris Hendrickson, Research in Transportation System Characteristics and Operations, Transpn. Res. -A, Vol. 19A, No.5/6, pp.367-369, 1985.
[27]Nathan H. Gartner, Demand-Responsive Traffic Control Research, Transpn. Res.-A, Vol. 19A, No.5/6, pp.369-373, 1985.
[28]Hani Mahmassani and Panos Michalopoulos, Traffic Science: Perspective on Future Research, Transpn. Res. -A, Vol. 19A, No.5/6, pp.377-380, 1985.
[29]David Mahalel, Yehuda Gur and Yoram Shittan, Manual Versus Automation of Traffic Signal, Transpn. Res. -A, Vol.25A, No.2/3, pp. 121-127, 1991.
[30]R. M. Kimber and P. N. Daly, Time-Dependent Queuing at Road Junction Observation and Prediction, Transpn. Res. -B, Vol.20B, No.3, pp. 187-203, 1986.
[31]M. Papageorgiou, et al., Modeling and Real-Time Control of Traffic Flow on the Southern Part of Boulevard Peripherique in Paris: Part Ⅰ: Modeling, Transpn.Res. -A, Vol.24A, No.5, pp.345-359, 1990.
[32]S. C. Van As, Overflow Delay in Signalized Network, Transpn. Res. -A,Vol.25A, No.1, pp.1-7, 1991.
[33]Merchant D K and Nemhauser G L, A model and algorithm for dynamic traffic assignment problem. Transpn. Sci. 12, 1978.
[34]Ralf Salomon, Evolutionary Algorithms and Gradient Search: Similarities and Differences, Transaction on Evolutionary Computation, Vol.2, No.2, July 1998.
[35]Tang-Hsien Chang, Jen-Ting Lin, Optimal signal timing for an oversaturated intersection, Transpn. Res. Part B, Vol.34, pp.471-491, 2000.
[36]Suvrajeet Sen and K. Larry Head, Controlled Optimization of Phases at an Intersection, Transpn. Sci. Vol.31, No.1, Feb. 1997.
[37]G.K.S. Mung t al., Distribution of the Maximun Number of Opposed Turns in a Single Cycle at Time Traffic Signals, Transpn. Res. -B, Vol.32,No.6, pp.373-386,1998.
[38]S. Lee et al., Fuzzy-logic-based incident detection for signalized diamond interchanges, Transpn. Res. Part C 6, pp.359-377, 1998.
[39]J. C. Spell, et al., Traffic-responsive signal timing for system-wide traffic control, Transpn. Res. -C, Vol.5, No.3/4, pp. 153-163, 1997.
[40]O. M. J. Carsten et al., Intelligent Traffic signals for pedestrians: evaluatio of trial in three countries, Transpn. Res. Part C 6, pp.213-229, 1998.
[41]B. Wolshon, et al., Analysis of intersection delay under real-time adaptive signal control, Transpn. Res. Part C 7, pp.53-72, 1999.
[42]N. Vandaele, et al., A queueing based traffic flow model, Transpn. Res. Part D 5,pp.121-135, 2000.
[43]B. F. Simmonite, et al., Modeling Flares at traffic signal-controlled junctions,Traffic engineering and control, pp. 196-199, Apr. 1997.
[44]J. R. Head, et al., The use of microwave vehicle detectors with traffic signals,Traffic engineering and control, pp. 13-15, Jan. 1997.
[45]J. R. Peirce, et al., Repeated-stage signal control using MOVA, Traffic engineering and control, pp. 6-9, Jan. 1989.
[46]R. L. Pretty, A review of intersection traffic signal timing programs, Traffic engineering and control, pp. 429-430, Sep. 1993.
[47]E. A. A. Shawaly, et al. A comparison of observed, estimated and simulated queue lengths and delay at oversaturated signalized junctions, Traffic engineering and control, pp. 637-642, Dec. 1988.
[48]R. J. Salter, et al., Optimization of signal cycle time by a computer simulation,Traffic engineering and control, pp. 290-293, May. 1997.
[49]杨佩昆、黄文忠、车丕明，城市道路车队离散过程中的交通流模型，同济大学学报，Vol．22，No．3，Sep．1994。
[50]杨叔子等著，时间序列分析的工程应用(上、下)，武汉：华中理工大学出版社，1991。
[51]施仁杰、卢科学编著，时间序列分析引论，西安：西安电子科技大学出版社，1998。
[52][美]D．格罗彼著，梁泽环译，时间序列分析辨识与适应性滤波，北京：科学出版社，1987。
[53]张有为编著，预测的数学方法，北京：国防工业出版社，1991。
[54]蔡宣三编著，最优化与最优控制，北京：清华大学出版社，1982。
[55]李维铮等编著，运筹学，北京：清华大学出版社，1982。
[56]严颖等编著，运筹学随机模型，北京：中国人民大学出版社，1995。
[57]赵达纲等著，应用随机过程，北京：机械工业出版社，1993。
[58]俞钟祺等编著，随机过程理论及其应用，天津：天津科技出版社，1996。
[59]冯瓒刚、郭治编，随机控制，北京：国防工业出版社，1988。
[60]顾昌耀等编著，系统工程基础，北京：国防工业出版社，1990。
[61]杨佩昆、张树升，交通管理与控制，北京：人民交通出版社，1997。
[62]荆便顺，道路交通控制工程，北京：人民交通出版社，1995。
[63]陈国良等，《遗传算法及其应用》，人民邮电出版社，北京，1996。
[64]刘勇等，《数值计算优化方法——遗传算法》，科学出版社，北京，1998。
[65]陈洪等，单路口交通实时模糊控制的一种方法，信息与控制，Vol．26，NO．3，June 1997。
[66]何晓红等，交叉口交通灯的计算机控制，交通与计算机，No．18，1992。
[67]杨佩昆等，城市道路车队离散过程中的交通流模型，同济大学学报，Vol．22，No．3，Sep．1994。
[68]刘灿齐等，信号灯交叉口车队散布模型与信号灯协调控制，同济大学学报，Vol．24，No．6，Dec．1996。
[69]王亦兵等，城市高速公路交通控制综述，自动化学报，Vol．24，No．4，Jul．1998。
[70]张锦等，中国城市道路交通控制系统发展研究，西南交通大学学报，Vol．32，No．1，Feb．1997。
[71]王强、邵惠鹤，“遗传算法在甲醛生产过程优化中的应用”，控制理论与应用，Vol．13，No．4，Aug．1996。
[72]恽为民、席裕庚，遗传算法的全局收敛性和计算效率分析，控制理论与应用，Vol．13，No．4，Aug．1996。
[73]席裕庚等，遗传算法综述，控制理论与应用，Vol．13，No．6，Dec．1996。
[74]丁承民等，遗传算法纵横谈，信息与控制，Vol．26，No．1，Feb．1997。
[75]黄炯等，基于遗传算法的系统在线辨识，信息与控制，Vol．25，No．3，June 1996。
[76]章珂、刘贵忠，交叉位置非等概率选取的遗传算法，信息与控制，Vol．26，No．1，Dec．1997。
[77]李大卫、王梦光，一种改进的混合遗传算法，信息与控制，Vol．26，No．6，Dec．1997。
[78]周旭东、王国栋，小脑模型控制系统的遗传算法最优设计，信息与控制，Vol．26，No．6，Dec．1997。
[79]张彤等，变尺度混沌优化方法及其应用，控制与决策，Vol．14，No．3，May1999。
[80]钱富才等，利用混沌搜索全局最优的一种混合算法，信息与控制 Vol．27，No．3，June 1998。
[81]袁文平等，平面交叉交通流动态特征的神经网络模型，信息与控制，Vol．27，No．6，Dec．1998。
[82]张晓绩等，遗传算法种群多样性的分析研究，控制理论与应用，Vol．15，No．1，Feb．1998。
[83]李茂军等，单亲遗传算法及其全局性收敛分析，自动化学报，Vol．25，No．1，Jan．1999。
[84]黄晓峰等，实数编码遗传算法中交叉操作的效率分析，控制与决策，Vol．13，Suppl．，July 1998。
[85]孙艳丰等，自然数编码遗传算法的最优群体规模，信息与控制，Vol．25，No．5，Oct．1996。
[86]黄小原等，遗传算法在列车占线问题中的应用，信息与控制，Vol．25，No．1，Feb．1996。
[87]恽为民等，遗传算法的运行机理分析，控制理论与应用，Vol．13，No．3，Jun．1996。
[88]刘武元，城市公共交通管理，2010年陕西交通发展战略研讨会论文集。
[89]刘武元，发展城市公共交通是城市交通战略选择，2010年陕西交通发展战略研讨会论文集。
[90]张学艺，西安市交通运输现状、问题与对策，2010年陕西交通发展战略研讨会论文集。
[91]李立源，曹大铸，道路交通流量最优预测与交叉口最优控制，控制理论与应用，Vol．10，No．1，Feb．1993。
[92]中华人民共和国公共安全行业标准(GA／T47—93)——交通信号机技术要求与测试方法。
[93]王贵珠等，一种新型的自学习职能式城市交通实时控制系统，自动化学报，Vol．21，No．4，July 1995。
[94]韩锡令，MCS—51单片机控制多时段定时交通信号，西安公路学院学报，Vol．11，No．4，Dec．1991。
[95]韩直，交叉口的冲突与交叉口的信号化，西安公路学院学报，Vol．10，No．2，June 1990。
[96]刘智勇等，城市交通干线递阶模糊控制，公路交通科技，Vol．11，No．3，1997。
[97]申力茜，城市交通网络优化及实现方法研究，硕士学位论文，1999。
[98]王青，高速公路交通流密度控制方法，硕士学位论文，1999。
[99]姚祖康，道路与交通工程系统分析，人民交通出版社，1996。
[100]杨兆升，交通运输系统规划，人民交通出版社，1998。
[2]Dirk Heidemann, Queue Length and Delay Distribution at Traffic Signal, Transpn.Res. -B, Vol.28B, No.5, pp.377-389, 1994.
[3]M. G. H. Bell, et al., Discrete Time-Adaptive Singal Control: the Calculation of Expected Selays and Stop, Transpn. Res. -C, Vol. 1C, No. 1, pp.43-55, 1993.
[4]G. K. S. Mung, et al., Distribution of Length at Fixed Time Traffic Signal,Transpn. Res. -B, Vol.30, No.6, pp.421-439, 1996.
[5]Hong K. Lo, A Novel Traffic:Signal Control Formulation, Transpn. Rese. Part A,33,433-448, 1999.
[6]E. Kwon, et al., Development of an Adaptive Control Strategy in a Live Intersection Laboratory, Transportation Research Record Paper No. 98-0991.
[7]Bin Han, Optimizing Traffic Signal Setting for Periods of Time-Varying Demand,Transpn. Res. -A, Vol.30, No.3, pp.207-230, 1996.
[8]Jean-Louis Gallego, Jean-Loup Farges and Jean-Jacques, Design by Petri Nets of an Intersection Signal Control, Transpn. Res. -C, Vol.4, No.4, pp.231-248, 1996.
[9]Hal Yang and Sam Yagar, Traffic Assignment and Signal Control in Saturated Road Networks, Transpn. Res. -A, Vol.29A, No.2, pp.125-139, 1995.
[10]J. P. Silcock, Design Signal-Controlled Junctions for Group-Based Operation, Transpn. Res. -A, Vol.31, No.2, pp.157-173, 1997.
[11]Chiu Liu, Robert Herman, Denos C. Gazis, A Review of the Yellow Interval Dilemma, Transpn. Res. -A, Vol.30, No.5, pp.333-348, 1996.
[12]Bin Han, A New Comprehensive Sheared Delay Formula for Traffic Signal Optimization, Transpn. Res. -A, Vol.30, No.2, pp. 155-171, 1996.
[13]Fen-Bor Lin, Modeling Average Cycle Lengths and Green Intervals of Semi-Actuated Signal Operations with Exclusive Pedestrain-Actuated Phase, Transpn.Res. -B, Vol.26B, No.3, pp.221-240, 1992.
[14]G. E. Cantarella et al., Capacity Factor or Cycle Time Optimization for Signalized Junction: A Graph Theory Approach, Transpn. Res. -B, Vol.22B, No. 1,pp.1-23, 1988.
[15]David Mahalel and Alfred S. Hakkert, Time-Series Model for Vehicle Speed Transpn. Res. -B, Vol. 19B, No. 3, pp.217-225, 1985.
[16]Julian Benjamin, A Time Series Forecast of Average Daily Traffic Volune, Transpn. Res. -A, Vol.20A, No. 1, pp.51-60, 1986.
[17]Peter Joyce and Sam Yagar, Representing Stochastic Transit Dwell Times in Traffic Signal Optimization, Transpn. Res. -A, Vol.24A, No.2, pp.87-98, 1990.
[18]Benjamin Heydecker, Uncertainty and Variability in Traffic Signal Calculation, Transpn. Res. -B, Vol.21B, No.1, pp.79-85, 1987.
[19]Masaki Koshi, Cycle Time Optimization in Traffic Signal Coordination, Transpn. Res. -A, Vol.23A, No.1, pp.29-34, 1989.
[20]Yoshitsugu Hayashi, Issue in Financing Urban Rail Transit Project and Value Capture, Transpn. Res. -A, Vol.23A, No.1, pp.35-44, 1989.
[21]G. E. Cantarella, et al., Iterative Procedure for Equilibrium Network Traffic Signal Setting, Transpn. Res. -A, Vol.25A, No.5, pp.241-249 1991.
[22]David Leiser and Eliahu Stern, Determination of Subjective Time Estimates in Simulated Urban Drive, Transpn. Res. -A, Vol.22A, No.3, pp. 175-182, 1988.
[23]David A. Hensher, Electronic Toll Collection, Transpn. Res. -A, Vol.25A, No. 1, pp.9-16, 1991.
[24]Maurizio Bielli, Artificial Intelligence Techniques for Urban Traffic Control,Transpn. Res. -A, Vol.25A, No.5, pp.319-325, 1991.
[25]M. A. Tumquist, Research Opportunities in Transportation System Characteristics and Operations, Transpn. Res. -A, Vol.19A, No.5/6, pp.357-366,1985.
[26]Chris Hendrickson, Research in Transportation System Characteristics and Operations, Transpn. Res. -A, Vol. 19A, No.5/6, pp.367-369, 1985.
[27]Nathan H. Gartner, Demand-Responsive Traffic Control Research, Transpn. Res.-A, Vol. 19A, No.5/6, pp.369-373, 1985.
[28]Hani Mahmassani and Panos Michalopoulos, Traffic Science: Perspective on Future Research, Transpn. Res. -A, Vol. 19A, No.5/6, pp.377-380, 1985.
[29]David Mahalel, Yehuda Gur and Yoram Shittan, Manual Versus Automation of Traffic Signal, Transpn. Res. -A, Vol.25A, No.2/3, pp. 121-127, 1991.
[30]R. M. Kimber and P. N. Daly, Time-Dependent Queuing at Road Junction Observation and Prediction, Transpn. Res. -B, Vol.20B, No.3, pp. 187-203, 1986.
[31]M. Papageorgiou, et al., Modeling and Real-Time Control of Traffic Flow on the Southern Part of Boulevard Peripherique in Paris: Part Ⅰ: Modeling, Transpn.Res. -A, Vol.24A, No.5, pp.345-359, 1990.
[32]S. C. Van As, Overflow Delay in Signalized Network, Transpn. Res. -A,Vol.25A, No.1, pp.1-7, 1991.
[33]Merchant D K and Nemhauser G L, A model and algorithm for dynamic traffic assignment problem. Transpn. Sci. 12, 1978.
[34]Ralf Salomon, Evolutionary Algorithms and Gradient Search: Similarities and Differences, Transaction on Evolutionary Computation, Vol.2, No.2, July 1998.
[35]Tang-Hsien Chang, Jen-Ting Lin, Optimal signal timing for an oversaturated intersection, Transpn. Res. Part B, Vol.34, pp.471-491, 2000.
[36]Suvrajeet Sen and K. Larry Head, Controlled Optimization of Phases at an Intersection, Transpn. Sci. Vol.31, No.1, Feb. 1997.
[37]G.K.S. Mung t al., Distribution of the Maximun Number of Opposed Turns in a Single Cycle at Time Traffic Signals, Transpn. Res. -B, Vol.32,No.6, pp.373-386,1998.
[38]S. Lee et al., Fuzzy-logic-based incident detection for signalized diamond interchanges, Transpn. Res. Part C 6, pp.359-377, 1998.
[39]J. C. Spell, et al., Traffic-responsive signal timing for system-wide traffic control, Transpn. Res. -C, Vol.5, No.3/4, pp. 153-163, 1997.
[40]O. M. J. Carsten et al., Intelligent Traffic signals for pedestrians: evaluatio of trial in three countries, Transpn. Res. Part C 6, pp.213-229, 1998.
[41]B. Wolshon, et al., Analysis of intersection delay under real-time adaptive signal control, Transpn. Res. Part C 7, pp.53-72, 1999.
[42]N. Vandaele, et al., A queueing based traffic flow model, Transpn. Res. Part D 5,pp.121-135, 2000.
[43]B. F. Simmonite, et al., Modeling Flares at traffic signal-controlled junctions,Traffic engineering and control, pp. 196-199, Apr. 1997.
[44]J. R. Head, et al., The use of microwave vehicle detectors with traffic signals,Traffic engineering and control, pp. 13-15, Jan. 1997.
[45]J. R. Peirce, et al., Repeated-stage signal control using MOVA, Traffic engineering and control, pp. 6-9, Jan. 1989.
[46]R. L. Pretty, A review of intersection traffic signal timing programs, Traffic engineering and control, pp. 429-430, Sep. 1993.
[47]E. A. A. Shawaly, et al. A comparison of observed, estimated and simulated queue lengths and delay at oversaturated signalized junctions, Traffic engineering and control, pp. 637-642, Dec. 1988.
[48]R. J. Salter, et al., Optimization of signal cycle time by a computer simulation,Traffic engineering and control, pp. 290-293, May. 1997.
[49]杨佩昆、黄文忠、车丕明，城市道路车队离散过程中的交通流模型，同济大学学报，Vol．22，No．3，Sep．1994。
[50]杨叔子等著，时间序列分析的工程应用(上、下)，武汉：华中理工大学出版社，1991。
[51]施仁杰、卢科学编著，时间序列分析引论，西安：西安电子科技大学出版社，1998。
[52][美]D．格罗彼著，梁泽环译，时间序列分析辨识与适应性滤波，北京：科学出版社，1987。
[53]张有为编著，预测的数学方法，北京：国防工业出版社，1991。
[54]蔡宣三编著，最优化与最优控制，北京：清华大学出版社，1982。
[55]李维铮等编著，运筹学，北京：清华大学出版社，1982。
[56]严颖等编著，运筹学随机模型，北京：中国人民大学出版社，1995。
[57]赵达纲等著，应用随机过程，北京：机械工业出版社，1993。
[58]俞钟祺等编著，随机过程理论及其应用，天津：天津科技出版社，1996。
[59]冯瓒刚、郭治编，随机控制，北京：国防工业出版社，1988。
[60]顾昌耀等编著，系统工程基础，北京：国防工业出版社，1990。
[61]杨佩昆、张树升，交通管理与控制，北京：人民交通出版社，1997。
[62]荆便顺，道路交通控制工程，北京：人民交通出版社，1995。
[63]陈国良等，《遗传算法及其应用》，人民邮电出版社，北京，1996。
[64]刘勇等，《数值计算优化方法——遗传算法》，科学出版社，北京，1998。
[65]陈洪等，单路口交通实时模糊控制的一种方法，信息与控制，Vol．26，NO．3，June 1997。
[66]何晓红等，交叉口交通灯的计算机控制，交通与计算机，No．18，1992。
[67]杨佩昆等，城市道路车队离散过程中的交通流模型，同济大学学报，Vol．22，No．3，Sep．1994。
[68]刘灿齐等，信号灯交叉口车队散布模型与信号灯协调控制，同济大学学报，Vol．24，No．6，Dec．1996。
[69]王亦兵等，城市高速公路交通控制综述，自动化学报，Vol．24，No．4，Jul．1998。
[70]张锦等，中国城市道路交通控制系统发展研究，西南交通大学学报，Vol．32，No．1，Feb．1997。
[71]王强、邵惠鹤，“遗传算法在甲醛生产过程优化中的应用”，控制理论与应用，Vol．13，No．4，Aug．1996。
[72]恽为民、席裕庚，遗传算法的全局收敛性和计算效率分析，控制理论与应用，Vol．13，No．4，Aug．1996。
[73]席裕庚等，遗传算法综述，控制理论与应用，Vol．13，No．6，Dec．1996。
[74]丁承民等，遗传算法纵横谈，信息与控制，Vol．26，No．1，Feb．1997。
[75]黄炯等，基于遗传算法的系统在线辨识，信息与控制，Vol．25，No．3，June 1996。
[76]章珂、刘贵忠，交叉位置非等概率选取的遗传算法，信息与控制，Vol．26，No．1，Dec．1997。
[77]李大卫、王梦光，一种改进的混合遗传算法，信息与控制，Vol．26，No．6，Dec．1997。
[78]周旭东、王国栋，小脑模型控制系统的遗传算法最优设计，信息与控制，Vol．26，No．6，Dec．1997。
[79]张彤等，变尺度混沌优化方法及其应用，控制与决策，Vol．14，No．3，May1999。
[80]钱富才等，利用混沌搜索全局最优的一种混合算法，信息与控制 Vol．27，No．3，June 1998。
[81]袁文平等，平面交叉交通流动态特征的神经网络模型，信息与控制，Vol．27，No．6，Dec．1998。
[82]张晓绩等，遗传算法种群多样性的分析研究，控制理论与应用，Vol．15，No．1，Feb．1998。
[83]李茂军等，单亲遗传算法及其全局性收敛分析，自动化学报，Vol．25，No．1，Jan．1999。
[84]黄晓峰等，实数编码遗传算法中交叉操作的效率分析，控制与决策，Vol．13，Suppl．，July 1998。
[85]孙艳丰等，自然数编码遗传算法的最优群体规模，信息与控制，Vol．25，No．5，Oct．1996。
[86]黄小原等，遗传算法在列车占线问题中的应用，信息与控制，Vol．25，No．1，Feb．1996。
[87]恽为民等，遗传算法的运行机理分析，控制理论与应用，Vol．13，No．3，Jun．1996。
[88]刘武元，城市公共交通管理，2010年陕西交通发展战略研讨会论文集。
[89]刘武元，发展城市公共交通是城市交通战略选择，2010年陕西交通发展战略研讨会论文集。
[90]张学艺，西安市交通运输现状、问题与对策，2010年陕西交通发展战略研讨会论文集。
[91]李立源，曹大铸，道路交通流量最优预测与交叉口最优控制，控制理论与应用，Vol．10，No．1，Feb．1993。
[92]中华人民共和国公共安全行业标准(GA／T47—93)——交通信号机技术要求与测试方法。
[93]王贵珠等，一种新型的自学习职能式城市交通实时控制系统，自动化学报，Vol．21，No．4，July 1995。
[94]韩锡令，MCS—51单片机控制多时段定时交通信号，西安公路学院学报，Vol．11，No．4，Dec．1991。
[95]韩直，交叉口的冲突与交叉口的信号化，西安公路学院学报，Vol．10，No．2，June 1990。
[96]刘智勇等，城市交通干线递阶模糊控制，公路交通科技，Vol．11，No．3，1997。
[97]申力茜，城市交通网络优化及实现方法研究，硕士学位论文，1999。
[98]王青，高速公路交通流密度控制方法，硕士学位论文，1999。
[99]姚祖康，道路与交通工程系统分析，人民交通出版社，1996。
[100]杨兆升，交通运输系统规划，人民交通出版社，1998。