基于AGENT的快速公交系统仿真研究
|
摘要
基于Agent的建模与仿真方法(Agent-Based Modeling and Simulation,ABMS)是一种新型的建模与仿真方法,在过去十多年里获得越来越多的关注。一些学者主张ABMS是归纳法和演绎法之外的第三种研究方法。这种类型仿真的特点是没有或者只有很少中间核心的管理与指导,只通过许许多多agent之间的交互影响而存在。ABMS基于Agent的思想和智能模拟复杂系统,通过描述agent之间的交互活动产生复杂系统总体的运行效果。所以,基于agent模型涌现出的特性不是沿着“自顶向下”的方向展开,而是一个“自底向上”的过程。
本文基于agent理论和ABMS方法,构建了快速公交系统仿真模型。将乘客、公交车、信号灯抽象为不同的agent,并引入车辆调度agent和站台管理agent,通过乘客agent、车辆调度agent、站台管理agent、公交车agent和信号灯agent之间的交互仿真快速公交系统的运行。其中,站台管理agent是连接乘客agent和公交车agent的纽带。每个站台对应一个站台管理agent,每一个站台管理agent负责管理一个乘客agent队列。车辆调度agent负责整个快速公交系统车辆的产生与调度,并接受公交车agent和站台管理agent发送的消息。信号灯agent根据初始设定的红绿灯交替变换的周期发生状态更替。
公交公司根据乘客流量的平峰期和高峰期,来制定不同时间段的发车时刻表。一般做法为发车时间间隔为一固定值,平峰期时该间隔较长,高峰期时较短。此种方案简单,但对诸如个别站点出现乘客“涌现”等问题不易解决。为了降低乘客候车时间,在兼顾公交公司利益的前提下,提出了一种基于动态调整的车辆调度算法。本算法核心思想是：在通常情况下,车辆调度agent根据某方向乘客候车总人数设定平峰与高峰两个发车时间间隔。如果当前个别站台出现某方向乘客“涌现”现象,根据预计得出若现在发车直达该站台的时间,再计算得到该时间范围内已经发出尚未到达该站台的公交车数目,进而求得到达该站台时的预计载客量,再由单车最大载客量计算出所需的车辆数目,然后根据当前库存车辆数目和最近即将到站的公交车时间,做出分析判断,计算得出实际可发车数目,这些车辆直接发往出现乘客涌现的站台,之前所有站台均不停车,且行驶速度高于常规速度,以超车的方式直达目的站台,解决因“涌现”现象导致该站台乘客等待时间过久的问题。
本文采用net logo平台实现了快速公交系统模型,并进行了系统运行仿真实验。实验结果和分析表明,该模型既能够较为逼真地模拟快速公交系统运行,又对缩短乘客等候时间、充分合理利用公交车资源有一定的借鉴作用。需要指出的是：模型假定乘客到站率和下车站号随机产生,这与现实有一定差异。另外,现实中存在多条公交线路共用某段专用车道的情形,因此多条公交线路重叠车道下的仿真与优化是本文进一步研究的课题。
Agent based modeling and simulation (ABMS) is a new modeling approach that has gained increasing attention over the past 10 years. Some contend that ABMS "is a third way of doing science" and could augment traditional deductive and inductive reasoning as discovery methods. This type of simulation is characterized by the existence of many agents who interact with each other with little or no central direction. Based on the mentality of Agent, ABMS simulates the complex systems, and receives the action of the complex systems by describing the interaction among the agents.The emergent properties of an agent-based model are then the result of "bottom-up" processes, rather than "top-down" direction.
Based on agent a simulation model of bus rapid transit system was developed. The passengers, buses and signal lights were abstracted as different agents in the model, and vehicle scheduling agent and station management agent were also introduced. The situation of bus rapid transit system was simulated through the interaction among agents. The station management agent was the ligament between the bus agent and the passenger agent. Each station corresponds to a station management agent which is responsible for managing a queue of passenger agents. Vehicle scheduling agent is responsible for the production and scheduling of buses and accepts the messages from bus agents and station management agents, according to the initial set signal light agents alternate the state.
The public traffic company develops different time-schedules under the peak and normal of passenger flow. Such a scheme is simple, but it is difficult to resolve when it appears that passengers "merge" in a few stations. In order to reduce passenger waiting time and benefit the public traffic company, a vehicle scheduling algorithm based on dynamic adjustment is proposed. The mean idea of the algorithm is that if the phenomenon of passengers "emerging" in one station appears, a run is in the following:first, the time of direct access to the station from the originating station is forecasted; second, the number of the buses which have not arrived at the station is calculated; third, the maximum capacity for that buses is gained; forth, the number of needing buses is actually calculated; last, the buses move to the station directly with faster than normal.
The model based on the Netlogo platform and simulated the Jinan BRT 1. The experiment and analysis indicate the model not only can simulate the situation of Jinan BRT 1, but also can decrease the waiting time of passengers. But the model assumes that the arrival rate of passengers who arrivered at the station and the number of geting-off station are both randomly generated, which have some differences with the reality. In addition, there are multiple bus lines shared the case of certain lanes in reality, so the Simulation and optimization with many bus lines overlapped is further study of this subject.
本文基于agent理论和ABMS方法,构建了快速公交系统仿真模型。将乘客、公交车、信号灯抽象为不同的agent,并引入车辆调度agent和站台管理agent,通过乘客agent、车辆调度agent、站台管理agent、公交车agent和信号灯agent之间的交互仿真快速公交系统的运行。其中,站台管理agent是连接乘客agent和公交车agent的纽带。每个站台对应一个站台管理agent,每一个站台管理agent负责管理一个乘客agent队列。车辆调度agent负责整个快速公交系统车辆的产生与调度,并接受公交车agent和站台管理agent发送的消息。信号灯agent根据初始设定的红绿灯交替变换的周期发生状态更替。
公交公司根据乘客流量的平峰期和高峰期,来制定不同时间段的发车时刻表。一般做法为发车时间间隔为一固定值,平峰期时该间隔较长,高峰期时较短。此种方案简单,但对诸如个别站点出现乘客“涌现”等问题不易解决。为了降低乘客候车时间,在兼顾公交公司利益的前提下,提出了一种基于动态调整的车辆调度算法。本算法核心思想是：在通常情况下,车辆调度agent根据某方向乘客候车总人数设定平峰与高峰两个发车时间间隔。如果当前个别站台出现某方向乘客“涌现”现象,根据预计得出若现在发车直达该站台的时间,再计算得到该时间范围内已经发出尚未到达该站台的公交车数目,进而求得到达该站台时的预计载客量,再由单车最大载客量计算出所需的车辆数目,然后根据当前库存车辆数目和最近即将到站的公交车时间,做出分析判断,计算得出实际可发车数目,这些车辆直接发往出现乘客涌现的站台,之前所有站台均不停车,且行驶速度高于常规速度,以超车的方式直达目的站台,解决因“涌现”现象导致该站台乘客等待时间过久的问题。
本文采用net logo平台实现了快速公交系统模型,并进行了系统运行仿真实验。实验结果和分析表明,该模型既能够较为逼真地模拟快速公交系统运行,又对缩短乘客等候时间、充分合理利用公交车资源有一定的借鉴作用。需要指出的是：模型假定乘客到站率和下车站号随机产生,这与现实有一定差异。另外,现实中存在多条公交线路共用某段专用车道的情形,因此多条公交线路重叠车道下的仿真与优化是本文进一步研究的课题。
Agent based modeling and simulation (ABMS) is a new modeling approach that has gained increasing attention over the past 10 years. Some contend that ABMS "is a third way of doing science" and could augment traditional deductive and inductive reasoning as discovery methods. This type of simulation is characterized by the existence of many agents who interact with each other with little or no central direction. Based on the mentality of Agent, ABMS simulates the complex systems, and receives the action of the complex systems by describing the interaction among the agents.The emergent properties of an agent-based model are then the result of "bottom-up" processes, rather than "top-down" direction.
Based on agent a simulation model of bus rapid transit system was developed. The passengers, buses and signal lights were abstracted as different agents in the model, and vehicle scheduling agent and station management agent were also introduced. The situation of bus rapid transit system was simulated through the interaction among agents. The station management agent was the ligament between the bus agent and the passenger agent. Each station corresponds to a station management agent which is responsible for managing a queue of passenger agents. Vehicle scheduling agent is responsible for the production and scheduling of buses and accepts the messages from bus agents and station management agents, according to the initial set signal light agents alternate the state.
The public traffic company develops different time-schedules under the peak and normal of passenger flow. Such a scheme is simple, but it is difficult to resolve when it appears that passengers "merge" in a few stations. In order to reduce passenger waiting time and benefit the public traffic company, a vehicle scheduling algorithm based on dynamic adjustment is proposed. The mean idea of the algorithm is that if the phenomenon of passengers "emerging" in one station appears, a run is in the following:first, the time of direct access to the station from the originating station is forecasted; second, the number of the buses which have not arrived at the station is calculated; third, the maximum capacity for that buses is gained; forth, the number of needing buses is actually calculated; last, the buses move to the station directly with faster than normal.
The model based on the Netlogo platform and simulated the Jinan BRT 1. The experiment and analysis indicate the model not only can simulate the situation of Jinan BRT 1, but also can decrease the waiting time of passengers. But the model assumes that the arrival rate of passengers who arrivered at the station and the number of geting-off station are both randomly generated, which have some differences with the reality. In addition, there are multiple bus lines shared the case of certain lanes in reality, so the Simulation and optimization with many bus lines overlapped is further study of this subject.
引文
[1]Macal. Charles M and North. Michael J.Agent-based modeling and simulation:Proceedings-Winter Simulation Conference, p 86-98,2009, Proceedings of the 2009 Winter Simulation Conference, WSC 2009
[2]Herbert S.L.Scoott R.,Eric B.TCRP report90:Bus Rapid Transit[R].Transportation Research Board.2003.3-1.3.1
[3]赵杰,胡子祥,刘丽亚.国外发展快速公交的经验及对我国城市交通发展的启示[J].城市交通Vol2.No.3 Aug.2004:56-59
[4]王少飞,关可,肖鹏等.我国快速公交系统BRT)发展综述[J]中国智能交通2008.1 70～74
[5]盛昭翰,张军,杜建国等著.社会科学计算实验理论与应用[C]上海三联书店2009
[6]廖守亿,戴金海.复杂系统基于Agent的建模与仿真设计模式及软件框架[J].计算机仿真2005,22(5)：254～258.
[7]Macal, Charles M. North, Michael J.Tutorial on agent-based modeling and simulation:Proceedings of Winter Simulation Conference, v 2005, p2-15
[8]李成杰.基于Agent的排队系统仿真研究.工学硕士学位论文,山东大学,2009.
[9]霍兰.隐秩序-适应性造就复杂性.周晓牧等译.上海科技出版社,2000.
[10]卡斯蒂著.王千祥等译.虚实世界[M].上海：上海科技教育出版社,1998.
[11]Schreiber D. The Emergence of Parties:An Agent-Based Simulation. http://www.bol.ucla.edu/-dschreib/EmergingParties/Emergence Parties6-24-01.pdf
[12]Helbing D. Agent-Based Simulation of Traffic Jam, Crowds, and Supply Networks. In Proceeding of the IMA'Hot Topics' Workshop, EMA, Minneapolis, MN.2003.
[13]Barret C. Simulation Scientist Relates to Data/Information Fusion and C2 Systems, Briefing Slides, Los Alamos(1997).
[14]Yang,L.Z,J.Li,Liu,S.B. Simulation of pedestrian counter-flow with right-moving preference.Physica a-Statistical Mechanics and Its Applications,2008,387(13):3281-3289
[15]Epstein J M, Axtell R. Growing artificial societies, social science from the bottom up[M]. Washington,D.C.Brookings Institution Press;Cambridge,Mass.MIT Press,1996.
[16]http://www.simworld.co.uk/
[17]Srbljinovic A, Penzar D, Rodik P, Kardov K. Agent-Based Modeling of Ethnic Mobilization:The Former ugoslaviaCase.1st LA Conference on Computational Social Science and Social Complexity:AB Modeling in Social Sciences,2002.
[18]Derek WB, Oliveira FS. Agent-based Simulation:An Application to the New Electricity Trading Arrangements of England and Wales. IEEE-TEC, special issue:Agent Based Computational Economics,2001.
[19]廖守亿.复杂系统基于Agent的建模与仿真方法研究及应用.工学博士论文,国防科学技术大学,2005.
[20]张江,李学伟.人工社会——基于Agent的社会学仿真[J].系统工程,2005,23(1)：13-20.
[21]Deguchi H,Deguchi H. Economics as an agent-based complex system[M]. Springer-Verlag Press,2004.
[22]Basu N,Pryor J,Quint T,Arnold T. Aspen:a microsimulation model of the economy(Sandia Report#SAND96-2459)[R]. Sandia National Laboratories,Albuquerque,NM,October,1996, http://www.sandia.gov.
[23]Arthur W B,Holland J H,LeBaron B,Palmer R,Tayler P. Asset pricing under endogenous expectations[R]. Santa Fe Institute,1996.
[24]Ilachinski A. Towards a Science of Experimental Complexity:An Artificial-Life Approach to Modeling Warfare. Center for Naval Analyses, Alenandria, Virginia, USA.
[25]Andrew Ilachinski著,张志祥译.人工战争：基于多Agent的作战仿真.电子工业出版社2010,8.
[26]Marcenac P. Emergence of Earthquakes by Multi Agent Simulation. http://www.univ-reunion. fr/-geomas.
[27]Dong Won Yi, Soung Hie Kim, Nak Hyun Kim. Combined Modeling with Multi-Agent Systems and Simulation:Its Application to Harbor Supply Chain Management. Proceeding of the 35th Hawaii International Conference on System Sciences,2002.
[28]Szirbik N, Wagner Q Tulba F. Agent-Based Modeling and Simulation of Distributed Business Processes in Supply Networks. The International Workshop on Modeling & Applied Simulation, MAS2003Program.
[29]Standish R K. Complexity Growth in Artificial Life. http://parallel.acsu.unsw.edu.au/rks.
[30]Railsback S. Complex Adaptive Systems Meets the Real World:Agent-based Simulation for Ecological Management and Research. http://math.humboldt.edu/-simsys/.
[31]Stuart J. Russell and Peter Norvig. Artificial Intelligence A Modern Approach (Third Edition), http://aima.cs.berkeley.edu/
[32]廖守亿.复杂系统基于Agent建模与仿真方法研究及应用(D).长沙：国防科技大学,2005.
[33]徐绪松.复杂科学管理.科学出版社.2010.10
[34]孙成松,花传杰.基于Multi-agent的坦克分队作战仿真[J].计算机仿真,2005,22(3)：11-14.
[35]贺建民,刘晓明.多Agent系统在作战仿真中的应用.解放军理工大学学报(自然科学版)Vo 1.7 No.6.Dec.2006
[36]郭叶军.机器人足球仿真比赛中多智能体系统的构建.浙江大学硕士学位论文.2004
[37]Uhrmacher A M, Gugler K. Distributed, Parallel Simulation of Multiple, Deliberative Agents. Proceedings of the 14th Workshop on Parallel and Distributed Simulation,2000.
[38]Uhrmacher A M, Tyschler P, etc Modeling and Simulation of Mobile Agents. Future Generation Computer Systems,2000.
[39]Ting-Peng Liang, Jin-Shiang Huang. A Framework for Applying intelligent agents to electronic trading. Decision Support Systems,2000,28:305-317.
[40]Lee K J, Chang Y S, Lee J K. Time-bound negotiation framework for electronic commerce agents. Decision Support Systems,2000:319-331
[41]Jennings N R, Coerra J M, etc. Developing Industrial Multi-agent System. In: Proceedings of the First International Conference on Multi-agent Systems,(ICMA-95),423-430.
[42]Franklin S, Graesser A. Is it an agent, or just a program? A Taxonomy for autonomous agent. In:Proceedings of the Third international Workshops on Agent Theories, Architectures, and Language, Springer-Velag,1996:62-71.
[43]Wooldridge M J. Agent-based Software Engineering. JEE Proc. Software Engineering.1997,144(1):26-37.
[44]Lane D M, Mcfadzean A G Distributed problem solving and real-time mechanisms in robot architectures. Engineering Application intelligence, 1994,7(2):105-117.
[45]Shoham Y. Agent-oriented programming. Artificial Intelligence,1993,60: 51-92.
[46]Wooldridge M J, Jennings N R. Intelligent agents:Theory and practice. Knowledge Engineering Reviews,1995,10(2):115-152.
[47]Rao A S, George M P. BDI Agents:from theory to practice. Proceedings of 1st International Conference on Multi-Agent Systems(ICMAS-95), San Francisco, ACM Press,1995:312-319.
[48]Ferber J. Multi-agent systems, an introduction to distributed artificial intelligence. Addison-Wesley,1999.
[49]史忠植.智能主体及其应用.北京：科学出版社,2001.
[50]方美琪,宗骁.一种普及型的建模环境——StarLogo[J].计算机教育,2003,12(1)：71—72.
[51]Wilensky, U. (1999). NetLogo. http://ccl.northwestern.edu/netlogo. Center for Connected Learning and Computer-Based Modeling, Northwestern University, Evanston, IL.
[52]丁浩,杨小平.Swarm—一个支持人工生命建模的面向对象模拟平台[J].系统仿真学报,2002,14(5)：569—572.
[53]Nick C. Repast:An extensible framework for Agent simulation [EB/ OL]. http://www.econ.iastate.edu/tesfatsi/RepasTutorial. Coiler. pdf,2001 —10.
[54]赵剑冬,林健.基于Agent的Repast仿真分析与实现[J].计算机仿真2007,24(9)：265-268
[55]Miles T P. What is Ascape and why should you care?[J]. Journal of Artificial Societies and Social Simulation, 2001,4(1):383—397.
[56]霍凯,肖建毅.在TNG系统中定制Agent的开发技术[J].计算机应用,2001,21(4)：61—62.
[57]杨公平,曾广周,卢朝霞.移动Agent系统中的排队机制研究[J].计算机学报Vol.28 No.11, Nov.2005:1817-1822.
[58]Green,D G Hierarchy, complexity and agent based models [C]//In Our Fragile World:Challenges and Opportunities for Sustainable Development. UNESCO,Paris.Green,DQ2000.
[59]朱江,伍聪基于Agent的计算机建模平台的比较研究[J].系统工程学报Vol.20 No.2 Apr.2005 160～166
[60]郭锦 基于多智能体的植被空间格局动态模拟《北京林业大学硕士论文》2009.4.1
[2]Herbert S.L.Scoott R.,Eric B.TCRP report90:Bus Rapid Transit[R].Transportation Research Board.2003.3-1.3.1
[3]赵杰,胡子祥,刘丽亚.国外发展快速公交的经验及对我国城市交通发展的启示[J].城市交通Vol2.No.3 Aug.2004:56-59
[4]王少飞,关可,肖鹏等.我国快速公交系统BRT)发展综述[J]中国智能交通2008.1 70～74
[5]盛昭翰,张军,杜建国等著.社会科学计算实验理论与应用[C]上海三联书店2009
[6]廖守亿,戴金海.复杂系统基于Agent的建模与仿真设计模式及软件框架[J].计算机仿真2005,22(5)：254～258.
[7]Macal, Charles M. North, Michael J.Tutorial on agent-based modeling and simulation:Proceedings of Winter Simulation Conference, v 2005, p2-15
[8]李成杰.基于Agent的排队系统仿真研究.工学硕士学位论文,山东大学,2009.
[9]霍兰.隐秩序-适应性造就复杂性.周晓牧等译.上海科技出版社,2000.
[10]卡斯蒂著.王千祥等译.虚实世界[M].上海：上海科技教育出版社,1998.
[11]Schreiber D. The Emergence of Parties:An Agent-Based Simulation. http://www.bol.ucla.edu/-dschreib/EmergingParties/Emergence Parties6-24-01.pdf
[12]Helbing D. Agent-Based Simulation of Traffic Jam, Crowds, and Supply Networks. In Proceeding of the IMA'Hot Topics' Workshop, EMA, Minneapolis, MN.2003.
[13]Barret C. Simulation Scientist Relates to Data/Information Fusion and C2 Systems, Briefing Slides, Los Alamos(1997).
[14]Yang,L.Z,J.Li,Liu,S.B. Simulation of pedestrian counter-flow with right-moving preference.Physica a-Statistical Mechanics and Its Applications,2008,387(13):3281-3289
[15]Epstein J M, Axtell R. Growing artificial societies, social science from the bottom up[M]. Washington,D.C.Brookings Institution Press;Cambridge,Mass.MIT Press,1996.
[16]http://www.simworld.co.uk/
[17]Srbljinovic A, Penzar D, Rodik P, Kardov K. Agent-Based Modeling of Ethnic Mobilization:The Former ugoslaviaCase.1st LA Conference on Computational Social Science and Social Complexity:AB Modeling in Social Sciences,2002.
[18]Derek WB, Oliveira FS. Agent-based Simulation:An Application to the New Electricity Trading Arrangements of England and Wales. IEEE-TEC, special issue:Agent Based Computational Economics,2001.
[19]廖守亿.复杂系统基于Agent的建模与仿真方法研究及应用.工学博士论文,国防科学技术大学,2005.
[20]张江,李学伟.人工社会——基于Agent的社会学仿真[J].系统工程,2005,23(1)：13-20.
[21]Deguchi H,Deguchi H. Economics as an agent-based complex system[M]. Springer-Verlag Press,2004.
[22]Basu N,Pryor J,Quint T,Arnold T. Aspen:a microsimulation model of the economy(Sandia Report#SAND96-2459)[R]. Sandia National Laboratories,Albuquerque,NM,October,1996, http://www.sandia.gov.
[23]Arthur W B,Holland J H,LeBaron B,Palmer R,Tayler P. Asset pricing under endogenous expectations[R]. Santa Fe Institute,1996.
[24]Ilachinski A. Towards a Science of Experimental Complexity:An Artificial-Life Approach to Modeling Warfare. Center for Naval Analyses, Alenandria, Virginia, USA.
[25]Andrew Ilachinski著,张志祥译.人工战争：基于多Agent的作战仿真.电子工业出版社2010,8.
[26]Marcenac P. Emergence of Earthquakes by Multi Agent Simulation. http://www.univ-reunion. fr/-geomas.
[27]Dong Won Yi, Soung Hie Kim, Nak Hyun Kim. Combined Modeling with Multi-Agent Systems and Simulation:Its Application to Harbor Supply Chain Management. Proceeding of the 35th Hawaii International Conference on System Sciences,2002.
[28]Szirbik N, Wagner Q Tulba F. Agent-Based Modeling and Simulation of Distributed Business Processes in Supply Networks. The International Workshop on Modeling & Applied Simulation, MAS2003Program.
[29]Standish R K. Complexity Growth in Artificial Life. http://parallel.acsu.unsw.edu.au/rks.
[30]Railsback S. Complex Adaptive Systems Meets the Real World:Agent-based Simulation for Ecological Management and Research. http://math.humboldt.edu/-simsys/.
[31]Stuart J. Russell and Peter Norvig. Artificial Intelligence A Modern Approach (Third Edition), http://aima.cs.berkeley.edu/
[32]廖守亿.复杂系统基于Agent建模与仿真方法研究及应用(D).长沙：国防科技大学,2005.
[33]徐绪松.复杂科学管理.科学出版社.2010.10
[34]孙成松,花传杰.基于Multi-agent的坦克分队作战仿真[J].计算机仿真,2005,22(3)：11-14.
[35]贺建民,刘晓明.多Agent系统在作战仿真中的应用.解放军理工大学学报(自然科学版)Vo 1.7 No.6.Dec.2006
[36]郭叶军.机器人足球仿真比赛中多智能体系统的构建.浙江大学硕士学位论文.2004
[37]Uhrmacher A M, Gugler K. Distributed, Parallel Simulation of Multiple, Deliberative Agents. Proceedings of the 14th Workshop on Parallel and Distributed Simulation,2000.
[38]Uhrmacher A M, Tyschler P, etc Modeling and Simulation of Mobile Agents. Future Generation Computer Systems,2000.
[39]Ting-Peng Liang, Jin-Shiang Huang. A Framework for Applying intelligent agents to electronic trading. Decision Support Systems,2000,28:305-317.
[40]Lee K J, Chang Y S, Lee J K. Time-bound negotiation framework for electronic commerce agents. Decision Support Systems,2000:319-331
[41]Jennings N R, Coerra J M, etc. Developing Industrial Multi-agent System. In: Proceedings of the First International Conference on Multi-agent Systems,(ICMA-95),423-430.
[42]Franklin S, Graesser A. Is it an agent, or just a program? A Taxonomy for autonomous agent. In:Proceedings of the Third international Workshops on Agent Theories, Architectures, and Language, Springer-Velag,1996:62-71.
[43]Wooldridge M J. Agent-based Software Engineering. JEE Proc. Software Engineering.1997,144(1):26-37.
[44]Lane D M, Mcfadzean A G Distributed problem solving and real-time mechanisms in robot architectures. Engineering Application intelligence, 1994,7(2):105-117.
[45]Shoham Y. Agent-oriented programming. Artificial Intelligence,1993,60: 51-92.
[46]Wooldridge M J, Jennings N R. Intelligent agents:Theory and practice. Knowledge Engineering Reviews,1995,10(2):115-152.
[47]Rao A S, George M P. BDI Agents:from theory to practice. Proceedings of 1st International Conference on Multi-Agent Systems(ICMAS-95), San Francisco, ACM Press,1995:312-319.
[48]Ferber J. Multi-agent systems, an introduction to distributed artificial intelligence. Addison-Wesley,1999.
[49]史忠植.智能主体及其应用.北京：科学出版社,2001.
[50]方美琪,宗骁.一种普及型的建模环境——StarLogo[J].计算机教育,2003,12(1)：71—72.
[51]Wilensky, U. (1999). NetLogo. http://ccl.northwestern.edu/netlogo. Center for Connected Learning and Computer-Based Modeling, Northwestern University, Evanston, IL.
[52]丁浩,杨小平.Swarm—一个支持人工生命建模的面向对象模拟平台[J].系统仿真学报,2002,14(5)：569—572.
[53]Nick C. Repast:An extensible framework for Agent simulation [EB/ OL]. http://www.econ.iastate.edu/tesfatsi/RepasTutorial. Coiler. pdf,2001 —10.
[54]赵剑冬,林健.基于Agent的Repast仿真分析与实现[J].计算机仿真2007,24(9)：265-268
[55]Miles T P. What is Ascape and why should you care?[J]. Journal of Artificial Societies and Social Simulation, 2001,4(1):383—397.
[56]霍凯,肖建毅.在TNG系统中定制Agent的开发技术[J].计算机应用,2001,21(4)：61—62.
[57]杨公平,曾广周,卢朝霞.移动Agent系统中的排队机制研究[J].计算机学报Vol.28 No.11, Nov.2005:1817-1822.
[58]Green,D G Hierarchy, complexity and agent based models [C]//In Our Fragile World:Challenges and Opportunities for Sustainable Development. UNESCO,Paris.Green,DQ2000.
[59]朱江,伍聪基于Agent的计算机建模平台的比较研究[J].系统工程学报Vol.20 No.2 Apr.2005 160～166
[60]郭锦 基于多智能体的植被空间格局动态模拟《北京林业大学硕士论文》2009.4.1