计算机复杂网络系统中竞争特性的研究
|
摘要
随着近二十多年计算机网络、通信技术的飞速发展,在计算机系统、通信系统基础上发展形成的计算机网络系统呈现出日益复杂的特性。因特网以及广域网、城域网、局域网都近似呈现出开放的复杂巨系统的特性,其中尤其以竞争、合作特性为最。为此本文对计算机网络复杂系统中存在的竞争—冲突问题进行了研究。主要包括以下几个方面的工作:
讨论了计算机网络系统表现出来的复杂特性,尤其对系统的竞争特性进行了深入分析。得出以下结论:在复杂的计算机网络系统中,竞争具有普遍性和客观性,而合作具有特殊性和暂时性。要根据客观的需求和竞争的特性改进冲突解决策略,化解冲突,从而实现成员间的有序合作。
针对由用户竞争Internet网络资源引起的网络拥塞,提出了基于多优先级动态缓存管理策略的优化算法—PDT-RED算法和OPDT-RED算法。通过该算法,当大量突发数据竞争缓存引发冲突时,保证了高优先级数据的低丢包率和缓冲区的利用率。实验证明,这两种改进的RED算法不仅简单易于实现,还降低了平均分组丢失率。
基于OPNet网络仿真工具,对多星局域网(Local Area Network,LAN)中存在的竞争—冲突淘汰(Contention-Collision Cancellation,C-CC)存取控制方式进行了仿真建模。通过仿真实验,将仿真结果与已报告的单星LAN的Ⅰ类系统模型数学建模结果进行了比较;对C-CC存取方式Ⅰ类、Ⅲ类、Ⅴ类系统模型进行了性能比较;同时探讨了C-CC存取方式Ⅰ类系统模型在中心节点交换通道大于1条件下的性能。
对重负载下双星LAN的C-CC存取方式Ⅰ类系统模型进行了数学建模研究。关于多星LAN数学建模的研究,较长一个时期人们主要集中在中心节点交换通道为1的单星LAN。截止目前C-CC存取方式的Ⅰ-Ⅵ类系统模型都已进行了数学建模。由于数学方面存在的困难,中心节点交换通道为2的所谓双星LAN的数学建模研究突破很晚。目前只报告了重负载下双星LAN的一种数学建模。该文选择了观察时点有顾客的终端作为观察终端A,求得了顾客在系统中的平均滞留时间。而本文选择了观察时点无顾客的终端作为观察终端A,求得了以嵌入点r时点为起点至A第一次产生的顾客离开系统的平均时间τ_i,由于τ_i能体现观察终端产生顾客的滞留时间,因此能够进一步评价双星LAN的性能。
在完成上述研究工作之后,本文首次对重负载下双星LAN的C-CC存取方式Ⅴ类系统模型进行了数学建模研究。选择了观察时点有顾客的终端作为观察终端A,求得了以嵌入点r时点为起点至A顾客离开系统的平均时间t_i。这一研究是继Ⅰ类双星LAN之后,对双星LAN竞争-冲突淘汰方式的又一创新研究。
With the rapid development of computer science and communication technology in the recent decades,computer network systems,which come into being based on the computer system and communication system,show the increasingly complex characters. The Internet,Wide Area Network,Metropolitan Area Network,Local Area Network all present complex features,particularly the competition-cooperation feature.The contention-conflict issues of computer networks are discussed in this paper.The study includes the following five issues:
Firstly,the complex features of the computer network systems,especially the competition character,are deeply discussed.It is conclude that the competition show universality and objectivity,whereas the cooperation show particularity and provisionality. According to the law of the competition character,the conflict resolution strategy can be improved to meet the objective demand,so that the competition can be solved to realize the order cooperation between members.
Secondly,to resolve the Internet congestion result from competing network resources,a multi-priority dynamic threshold deployment—Preferential Dynamic Threshold RED and Optimized Preferential Dynamic Threshold RED algorithms are proposed.They can satisfy the lower loss rate of packets with high priority and high buffer utilization.
Thirdly,based on OPNet modeler,the simulation for Contention-Collision Cancellation(C-CC) access control mode in multi-star LAN is implemented.Through the simulation modeling,The simulation result for typeⅠsingle-star LAN is compared with the mathematical result in previous reference;the performance of typeⅠ,typeⅢand typeⅤsingle-star LAN are evaluated;the typeⅠmulti-star LAN is also discussed.
Fourthly,the typeⅠsystem model for double-star LAN based on heavy load is revaluated.During the past long period,the mathematical modeling researches for multi-star LAN have been focusing on single-star LAN,for which all models and performance evaluation of the Contention-Collision Cancellation(C-CC) access mode have already finished.The breakthrough of mathematical modeling for double-star LAN is very late because of difficulty in math aspect,and just deduced the mean waiting time of the customer generated by observing terminal A.In this paper,we select the terminal A without customer as observing object,then getτ_i which is the mean period from time point r to the end of service for the customer generated firstly by terminal A,on the condition that at observing time point r,there are i(i＞0) customers in system and no customer in observing terminal A.This paper consummates the mathematical model of typeⅠC-CC access mode for double-star LAN.
Finally,for the first time,the case of 2 servers is introduced into the typeⅤsystem model of C-CC access control mode in this paper.The terminal A with customer is selected as the observing object,and the tme delay t_i is got.The parameter t_i is the mean period from the observing time point r to the time point when the customer of terminal A departs from system.,on the condition that at the time point r,there are i(i＞0, based on heavy load) customers in system.This is another creative research on the C-CC access mode for double-star LAN after the typeⅠdouble-star LAN.
讨论了计算机网络系统表现出来的复杂特性,尤其对系统的竞争特性进行了深入分析。得出以下结论:在复杂的计算机网络系统中,竞争具有普遍性和客观性,而合作具有特殊性和暂时性。要根据客观的需求和竞争的特性改进冲突解决策略,化解冲突,从而实现成员间的有序合作。
针对由用户竞争Internet网络资源引起的网络拥塞,提出了基于多优先级动态缓存管理策略的优化算法—PDT-RED算法和OPDT-RED算法。通过该算法,当大量突发数据竞争缓存引发冲突时,保证了高优先级数据的低丢包率和缓冲区的利用率。实验证明,这两种改进的RED算法不仅简单易于实现,还降低了平均分组丢失率。
基于OPNet网络仿真工具,对多星局域网(Local Area Network,LAN)中存在的竞争—冲突淘汰(Contention-Collision Cancellation,C-CC)存取控制方式进行了仿真建模。通过仿真实验,将仿真结果与已报告的单星LAN的Ⅰ类系统模型数学建模结果进行了比较;对C-CC存取方式Ⅰ类、Ⅲ类、Ⅴ类系统模型进行了性能比较;同时探讨了C-CC存取方式Ⅰ类系统模型在中心节点交换通道大于1条件下的性能。
对重负载下双星LAN的C-CC存取方式Ⅰ类系统模型进行了数学建模研究。关于多星LAN数学建模的研究,较长一个时期人们主要集中在中心节点交换通道为1的单星LAN。截止目前C-CC存取方式的Ⅰ-Ⅵ类系统模型都已进行了数学建模。由于数学方面存在的困难,中心节点交换通道为2的所谓双星LAN的数学建模研究突破很晚。目前只报告了重负载下双星LAN的一种数学建模。该文选择了观察时点有顾客的终端作为观察终端A,求得了顾客在系统中的平均滞留时间。而本文选择了观察时点无顾客的终端作为观察终端A,求得了以嵌入点r时点为起点至A第一次产生的顾客离开系统的平均时间τ_i,由于τ_i能体现观察终端产生顾客的滞留时间,因此能够进一步评价双星LAN的性能。
在完成上述研究工作之后,本文首次对重负载下双星LAN的C-CC存取方式Ⅴ类系统模型进行了数学建模研究。选择了观察时点有顾客的终端作为观察终端A,求得了以嵌入点r时点为起点至A顾客离开系统的平均时间t_i。这一研究是继Ⅰ类双星LAN之后,对双星LAN竞争-冲突淘汰方式的又一创新研究。
With the rapid development of computer science and communication technology in the recent decades,computer network systems,which come into being based on the computer system and communication system,show the increasingly complex characters. The Internet,Wide Area Network,Metropolitan Area Network,Local Area Network all present complex features,particularly the competition-cooperation feature.The contention-conflict issues of computer networks are discussed in this paper.The study includes the following five issues:
Firstly,the complex features of the computer network systems,especially the competition character,are deeply discussed.It is conclude that the competition show universality and objectivity,whereas the cooperation show particularity and provisionality. According to the law of the competition character,the conflict resolution strategy can be improved to meet the objective demand,so that the competition can be solved to realize the order cooperation between members.
Secondly,to resolve the Internet congestion result from competing network resources,a multi-priority dynamic threshold deployment—Preferential Dynamic Threshold RED and Optimized Preferential Dynamic Threshold RED algorithms are proposed.They can satisfy the lower loss rate of packets with high priority and high buffer utilization.
Thirdly,based on OPNet modeler,the simulation for Contention-Collision Cancellation(C-CC) access control mode in multi-star LAN is implemented.Through the simulation modeling,The simulation result for typeⅠsingle-star LAN is compared with the mathematical result in previous reference;the performance of typeⅠ,typeⅢand typeⅤsingle-star LAN are evaluated;the typeⅠmulti-star LAN is also discussed.
Fourthly,the typeⅠsystem model for double-star LAN based on heavy load is revaluated.During the past long period,the mathematical modeling researches for multi-star LAN have been focusing on single-star LAN,for which all models and performance evaluation of the Contention-Collision Cancellation(C-CC) access mode have already finished.The breakthrough of mathematical modeling for double-star LAN is very late because of difficulty in math aspect,and just deduced the mean waiting time of the customer generated by observing terminal A.In this paper,we select the terminal A without customer as observing object,then getτ_i which is the mean period from time point r to the end of service for the customer generated firstly by terminal A,on the condition that at observing time point r,there are i(i＞0) customers in system and no customer in observing terminal A.This paper consummates the mathematical model of typeⅠC-CC access mode for double-star LAN.
Finally,for the first time,the case of 2 servers is introduced into the typeⅤsystem model of C-CC access control mode in this paper.The terminal A with customer is selected as the observing object,and the tme delay t_i is got.The parameter t_i is the mean period from the observing time point r to the time point when the customer of terminal A departs from system.,on the condition that at the time point r,there are i(i＞0, based on heavy load) customers in system.This is another creative research on the C-CC access mode for double-star LAN after the typeⅠdouble-star LAN.
引文
1.钱学森,于景元,戴汝为.一个科学的新领域——开放的复杂巨系统及其方法论.自然杂志,1990,13(1):3-10
2.戴汝为,操龙兵.Internet——一个开放的复杂巨系统.中国科学(E辑),2003,33(4):289-296
3.许国志.系统科学与工程研究.上海:上海科技技术出版社,2004
4.米歇尔·沃尔德罗普.复杂—诞生于秩序与混沌边缘的科学.北京:三联书店,1997
5.张嗣瀛.复杂系统与复杂性科学简介.青岛大学学报,2001,16(4):25-28
6.戴汝为.复杂巨系统科学—一门21世纪的科学.自然杂志,1997,19(4):187-192
7.金吾伦,郭元林.国外复杂性科学的研究进展.国外社会科学,2003(6):2-5
8.戴昌钧,冯惠玲.竞争与对策.上海:学林出版社,1990
9.郭雷,许晓鸣.复杂网络.上海:上海科技教育出版社,2006
10.汪小帆,李翔,陈关荣.复杂网络理论及其应用.北京:清华大学出版社,2006
11.George Johnson.First cells,then species,now the web.United States:The New York Times Company,2000.http://www.nytimes.com/2000/12/26/science/26WEBS.html?pagewanted=all.
12.Waxman BM.Routing of multipoint connections.IEEE Journal on selected areas in communications.1988,6(9):1617-1622
13.Doar M B.A better model for generating test networks.In:Proc.of the GLOBECOM'96.London:IEEE,1996:86-93
14.Zegura E W,Calvert K L,Donahoo M J.A quantitative comparison of graph-based models for Internet topology.IEEE/ACM Trans.on Networking,1997,5(6):770-783
15.Albert-Laszlo Barabasi,Reka Albert,Hawoong Jeong.Scale-free characteristics of random networks:the topology of the world-wide web.Physica A,2000,281:69-77
16.Faloutsos M,Faloutsos P,Faloutsos C.On power-law relationships of the Internet topology.Proceedings SIGCOMM'99.United States:ACM Press,1999,29(4):251-262.
17.Adamic L,Huberman B.Power-law distribution of the world-wide web.Science,2000,287(24):2115
18.Newman M E J.Models of the small world.Stat Phys,2000,101:819-841
19.Reka Albert,Hawoong Jeong,Albert-Laszlo Barabasi.Diameter of the world-wide web.Nature,1999,401:130-131
20.Adamic L.The small world web.European Conference on Digital Libraries.France:Springer,1999:443-454
21.Albert-Laszlo Barabasi,Reka Albert.Emergence of scaling in random networks.Science,1999,286:509-512
22.王林,戴冠中,覃森.Internet的一种新的动态演化模型.系统工程理论与实践,2006,26(10):102-106
23.Krapivsky P L,Redner S.A statistical physics perspective on web growth.Computer Networks,2002,39:261-276
24.Dorogovtsev S N,Mendes J F F,Samukhin A N.Structure of growing networks with preferential linking.Phys Rev Lett,2000,85(21):4633-4636
25.Dorogovtsev S N,Mendes J F F.Evolution of networks with aging of sites.Phys Rev E,2000,62(2):1842-1845
26.Reka Albert,Albert-Laszlo Barabasi.Topology of evolving networks:Local events and universality.Phys Rev Lett,2000,85(24):5234-5237
27.Ginestra Bianconi,Albert-Laszlo Barabasi.Bose-Einstein condensation in complex networks.Phys Rev Lett,2001,86(24):5632-5635
28.Wang Wenxu,Wang Binghong,Bo Hu,et al.General dynamics of topology and traffic on weighted technological networks.Phys Rev Lett,2005,94:188702
29.Leland W,Taqqu M,Willinger W,et al.On the self-similar nature of Ethernet traffic.IEEE/ACM Transactions on Networking,1994,2(1):1-15
30.Willinger W,Taqqu M S,Sherman R.Self-similarity through high-variability:statistical analysis of Ethemet LAN traffic at source level.ACM Computer Communication Review,1995,25(4):100-113
31.袁坚,任勇,刘锋,等.复杂计算机网络中的相变和整体关联行为.物理学报,2001,50(7):1221-1225
32.刘锋,任勇,山秀明.互联网络数据报传输的一种简单元胞自动机模型.物理学报,2002,51(06):1175-1180
33.Tretyakov A Y,Takayasu H,and Takayasu M.Phase transition in a computer network model.PhysicaA,1998,253(1):315-322
34.Ohira T,Sawatari R.Phase transition in a computer network traffic model.Phys.Rev.E.1998,58(1):193-195
35.白刚,隆克平,程时端.Internet中的相变现象及一种新的相变业务流模型.电子学报,2002,30(2):191-195
36.Lawniczak A T,Gerisch A,and Maxie K.Effects of randomly added links on a phase transition in data network traffic models.Proceedings of DCDIS,2003.384-389
37.Takayasu M,Fukuda K,and Takayasu H.Application of statistical physics to the Internet traffics.PhysicaA,1999,274(1):140-148
38.KONHEIM A G.Descendent set:an efficient approach for analysis of polling systems.IEEE Transaction on Communication,1994,42(8):1245-1253
39.王智,于海斌,宋叶琼,等.混合服务方式下的M_1+M_2/G/1轮询系统的平均运行周期.通信学报,2002,23(7):8-18
40.逯昭义,罗秀秀.综合业务城域网IEEE802.5预约级协议改进策略.电子与信息学报,2002,24(11):1581-1588
41.逯昭义.计算机网络体系结构.清华大学出版社、北京交通大学出版社,2003:115-126
42.陆文彦,贾维嘉,杜文峰等.IEEE802.16竞争解决方案的性能分析.软件学报,2007,18(9):2259-2270
43.王忠锋,于海斌,王宏等.工业以太网实时通信中的调度表构建策略研究.信息与控制,2007,36(3):261-265
44.逯昭义,齐藤忠夫.同时多重接续星形LAN中心节的构成.通信学报,9(3):79-82
45.逯昭义,王思明.同时多重接续星形LAN的改进模式.科学通报,1989,(22):1749-1752
46.Lu Zhaoyi,Saito T.Star Type Local Area Network Access Control.Science in China,1990,33(a):1123-1131.
47.逯昭义,齐藤忠夫.改进型多星LAN.电子学报,1993,21(11):99-103
48.逯昭义.竞争-冲突淘汰存取方式Ⅰ类系统模型性能评价.电子学报,1995,23(9):115-117
49.逯昭义,陈永义,张建树.竞争-冲突淘汰存取方式的数学模型.电子科学学刊,1996,18(6):607-611
50.Lu Z,Sun L.Mathematical model for access mode of contention-collision cancellation in a star LAN.Journal of Electronics,2004,21(1):37-47.
51.Lu Z,Lu M,Zhao D,et al.On the Ⅱnd model of contention-collision elimination access mode in star LAN.Applied Math.Modelling,2003,27(11):899-911
52.Lu Z,et al.A special random selective services queuing model for access to a star LAN[J].Applied Math.Modelling,1997,21:15-20
53.Lu Z,Sun L,Lu M,et al.The mathematical modeling for the Contention-Collision Elimination access mode of the Ⅳth system model to a multiple star LAN.Applied Math.Modelling,30(44):367-385
54.Lu Z,Zhang J,Lu M.The mathematical modelling for the access mode of the Ⅴth System Model to a Multiple Star LAN.Applied Math.Modelling,1999,23:231-239
55.逯昭义,杨兴梅,王超.竞争—冲突淘汰存取方式Ⅵ类系统模型建模研究.电子学报,2007,35(10):1817-1822
56.刘海光,逯昭义,崔杰.重负载下双星LAN的一种数学模型的探讨.中国科学(E辑),2007,37(6):813-823
57.Stevens.TCP Slow Start,Congestion Avoidance,Fast Retransmit,and Fast Recovery Algorithms. RFC 2001,Jan.1997
58.Stiliadis D,Varma A.Rate-proportional servers:a design methodology for fair qurueing algorithms.IEEE/ACM Transactions on networking,1998,6(2):164-174
59.王重钢,隆克平,龚向阳,程时端.分组交换网络中队列调度算法的研究及其展望.电子学报,2001,29(4):553-559
60.Chow H,Leon-Garcia A.A Feedback Control Extension to Differentiated Services,Internet Draft,March 1999,http://bgp.potaroo.net/ietf/all-ids/draft-chow-diffserv-fbctrl-00.txt
61.Kalyanaraman S,Harrison D,Arora S,et al.A One-bit Feedback Enhanced Differentiated Services Architecture.Internet Draft,March 1998,http://bgp.potaroo.net/ietf/all-ids/draft-shivkuma-ecn-diffserv-00.txt
62.Sally Folyd,Van Jacobson.Random Early Detection Gateways for Congestion Control,IEEE/ACM Transactions on Networking,1993,1(4):397-413
63.Feng W,Kandlur D,Saha D,et al.A Self-Configuring RED gateway.In Proceedings of INFOCOM'99.New York:IEEE communications society,1999:1320-1328
64.Ott T J,Lakshman T V,Wong L H.SRED:Stabilized RED.In Proceedings of INFOCOM'99.New York:IEEE communications society,1999:1346-1355
65.Feng W,Kandlur D,Saha D,et al.Blue:A New Class of Active Queue Management Algorithms.IEEE INFOCOM 2001.Anchorage,Alaska,2001:1520-1529]
66.Yoo S J B,Bansal Y,Pan Z,et al.Optical-Label based packet routing system with contention resolution in wavelength,time and space domains.Technical Digest,OFC 2002,Anaheim,California,March,2002
67.Kim S,Kim N,Kang M.Contention resolution for optical burst switching networks using alternative routing.Communications,2002,5:2678-2681
68.Yao S,Mukherjee B,Yoo S J B.A unified study of contention-resolution schemes in optical packet-switched networks.Lightwave Technology,2003,21(3):672-683
69.Gauger C M,Kohn M,and ScharfJ.Comparison of contention resolution strategies in OBS network scenarios.Transparent Optical Networks,2004,1(1):18-21
70.张丽娟,李维民,张淳民等.一种用于解决OBS网中资源竞争的新机制.光通信研究,2006,6:8-10
71.张正江,王汝言.光突发交换竞争解决机制研究.微计算机信息,2006,22(12):154-157
72.许光辉.随机服务系统.北京:科学出版社,1980
73.华兴.排队论与随机服务系统.上海:上海翻译出版公司,1987
74.唐应辉,唐小我.排队论基础与分析技术.北京:科学出版社,2006
75.罗荣桂.排队模型及其应用.武汉:华中理工大学出版社,1990
76.盛友招.排队论及其在计算机通信中的应用.北京:北京邮电大学出版社,1998
77.逯昭义,王思明.计算机通信网络信息量理论.电子工业出版社.1997
78.Casettv C,Meo M.An analytical framework for the performance evaluation ofTCP Reno connections.Computer Networks.2001,37(5):669-682
79.Altman E,Avrachenkov K,Barakat C,et al.State-dependent M/G/1 type queueing analysis for congestion control in data networks.Computer Networks.2002,39(6):789-808
80.Brown T X,Gabow N H.The limits of input-queued switch performance with future packet arrival information.Computer Networks.2003,42(4):441-460
81.Yook SH,Joong H,Barabasi A L,Modeling the Internet's large-scale topology,Proceedings of the National Academy of Science of the United State of America,2002,99(21):13382-13386
82.Hart J.Conquering complexity:data networking trends as technology meets market reality.In Proceedings of LCN'01.USA:2001:4-17
83.Dai D,Panda D K.How much does network contention affect distributed shared memory performance? USA:ICPP'97
84.Steffenel L A.Modelling network contention effects on all-to-all operations.IEEE Internation Conference on Cluster Computing 2006:1-10
85.Moritz C A,Frank M I.LoGPC:Modeling Network Contention in Message-Passing Programs.IEEE transactions on parallel and distributed systems,2001,12(4):404-415
86.Andrews M,Awerbuch B,Fernandez A,et al.Universal-stability results and performance bounds for greedy contention-resolution protocols.Journal of the ACM,2001,48(1):39-69
87.Gao F,Zhao D.Improved Ternary-tree Algorithm for Contention Resolution over Random Multi-access Channel.Journal of china universities of posts and telecommunications.2001,8(2):35-39
88.何丽红,景方,杜德生等.复杂适应系统中合作与竞争关系的涌现.哈尔滨理工大学学报,2003,8(4):75-78
89.徐恪,吴建平,徐明伟.高等计算机网络—体系结构、协议机制、算法设计与路由器技术.北京:机械工业出版社,2003
90.Thareja A K,Agrawala A K.On the Design of Optimal Policy for Sharing Finite Buffers.IEEE Transactions on Communications,1984,32(6):737-740
91.Choudhury A K,Hahne E L.Dynamic Queue Length Thresholds for Shared-Memory Packet Switches.IEEE/ACM Transactions on Networking,1998,6(2):130-140
92.Hahne E L,Choudhury A K.Dynamic Queue Length Thresholds for Multiple Loss Priorities.IEEE/ACM Transactions on Networking,2002,10(3):368-380.
93.Agharebparast F,Leung V C M.Improving the performance of RED deployment on a class based queue with shared buffer.Proc.of IEEE Globecom'01.San Antonio,TX,USA:2001:2363-2367.
94.Hu C,Liu B.RED with optimized dynamic threshold deployment on shared buffer.Fukuoka,Japan:AINA,2004,(2):451-454.
95.Lin D,Morris R.Dynamics of Random Early Detection.Proc.of ACM SIGCOMM.New York:ACM Press,1997:127-137.
96.NS Project.http://nsnam.isi.edu/nsnam.
97.于斌,孙斌,温暖等.NS2与网络模拟.北京:人民邮电出版社,2007
98.Floyd S.RED:Discussions of setting parameters,http://www.icir.org/floyd/red.html
99.Pappu S K.Simulating computer systems.Potentials,IEEE,1997,16(1):16-18
100.孙屹.OPNET通信仿真开发手册.北京:国防工业出版社,2005.
101.李馨,叶明.OPNET Modeler网络建模与仿真.西安:西安电子科技大学出版社,2006
102.李信真,车刚明等.《计算方法》.西安:西北工业大学出版社,2000年
2.戴汝为,操龙兵.Internet——一个开放的复杂巨系统.中国科学(E辑),2003,33(4):289-296
3.许国志.系统科学与工程研究.上海:上海科技技术出版社,2004
4.米歇尔·沃尔德罗普.复杂—诞生于秩序与混沌边缘的科学.北京:三联书店,1997
5.张嗣瀛.复杂系统与复杂性科学简介.青岛大学学报,2001,16(4):25-28
6.戴汝为.复杂巨系统科学—一门21世纪的科学.自然杂志,1997,19(4):187-192
7.金吾伦,郭元林.国外复杂性科学的研究进展.国外社会科学,2003(6):2-5
8.戴昌钧,冯惠玲.竞争与对策.上海:学林出版社,1990
9.郭雷,许晓鸣.复杂网络.上海:上海科技教育出版社,2006
10.汪小帆,李翔,陈关荣.复杂网络理论及其应用.北京:清华大学出版社,2006
11.George Johnson.First cells,then species,now the web.United States:The New York Times Company,2000.http://www.nytimes.com/2000/12/26/science/26WEBS.html?pagewanted=all.
12.Waxman BM.Routing of multipoint connections.IEEE Journal on selected areas in communications.1988,6(9):1617-1622
13.Doar M B.A better model for generating test networks.In:Proc.of the GLOBECOM'96.London:IEEE,1996:86-93
14.Zegura E W,Calvert K L,Donahoo M J.A quantitative comparison of graph-based models for Internet topology.IEEE/ACM Trans.on Networking,1997,5(6):770-783
15.Albert-Laszlo Barabasi,Reka Albert,Hawoong Jeong.Scale-free characteristics of random networks:the topology of the world-wide web.Physica A,2000,281:69-77
16.Faloutsos M,Faloutsos P,Faloutsos C.On power-law relationships of the Internet topology.Proceedings SIGCOMM'99.United States:ACM Press,1999,29(4):251-262.
17.Adamic L,Huberman B.Power-law distribution of the world-wide web.Science,2000,287(24):2115
18.Newman M E J.Models of the small world.Stat Phys,2000,101:819-841
19.Reka Albert,Hawoong Jeong,Albert-Laszlo Barabasi.Diameter of the world-wide web.Nature,1999,401:130-131
20.Adamic L.The small world web.European Conference on Digital Libraries.France:Springer,1999:443-454
21.Albert-Laszlo Barabasi,Reka Albert.Emergence of scaling in random networks.Science,1999,286:509-512
22.王林,戴冠中,覃森.Internet的一种新的动态演化模型.系统工程理论与实践,2006,26(10):102-106
23.Krapivsky P L,Redner S.A statistical physics perspective on web growth.Computer Networks,2002,39:261-276
24.Dorogovtsev S N,Mendes J F F,Samukhin A N.Structure of growing networks with preferential linking.Phys Rev Lett,2000,85(21):4633-4636
25.Dorogovtsev S N,Mendes J F F.Evolution of networks with aging of sites.Phys Rev E,2000,62(2):1842-1845
26.Reka Albert,Albert-Laszlo Barabasi.Topology of evolving networks:Local events and universality.Phys Rev Lett,2000,85(24):5234-5237
27.Ginestra Bianconi,Albert-Laszlo Barabasi.Bose-Einstein condensation in complex networks.Phys Rev Lett,2001,86(24):5632-5635
28.Wang Wenxu,Wang Binghong,Bo Hu,et al.General dynamics of topology and traffic on weighted technological networks.Phys Rev Lett,2005,94:188702
29.Leland W,Taqqu M,Willinger W,et al.On the self-similar nature of Ethernet traffic.IEEE/ACM Transactions on Networking,1994,2(1):1-15
30.Willinger W,Taqqu M S,Sherman R.Self-similarity through high-variability:statistical analysis of Ethemet LAN traffic at source level.ACM Computer Communication Review,1995,25(4):100-113
31.袁坚,任勇,刘锋,等.复杂计算机网络中的相变和整体关联行为.物理学报,2001,50(7):1221-1225
32.刘锋,任勇,山秀明.互联网络数据报传输的一种简单元胞自动机模型.物理学报,2002,51(06):1175-1180
33.Tretyakov A Y,Takayasu H,and Takayasu M.Phase transition in a computer network model.PhysicaA,1998,253(1):315-322
34.Ohira T,Sawatari R.Phase transition in a computer network traffic model.Phys.Rev.E.1998,58(1):193-195
35.白刚,隆克平,程时端.Internet中的相变现象及一种新的相变业务流模型.电子学报,2002,30(2):191-195
36.Lawniczak A T,Gerisch A,and Maxie K.Effects of randomly added links on a phase transition in data network traffic models.Proceedings of DCDIS,2003.384-389
37.Takayasu M,Fukuda K,and Takayasu H.Application of statistical physics to the Internet traffics.PhysicaA,1999,274(1):140-148
38.KONHEIM A G.Descendent set:an efficient approach for analysis of polling systems.IEEE Transaction on Communication,1994,42(8):1245-1253
39.王智,于海斌,宋叶琼,等.混合服务方式下的M_1+M_2/G/1轮询系统的平均运行周期.通信学报,2002,23(7):8-18
40.逯昭义,罗秀秀.综合业务城域网IEEE802.5预约级协议改进策略.电子与信息学报,2002,24(11):1581-1588
41.逯昭义.计算机网络体系结构.清华大学出版社、北京交通大学出版社,2003:115-126
42.陆文彦,贾维嘉,杜文峰等.IEEE802.16竞争解决方案的性能分析.软件学报,2007,18(9):2259-2270
43.王忠锋,于海斌,王宏等.工业以太网实时通信中的调度表构建策略研究.信息与控制,2007,36(3):261-265
44.逯昭义,齐藤忠夫.同时多重接续星形LAN中心节的构成.通信学报,9(3):79-82
45.逯昭义,王思明.同时多重接续星形LAN的改进模式.科学通报,1989,(22):1749-1752
46.Lu Zhaoyi,Saito T.Star Type Local Area Network Access Control.Science in China,1990,33(a):1123-1131.
47.逯昭义,齐藤忠夫.改进型多星LAN.电子学报,1993,21(11):99-103
48.逯昭义.竞争-冲突淘汰存取方式Ⅰ类系统模型性能评价.电子学报,1995,23(9):115-117
49.逯昭义,陈永义,张建树.竞争-冲突淘汰存取方式的数学模型.电子科学学刊,1996,18(6):607-611
50.Lu Z,Sun L.Mathematical model for access mode of contention-collision cancellation in a star LAN.Journal of Electronics,2004,21(1):37-47.
51.Lu Z,Lu M,Zhao D,et al.On the Ⅱnd model of contention-collision elimination access mode in star LAN.Applied Math.Modelling,2003,27(11):899-911
52.Lu Z,et al.A special random selective services queuing model for access to a star LAN[J].Applied Math.Modelling,1997,21:15-20
53.Lu Z,Sun L,Lu M,et al.The mathematical modeling for the Contention-Collision Elimination access mode of the Ⅳth system model to a multiple star LAN.Applied Math.Modelling,30(44):367-385
54.Lu Z,Zhang J,Lu M.The mathematical modelling for the access mode of the Ⅴth System Model to a Multiple Star LAN.Applied Math.Modelling,1999,23:231-239
55.逯昭义,杨兴梅,王超.竞争—冲突淘汰存取方式Ⅵ类系统模型建模研究.电子学报,2007,35(10):1817-1822
56.刘海光,逯昭义,崔杰.重负载下双星LAN的一种数学模型的探讨.中国科学(E辑),2007,37(6):813-823
57.Stevens.TCP Slow Start,Congestion Avoidance,Fast Retransmit,and Fast Recovery Algorithms. RFC 2001,Jan.1997
58.Stiliadis D,Varma A.Rate-proportional servers:a design methodology for fair qurueing algorithms.IEEE/ACM Transactions on networking,1998,6(2):164-174
59.王重钢,隆克平,龚向阳,程时端.分组交换网络中队列调度算法的研究及其展望.电子学报,2001,29(4):553-559
60.Chow H,Leon-Garcia A.A Feedback Control Extension to Differentiated Services,Internet Draft,March 1999,http://bgp.potaroo.net/ietf/all-ids/draft-chow-diffserv-fbctrl-00.txt
61.Kalyanaraman S,Harrison D,Arora S,et al.A One-bit Feedback Enhanced Differentiated Services Architecture.Internet Draft,March 1998,http://bgp.potaroo.net/ietf/all-ids/draft-shivkuma-ecn-diffserv-00.txt
62.Sally Folyd,Van Jacobson.Random Early Detection Gateways for Congestion Control,IEEE/ACM Transactions on Networking,1993,1(4):397-413
63.Feng W,Kandlur D,Saha D,et al.A Self-Configuring RED gateway.In Proceedings of INFOCOM'99.New York:IEEE communications society,1999:1320-1328
64.Ott T J,Lakshman T V,Wong L H.SRED:Stabilized RED.In Proceedings of INFOCOM'99.New York:IEEE communications society,1999:1346-1355
65.Feng W,Kandlur D,Saha D,et al.Blue:A New Class of Active Queue Management Algorithms.IEEE INFOCOM 2001.Anchorage,Alaska,2001:1520-1529]
66.Yoo S J B,Bansal Y,Pan Z,et al.Optical-Label based packet routing system with contention resolution in wavelength,time and space domains.Technical Digest,OFC 2002,Anaheim,California,March,2002
67.Kim S,Kim N,Kang M.Contention resolution for optical burst switching networks using alternative routing.Communications,2002,5:2678-2681
68.Yao S,Mukherjee B,Yoo S J B.A unified study of contention-resolution schemes in optical packet-switched networks.Lightwave Technology,2003,21(3):672-683
69.Gauger C M,Kohn M,and ScharfJ.Comparison of contention resolution strategies in OBS network scenarios.Transparent Optical Networks,2004,1(1):18-21
70.张丽娟,李维民,张淳民等.一种用于解决OBS网中资源竞争的新机制.光通信研究,2006,6:8-10
71.张正江,王汝言.光突发交换竞争解决机制研究.微计算机信息,2006,22(12):154-157
72.许光辉.随机服务系统.北京:科学出版社,1980
73.华兴.排队论与随机服务系统.上海:上海翻译出版公司,1987
74.唐应辉,唐小我.排队论基础与分析技术.北京:科学出版社,2006
75.罗荣桂.排队模型及其应用.武汉:华中理工大学出版社,1990
76.盛友招.排队论及其在计算机通信中的应用.北京:北京邮电大学出版社,1998
77.逯昭义,王思明.计算机通信网络信息量理论.电子工业出版社.1997
78.Casettv C,Meo M.An analytical framework for the performance evaluation ofTCP Reno connections.Computer Networks.2001,37(5):669-682
79.Altman E,Avrachenkov K,Barakat C,et al.State-dependent M/G/1 type queueing analysis for congestion control in data networks.Computer Networks.2002,39(6):789-808
80.Brown T X,Gabow N H.The limits of input-queued switch performance with future packet arrival information.Computer Networks.2003,42(4):441-460
81.Yook SH,Joong H,Barabasi A L,Modeling the Internet's large-scale topology,Proceedings of the National Academy of Science of the United State of America,2002,99(21):13382-13386
82.Hart J.Conquering complexity:data networking trends as technology meets market reality.In Proceedings of LCN'01.USA:2001:4-17
83.Dai D,Panda D K.How much does network contention affect distributed shared memory performance? USA:ICPP'97
84.Steffenel L A.Modelling network contention effects on all-to-all operations.IEEE Internation Conference on Cluster Computing 2006:1-10
85.Moritz C A,Frank M I.LoGPC:Modeling Network Contention in Message-Passing Programs.IEEE transactions on parallel and distributed systems,2001,12(4):404-415
86.Andrews M,Awerbuch B,Fernandez A,et al.Universal-stability results and performance bounds for greedy contention-resolution protocols.Journal of the ACM,2001,48(1):39-69
87.Gao F,Zhao D.Improved Ternary-tree Algorithm for Contention Resolution over Random Multi-access Channel.Journal of china universities of posts and telecommunications.2001,8(2):35-39
88.何丽红,景方,杜德生等.复杂适应系统中合作与竞争关系的涌现.哈尔滨理工大学学报,2003,8(4):75-78
89.徐恪,吴建平,徐明伟.高等计算机网络—体系结构、协议机制、算法设计与路由器技术.北京:机械工业出版社,2003
90.Thareja A K,Agrawala A K.On the Design of Optimal Policy for Sharing Finite Buffers.IEEE Transactions on Communications,1984,32(6):737-740
91.Choudhury A K,Hahne E L.Dynamic Queue Length Thresholds for Shared-Memory Packet Switches.IEEE/ACM Transactions on Networking,1998,6(2):130-140
92.Hahne E L,Choudhury A K.Dynamic Queue Length Thresholds for Multiple Loss Priorities.IEEE/ACM Transactions on Networking,2002,10(3):368-380.
93.Agharebparast F,Leung V C M.Improving the performance of RED deployment on a class based queue with shared buffer.Proc.of IEEE Globecom'01.San Antonio,TX,USA:2001:2363-2367.
94.Hu C,Liu B.RED with optimized dynamic threshold deployment on shared buffer.Fukuoka,Japan:AINA,2004,(2):451-454.
95.Lin D,Morris R.Dynamics of Random Early Detection.Proc.of ACM SIGCOMM.New York:ACM Press,1997:127-137.
96.NS Project.http://nsnam.isi.edu/nsnam.
97.于斌,孙斌,温暖等.NS2与网络模拟.北京:人民邮电出版社,2007
98.Floyd S.RED:Discussions of setting parameters,http://www.icir.org/floyd/red.html
99.Pappu S K.Simulating computer systems.Potentials,IEEE,1997,16(1):16-18
100.孙屹.OPNET通信仿真开发手册.北京:国防工业出版社,2005.
101.李馨,叶明.OPNET Modeler网络建模与仿真.西安:西安电子科技大学出版社,2006
102.李信真,车刚明等.《计算方法》.西安:西北工业大学出版社,2000年