IP网多路径数据传输关键技术研究
|
摘要
互联网作为全球最大的通信基础设施，已成为国家进步和社会发展的重要支柱。随着各种新兴业务和应用的不断涌现，对网络的带宽提供能力和服务质量保障能力提出了更高要求。现有网络普遍采用单下一跳最优路径进行数据传输，而这种基于单下一跳路由的尽力而为数据传送方式正是造成当前网络资源使用不均衡和局部拥塞的重要根源。多路径并行数据传输可以有效聚合使用多条路径的带宽，均衡网络流量，提高网络的可用性和生存性，从而有效提升网络的服务质量。
本课题依托国家863计划“快速自愈路由协议与试验系统”、“一种基于节点势能导向的多路由产生机制”和“一种基于多下一跳路由的动态均衡路由交换机制”，通过对IP网多路径数据传输的研究实现多下一跳数据的并行转发，从而充分使用现有网络带宽资源，达到网络流量的负载均衡，最大程度的减少网络拥塞的产生。课题围绕“寻找路径、选择路径和使用路径”三方面展开研究，重点研究了多路由产生机制，多路径网络的流量工程模型，多路径网络的流量控制算法和基于业务区分的多路径网络资源分配算法，并力图将研究成果有机整合，形成多路径网络数据传输的整体解决方案。具体而言，论文的主要研究成果包含了以下几个方面：
1、多路由生成是网络进行多路径数据传输的基础和前提，提出了基于节点位势的多路由生成算法框架NPMA，该算法框架指出多路由生成就等价于将网络图转换为有向无环图，而通过给网络节点赋不同的位势值可以实现有向无环图的转换。在此算法思想下，提出了NPMA-Dijkstra和NPMA-MCS两个多路由生成算法。NPMA-Dijkstra算法是基于最短路径算法扩展而来，方便于在当前的路由器中部署实现；NPMA-MCS算法可以提供节点对间的最大流传输，能够在路由层面上为提升网络的数据传输性能提供帮助。通过和现有的商用MDVA算法仿真对比，表明所提算法在多路由生成数目和并行传输能力上都比MDVA算法有所提升，可以充分挖掘使用网络的链路资源。
2、在多路由生成的基础上，研究了多路径网络的流量工程模型。针对每个路由节点进行多下一跳转发的特点，提出了一个最小化最大链路利用率的线性规划模型MM-TE，分析了模型的性能。针对模型在个别节点上没有进行流量分割的现象，提出了一个改进的流量工程模型MM-TE+，模型同时约束了对跳数过多路径的选取。通过在实际网络拓扑上的仿真实验，表明模型MM-TE+可以很好的和多路由生成算法配合使用，能够有效均衡网络链路的资源利用率。
3、从网络用户角度考虑了多路径网络的拥塞控制问题，提出了多路径网络的流量控制算法。在网络效用最大化的理论框架下，将单路径的流量控制算法扩展到了多路径网络中，针对多路径网络中效用最大化目标不是一个严格的凸函数问题，修正了效用最大化的目标函数，保证了对偶问题的处处可微，提出了一个包含源端和链路端的流量控制算法，理论分析和仿真实验验证了算法的收敛性。针对流量工程和流量控制相分离的研究现状，提出了一个联合优化的模型，从跨层优化的角度提出了一个防止网络拥塞的算法，仿真实验表明算法收敛时间短，可以优化网络的链路利用率。
4、针对“三网融合”演进中互联网需要进行多业务承载的问题，结合目前网络中实时多媒体业务迅猛发展的现状，提出了多路径网络的资源优化分配算法。通过分析不同业务效用函数的特点，将网络中的业务区分为弹性业务、软实时非弹性业务和硬实时非弹性业务。首先提出了弹性业务的资源优化分配算法，通过引入多路径聚合等效带宽的概念，分析得到了非弹性业务的资源最优分配的充分条件和多业务共存时资源最优分配的充分条件。针对多业务共存时资源分配的非凸优化本质，提出了一个基于罚函数的遗传优化算法。仿真实验表明，算法收敛快，可以得到各种业务共存条件下资源分配的优化解。
5、针对863项目“快速自愈路由协议和试验系统”的工程实现要求，设计并实现了一个支持多下一跳路由查找的转发引擎，转发引擎主要包含了一个支持多下一跳路由的三级转发表查找结构、基于流保序的多下一跳均衡转发处理模块和一个基于FPGA实现的128位并行CRC32哈希算法。针对每一个模块进行了详细的电路设计和性能分析，实现了基于ATCA架构的转发引擎电路板。通过商用的Spirent Testcenter测试仪器对转发引擎进行了测试，结果表明引擎的丢包率、处理时延和均衡保序性能指标都达到了10Gbps处理能力的设计预期。
As a foundation of building unified IP carrying and operational platform, the routing andswitching equipment must meet the rapid expansion of information capacity and the diversiformrequirements of network traffic to establish a stable and fundamental basis for NationalInformation Infrastructure (NII). However, with the network scales rapidly and new networkapplications emerge frequently, bandwidth supply for today’s Internet could not catch up with therapid increasing requirements. Unfortunately, irrational using of network sources makes thingsworse. Actual network deploys single-next-hop optimization paths for data transmission, butsuch “best effort” model leads to the imbalance use of network resources and usually leads tolocal congestion. On the other hand Multi-path routing can use the aggregation bandwidth ofmulti paths efficiently and improve the robustness of network, security, load balancing andquality of service. As a result, multi-path has attracted much attention in the routing andswitching research fields and many important ideas and solutions have been proposed.
Combined with the research on “Fast Self-Recovery Routing Protocol and ExperimentSystem”,“a Multi-Next Hop Routing Mechanism Based on Node Potential” and “A Multi-Next-hop Based Dynamical Load Balanced Routing and Switching”, this dissertation focuses onimplementing the parallel transmission of multi next-hop data,balancing the network traffic andreducing the congestion. In short, the contents of this dissertation can be included as follows:
1. Multi-routing generation is the basis and premise of the multi-path data transmission innetwork. This paper proposes a framework of multi-routing generation algorithm based on nodepotential, which pointed out that the multi-route generation is equal to convert the networkdiagram to a directed acyclic graph. Under the framework of this algorithm, two algorithms areproposed, that are NPMA-Dijkstra which based on Dijkstra algorithm and NPMA-MCSalgorithm which based on minimum cost sum algorithm. It is easy for NPMA-Dijkstra algorithmto deploy.And NPMA-MCS algorithm can improve the performance of data transmissionbetween nodes on the routing level. Compared with commercial mature MDVA algorithm, thealgorithms proposed in this paper improves the number of multi next hops and paralleltransmission capacity.So, the algorithms can make fully use of the network link resources.
2. Based on multi-routing generation, the multi-path network traffic engineering model isinvestigated. According to the characteristics of multi next hops transmission, this paperproposes a linear programming model MM-TE with the main idea of minimizing maximum linkutilization and analyzed the performance. As there is no traffic division for the model on someindividual nodes, improved traffic engineering model MM-TE+is proposed. MM-TE+modelconstrains the selection of the paths with excessive number of hops. Simulation on the actualnetwork topology shows that the MM-TE+model can cooperate with multi-routing generationalgorithm very well, and can effectively balance network link resource utilization.
3. From the perspective of network users, network congestion control problem in multi-pathnetwork is considered. Researching on multi-path network flow control algorithm under thetheoretical framework of network utility maximization, this paper extends the single-path flow control algorithm to multi-path network. Considering the problem of multi-path network utilitymaximization which is not a strictly convex function, it revises the objective function of theutility maximization, therefore it ensures the differential coefficient of dual problem.It also offersa source end and link end flow control algorithm and verifies the convergence of the algorithmby theoretical analysis and simulation. As traffic engineering and traffic control are separated, anoptimization model and algorithm to prevent network congestion from the perspective ofcross-layer is proposed. Experiments show that the algorithm can improve the throughput andthe load balancing performance of the network.
4. According to the multi-services carrying problems in the evolution of network, optimizedresource allocation algorithm in multi-path network is analyzed. By analyzing the characteristicof each service’s utility function, we divide the services in network into elastic service, softreal-time inelastic service and hard real-time inelastic service, and bring forward a resourceallocation algorithm of elastic service.By introducing the concept of equivalent bandwidth inmulti-path aggregation, the sufficient condition of optimized resource allocation of inelasticservice and multi-service co-existed can be gained. Based on the non-convex optimizationspeciality of resource allocation when multi-service co-existed, a genetic algorithm based onpenalty function is proposed. The results of simulations show that the algorithm converges fastand can get the optimization solution of resource allocation in multi-service co-existingconditions.
5. To satisfy the engineering requirement of the863project “Fast Self-Recovery RoutingProtocol and Experiment System”, a forwarding engine that supports multi-next hop routing isdesigned and implemented. The forwarding engine mainly consists of searching structure withthree levels forwarding, multi-next hop routing result processing module based on keepingin-order forwarding, and a128bits parallel CRC32hash algorithm based on FPGA. After adetailed circuit design and performance analysis for each module, the forwarding engine PCBboard based on ATCA architecture is implemented. Testing with the commercial SpirentTestCenter instrument the performance of the engine shows that the packet loss rate, theprocessing delay and balancing performance satisfy the requirements of10Gbps processingcapacity.
本课题依托国家863计划“快速自愈路由协议与试验系统”、“一种基于节点势能导向的多路由产生机制”和“一种基于多下一跳路由的动态均衡路由交换机制”，通过对IP网多路径数据传输的研究实现多下一跳数据的并行转发，从而充分使用现有网络带宽资源，达到网络流量的负载均衡，最大程度的减少网络拥塞的产生。课题围绕“寻找路径、选择路径和使用路径”三方面展开研究，重点研究了多路由产生机制，多路径网络的流量工程模型，多路径网络的流量控制算法和基于业务区分的多路径网络资源分配算法，并力图将研究成果有机整合，形成多路径网络数据传输的整体解决方案。具体而言，论文的主要研究成果包含了以下几个方面：
1、多路由生成是网络进行多路径数据传输的基础和前提，提出了基于节点位势的多路由生成算法框架NPMA，该算法框架指出多路由生成就等价于将网络图转换为有向无环图，而通过给网络节点赋不同的位势值可以实现有向无环图的转换。在此算法思想下，提出了NPMA-Dijkstra和NPMA-MCS两个多路由生成算法。NPMA-Dijkstra算法是基于最短路径算法扩展而来，方便于在当前的路由器中部署实现；NPMA-MCS算法可以提供节点对间的最大流传输，能够在路由层面上为提升网络的数据传输性能提供帮助。通过和现有的商用MDVA算法仿真对比，表明所提算法在多路由生成数目和并行传输能力上都比MDVA算法有所提升，可以充分挖掘使用网络的链路资源。
2、在多路由生成的基础上，研究了多路径网络的流量工程模型。针对每个路由节点进行多下一跳转发的特点，提出了一个最小化最大链路利用率的线性规划模型MM-TE，分析了模型的性能。针对模型在个别节点上没有进行流量分割的现象，提出了一个改进的流量工程模型MM-TE+，模型同时约束了对跳数过多路径的选取。通过在实际网络拓扑上的仿真实验，表明模型MM-TE+可以很好的和多路由生成算法配合使用，能够有效均衡网络链路的资源利用率。
3、从网络用户角度考虑了多路径网络的拥塞控制问题，提出了多路径网络的流量控制算法。在网络效用最大化的理论框架下，将单路径的流量控制算法扩展到了多路径网络中，针对多路径网络中效用最大化目标不是一个严格的凸函数问题，修正了效用最大化的目标函数，保证了对偶问题的处处可微，提出了一个包含源端和链路端的流量控制算法，理论分析和仿真实验验证了算法的收敛性。针对流量工程和流量控制相分离的研究现状，提出了一个联合优化的模型，从跨层优化的角度提出了一个防止网络拥塞的算法，仿真实验表明算法收敛时间短，可以优化网络的链路利用率。
4、针对“三网融合”演进中互联网需要进行多业务承载的问题，结合目前网络中实时多媒体业务迅猛发展的现状，提出了多路径网络的资源优化分配算法。通过分析不同业务效用函数的特点，将网络中的业务区分为弹性业务、软实时非弹性业务和硬实时非弹性业务。首先提出了弹性业务的资源优化分配算法，通过引入多路径聚合等效带宽的概念，分析得到了非弹性业务的资源最优分配的充分条件和多业务共存时资源最优分配的充分条件。针对多业务共存时资源分配的非凸优化本质，提出了一个基于罚函数的遗传优化算法。仿真实验表明，算法收敛快，可以得到各种业务共存条件下资源分配的优化解。
5、针对863项目“快速自愈路由协议和试验系统”的工程实现要求，设计并实现了一个支持多下一跳路由查找的转发引擎，转发引擎主要包含了一个支持多下一跳路由的三级转发表查找结构、基于流保序的多下一跳均衡转发处理模块和一个基于FPGA实现的128位并行CRC32哈希算法。针对每一个模块进行了详细的电路设计和性能分析，实现了基于ATCA架构的转发引擎电路板。通过商用的Spirent Testcenter测试仪器对转发引擎进行了测试，结果表明引擎的丢包率、处理时延和均衡保序性能指标都达到了10Gbps处理能力的设计预期。
As a foundation of building unified IP carrying and operational platform, the routing andswitching equipment must meet the rapid expansion of information capacity and the diversiformrequirements of network traffic to establish a stable and fundamental basis for NationalInformation Infrastructure (NII). However, with the network scales rapidly and new networkapplications emerge frequently, bandwidth supply for today’s Internet could not catch up with therapid increasing requirements. Unfortunately, irrational using of network sources makes thingsworse. Actual network deploys single-next-hop optimization paths for data transmission, butsuch “best effort” model leads to the imbalance use of network resources and usually leads tolocal congestion. On the other hand Multi-path routing can use the aggregation bandwidth ofmulti paths efficiently and improve the robustness of network, security, load balancing andquality of service. As a result, multi-path has attracted much attention in the routing andswitching research fields and many important ideas and solutions have been proposed.
Combined with the research on “Fast Self-Recovery Routing Protocol and ExperimentSystem”,“a Multi-Next Hop Routing Mechanism Based on Node Potential” and “A Multi-Next-hop Based Dynamical Load Balanced Routing and Switching”, this dissertation focuses onimplementing the parallel transmission of multi next-hop data,balancing the network traffic andreducing the congestion. In short, the contents of this dissertation can be included as follows:
1. Multi-routing generation is the basis and premise of the multi-path data transmission innetwork. This paper proposes a framework of multi-routing generation algorithm based on nodepotential, which pointed out that the multi-route generation is equal to convert the networkdiagram to a directed acyclic graph. Under the framework of this algorithm, two algorithms areproposed, that are NPMA-Dijkstra which based on Dijkstra algorithm and NPMA-MCSalgorithm which based on minimum cost sum algorithm. It is easy for NPMA-Dijkstra algorithmto deploy.And NPMA-MCS algorithm can improve the performance of data transmissionbetween nodes on the routing level. Compared with commercial mature MDVA algorithm, thealgorithms proposed in this paper improves the number of multi next hops and paralleltransmission capacity.So, the algorithms can make fully use of the network link resources.
2. Based on multi-routing generation, the multi-path network traffic engineering model isinvestigated. According to the characteristics of multi next hops transmission, this paperproposes a linear programming model MM-TE with the main idea of minimizing maximum linkutilization and analyzed the performance. As there is no traffic division for the model on someindividual nodes, improved traffic engineering model MM-TE+is proposed. MM-TE+modelconstrains the selection of the paths with excessive number of hops. Simulation on the actualnetwork topology shows that the MM-TE+model can cooperate with multi-routing generationalgorithm very well, and can effectively balance network link resource utilization.
3. From the perspective of network users, network congestion control problem in multi-pathnetwork is considered. Researching on multi-path network flow control algorithm under thetheoretical framework of network utility maximization, this paper extends the single-path flow control algorithm to multi-path network. Considering the problem of multi-path network utilitymaximization which is not a strictly convex function, it revises the objective function of theutility maximization, therefore it ensures the differential coefficient of dual problem.It also offersa source end and link end flow control algorithm and verifies the convergence of the algorithmby theoretical analysis and simulation. As traffic engineering and traffic control are separated, anoptimization model and algorithm to prevent network congestion from the perspective ofcross-layer is proposed. Experiments show that the algorithm can improve the throughput andthe load balancing performance of the network.
4. According to the multi-services carrying problems in the evolution of network, optimizedresource allocation algorithm in multi-path network is analyzed. By analyzing the characteristicof each service’s utility function, we divide the services in network into elastic service, softreal-time inelastic service and hard real-time inelastic service, and bring forward a resourceallocation algorithm of elastic service.By introducing the concept of equivalent bandwidth inmulti-path aggregation, the sufficient condition of optimized resource allocation of inelasticservice and multi-service co-existed can be gained. Based on the non-convex optimizationspeciality of resource allocation when multi-service co-existed, a genetic algorithm based onpenalty function is proposed. The results of simulations show that the algorithm converges fastand can get the optimization solution of resource allocation in multi-service co-existingconditions.
5. To satisfy the engineering requirement of the863project “Fast Self-Recovery RoutingProtocol and Experiment System”, a forwarding engine that supports multi-next hop routing isdesigned and implemented. The forwarding engine mainly consists of searching structure withthree levels forwarding, multi-next hop routing result processing module based on keepingin-order forwarding, and a128bits parallel CRC32hash algorithm based on FPGA. After adetailed circuit design and performance analysis for each module, the forwarding engine PCBboard based on ATCA architecture is implemented. Testing with the commercial SpirentTestCenter instrument the performance of the engine shows that the packet loss rate, theprocessing delay and balancing performance satisfy the requirements of10Gbps processingcapacity.
引文
[1] Internet World Stats[EB/OL]. http://www.internetworldstats.com/stats.htm.2011.
[2]中国互联网信息中心(CNNIC).第29次中国互联网络发展状况统计报告[EB/OL].http://www.cnnic.cn,2012.
[3] High Speed Broadband Services Demand Side Study [EB/OL].http://www.comcom.govt.nz/.
[4]黄孝建,陶蒙华． IPTV关键技术详解[M].北京:北京邮电大学出版社,2009:15-25.
[5] RFC2328. OSPF version2[S]. IETF,1988.
[6] RFC1195. Use of OSI IS-IS for Routing in TCP/IP and Dual Environments[S]. IETF,1990.
[7] Uhlig S, Quoitin B, Lepropre J, etal. Providing Public Intradomain Traffic Matrices to theResearch Community[J]. ACM SIGCOMM Computer Communication Review,2006,36(1):83-86.
[8]中华人民共和国国务院.推进三网融合总体方案[EB/OL]:三网融合12个试点城市名单和试点方案.
[9] Haim Zlatokrilov. Packet Dispersion and the Quality of Voice over IP Applications in IPnetworks[A]. In Proceedings of IEEE INFOCOM2004[C], Hong Kong, IEEE Press,2004:576-590.
[10]兰巨龙.国家高技术研究发展计划（863计划）课题申请书“快速自愈路由协议与试验系统”[R].郑州:解放军信息工程大学,2007-5-22.
[11]朱宣勇.国家高技术研究发展计划（863计划）课题申请书“一种基于节点势能导向的多路由产生机制”[R].郑州：解放军信息工程大学,2007.
[12]伊鹏.国家高技术研究发展计划（863计划）课题申请书“一种基于多下一跳路由的动态均衡路由交换机制”[R].郑州：解放军信息工程大学,2007.
[13] RFC2992. Analysis of an Equal-Cost Multi-Path Algorithm[S]. IETF.2002.
[14] T. Guven, C. Kommareddy, R. J. La, M. A. Shayman, and B. Bhattacharjee. Measurementbased optimal multi-path routing[A]. In Proceedings of IEEE INFOCOM2004[C], HongKong, IEEE Press,2004:187-196.
[15] P. Narvaez, K. Y. Siu. Efficient Algorithms for Multi-Path Link State Routing[C].ISCOM'99, Kaohsiung, Taiwan,1999.
[16] H. S. Palakurthi. Study of Multipath Routing for QoS Provisioning[J].EECS803-Introduction to Research, October5,2001:1-6.
[17] W. T. Zaumen and J.J. Garcia-Luna-Aceves. Loop-Free Multipath Routing UsingGeneralized Diffusing Computations. Proc. IEEE INFOCOM, March1998.
[18] S. Vutukury, J.J. Garcia-Luna-Aceves. A Simple Approximation to Minimum DelayRouting [A]. In Proceedings of ACM SIGCOMM[C].Cambridge, Massachusetts, USA,1999.
[19] Srinivas Vutukury, J.J. Garcia-Luna-Aceves. MDVA: A Distance-Vector Multipath RoutingProtocol [A]. In Proceedings of the INFOCOM2001[C],20th Annual Joint Conference ofthe IEEE Computer and Communications Societies[C], Anchorage, USA,2001.
[20] S. Vutukury and J.J. Garcia-Luna-Aceves. A Distributed Algorithm for MultipathComputation using Distance-Vectors with Predecessor Information[A]. In Proceedings ofGLOBECOM (Global Telecommunications Conference)[C], Volume3, IEEE Press,1999:1689-1693.
[21] S. Vutukury. Multipath Routing Mechanisms for Traffic Engineering and Quality ofService in the Internet[D]. PhD Thesis, Department of Computer Science, University ofCalifornia, Santa Cruz.2001.
[22] J.J. Garcia-Luna-Aceves. Loop-Free Routing Using Diffusing Computations[J].IEEE/ACM Transactions on Networking, February1993,1(1):130–141.
[23]陈文平.多下一跳快速自愈路由技术研究[D].解放军信息工程大学硕士学位论文,2009.6.
[24]张建辉.节点势能导向多下一跳路由协议研究与性能评价[D].解放军信息工程大学博士学位论文,2009.6.
[25] M.zhang, J.Lai, A.Krishnamurthy, L.Peterson, R.Wang. A transport layer approach forimproving end-to-end performance and robustness using redundant paths[A]. InProc.USENIX Annual Technical Conference[C]. Boston, USA,2004:99-112.
[26] A.Ford, C.Raiciu, S.Barre, J.Iyengar. Architectural guidelines for multipath TCPdevelopment, draft-ietf-mptcp-architecture-00[S].IETF,2010.
[27] H.Y.Hsieh, R.Sivakumar. A transport layer approach for achieving aggregate bandwidthson multi-homed mobile hosts[J]. Wireless Network,2005,11(1-2):99-114.
[28] RFC2960. Stream Control Transmission Protocol(SCTP)[S],IETF,2000.
[29] A.A.E.Al, T.Saadawi, M.Lee. LS-SCTP: a bandwidth aggregation technique for StreamControl Transmission Protocol[J]. Computer Communications,2004,27(10):1012-1024.
[30] A. E. Al, T.Saadawi, M.Lee. A transport layer load-sharing mechanism for mobile wirelesshosts[A]. In Proc.of the IEEE Annual Conference On Pervasive Computing andCommunications Workshops(PERCOMW)[C].Orlando,IEEE Press,2004:87-91.
[31] RFC3272. Overview and principles of Internet traffic engineering[S]. IETF,2010.
[32] Fortz B, Thorup M. Internet Traffic Engineering by Optimizing OSPF Weights[A]. InProceedings of IEEE INFOCOM[C],2000:519-528.
[33] Fortz B, Thorup M. Optimizing OSPF/IS-IS Weights in a Changing World[J]. IEEEJournal On Selected Areas In Communications,2002-5,20(4):756-767.
[34] Y.Wang,Z. Wang, and L. Zhang. Internet traffic engineering without full-meshoverlaying[A]. In Proceedings of INFOCOM2001[C], Apr.2001:565-571.
[35] S. Kandula, D. Katabi, B. Davie. Walking the Tightrope: Responsive yet Stable TrafficEngineering[A]. In Proceedings of SIGCOMM2005[C], Philadelphla, PA: ACM,2005:253-264.
[36] J. He, M. Chiang, and J. Rexford. DATE: Distributed Adaptive Traffic Engineering[A].InPoster session at INFOCOM2005[C] Miami, Florida, USA,2005:210-216.
[37] H. Wang, H. Xie, L. Qiu. Cope: Traffic engineering in dynamic networks[A]. InProceedings of the ACM SIGCOMM2006[C], Pisa, Italy: ACM,2006:99-110.
[38] D. H. Xu, M. Chiang, J. Rexford. DEFT: Distributed Exponentially-weighted FlowSplitting[A]. In Proceedings of the IEEE INFOCOM2007[C], Anchorage, AK, USA:IEEE, May2007:71-79.
[39] D. H. Xu, M. Chiang, J. Rexford. Link-State Routing with Hop-by-Hop Forwarding canAchieve Optimal Traffic Engineering[A]. In Proceedings of the IEEE INFOCOM2008[C],Phoenix, AZ: IEEE,2008:466-474.
[40] Elwalid A, Jin C, Low S, and Widjaja I. MATE: MPLS Adaptive Traffic Engineering.Anchorage[A]. In Proceedings of IEEE INFOCOM2001[C], AK, USA, IEEE Press,2001:1300-1309.
[41] MATTHEW W,CARLYLE R,KEVIN W.Near Shortest and K shortest Simple Paths[J]，Networks,2005,46(2):98-109.
[42] Roughan M, Thorup M, Zhang Y. Traffic Engineering with Estimated Traffic Matrices[A].In Proceedings of ACM IMC[C], Miami Beach, FL, USA,2003:248-258.
[43] Skivée F, Balon S, Leduc G. A Scalable Heuristic for Hybrid IGP/MPLS TrafficEngineering-Case Study on an Operational Network[A]. In Proceedings of IEEE ICON[C].Singapore, IEEE Press,2006:572-577.
[44] Pham H and Lavery B. Hybrid Routing for Scalable IP/MPLS Traffic Engineering[A]. InProceedings of IEEE ICC[C]. Anchorage, AK, USA, IEEE Press,2003:332-337.
[45] F. P. Kelly, A. Maulloo, D. Tan,. Rate control for communication networks: shadow prices,proportional fairness and stability[J].Operational Research Society,Mar.1998,49(3):237-252.
[46] M Chiang, S H Low, A R Calderbank and J C Doyle. Layering as optimizationdecomposition: A Mathematical theory of network architecture[A]. In Proceedings ofIEEE[C].2005,95(1):255-311.
[47] S. H. Low. A duality model of TCP and queue management algorithms[J]. IEEE/ACMTransactions on Networking, August2003,11(4):578-590.
[48] S. H. Low, D. E. Lapsley. Optimization flow control I: basic algorithm and convergence[J].IEEE/ACM Transactions on Networking, Dec1999,7(6):861-874.
[49] S. H. Low, L. Peterson, L. Wang. Understanding Vegas: A duality model[J].IEEE/ACMTransaction on Networking, August2003,11(4):525-536.
[50] Ao Tang, Krister Jacobsson, H Andrew, Steven H Low. An accurate link model and itsapplication to stability analysis of FAST TCP[A]. In Proceedings of IEEE INFOCOM2007[C], Anchorage, Alaska, May2007:1123-1135.
[51] L. H. Andrew, S. H. Low, B. P. Wydrowski. Understanding XCP:Equilibrium andfairness[J]. IEEE/ACM Transactions on Networking,2009,17(6):1697-1710.
[52] H. Han, S. Shakkottai, C. Hollot, R. Srikant, and D. Towsley. Overlay TCP for multi-pathrouting and congestion control[A]. In Proceedings of ENS-INRIA ARC-TCPWorkshop[C], Paris, France,2003:535-549.
[53] X. Lin and N. B. Shroff. Utility maximization for communication networks with multipathrouting[J].IEEE/ACM Transactions on Networking,2006,51(5):766-781.
[54] Wang J, Li Lt, Low S, et a1.Cross-Layer Optimization in TCP/IP Networks[J]. IEEE/ACMTransactions on Networking,2005,13(3):582-595.
[55] Key P, Massouli6L，Towsley D．Path Selection and Multipath Congestion Control[A]. InProceedings of IEEE INFOCOM2007[C], Anchorage, Alaska, May2007:143-151.
[56] T. Voice. Stability of multi-path dual congestion control algorithm[J]. IEEE/ACMTransactions on Networking,2007,15(6):1231-1239.
[57] J. Jin, W. H. Wang, M. Palaniswami. Utility max·min fair resource allocation forcommunieation networks with multipath routing[J]. Computer Communications,2009,32(17):1802-1809.
[58] Akon. M. M, Asaduzzaman. S, Rahman. Md. S. Proposal for st-Routing Protocol [J].Telecommunication Systems,2004,25(3-4):287-298.
[59] Y. Ohara, H. Kusumoto, O. Nakamura, and J. Murai. Drouting architecture: Improvementof failure avoidance capability using multipath routing[J]. IEICE Transactions,2008,91-B(5):1403-1415.
[60] Y. Ohara, Shinji Imahori, Rodney Van Meter. MARA: Maximum Alternative RoutingAlgorithm[A] In Proceedings of IEEE INFOCOM2009[C],2009:862-885.
[61] H. Nagamochi and T. Ibaraki. Computing edge-connectivity in multigraphs andcapacitated graphs[J]. SIAM J. Discret. Math,1992,5(1):54–66.
[62] H. Nagamochi and T. Ibaraki. Graph connectivity and its augmentation: applications ofMA orderings[J]. Discrete Appl. Math,2002,123(1-3):447–472.
[63] Z. Wang. On the complexity of quality of service routing[J]. Information Processing Leters,1999,69(3):111-114.
[64] Q.Ma.QoS Routing in the integrated services networks[D]. Ph.D.thesis. Carnegie MellonUniversity,1998.1.
[65] SSFNet1.5[EB/OL]. http://www.ssfnet.org/.
[66] BRITE Topology Generator [EB/OL]. http://www.cs.bu.edu/brite/.
[67] K. Ramakrishnan and M. Rodrigues. Optimal routing in shortest path data networks[J].Lucent Bell Labs Technical Journal,2001,6(1):772-785.
[68] A. Yuen T. Chung. Traffic Engineering for Multi-homed Mobile Networks[D]. AustraliaSydney: The university of new south wales sydney,2007.
[69]拉文德拉K.阿胡亚,托马斯L.马南提,詹姆斯B.沃林著,网络流:理论、算法及应用[M].北京:中国机械出版社,2005:337-385.
[70] G. Retvari and T Cinkler, Practical OSPF Trafic Engineering[J]. IEEE Communicationletter,2004,8(11):689-691.
[71] Zhang Y, Roughan M, Duffield N, et al. Fast Accurate Computation of Large-Scale IPTraffic Matrices from Link Loads[A]. In Proceedings of ACM SIGMETRICS2003[C],San Diego, CA, USA,2003:206-217.
[72] Zhang Y, Roughan M, Lund C, et al. Estimating Point-to-Point and Point-to-MultipointTraffic Matrices: An Information-Theoretic Approach[J]. IEEE/ACM Transactions onNetworks,2005,13(5):947-960.
[73] Abilene Backbone[EB/OL]. http://www.internet2.edu/network/.
[74] Zhang Y. Traffic Matrices of Abilene[EB/OL].http://www.cs.utexas.edu/~yzhang/research/AbileneTM,2009-11-29.
[75] The topology of internet2[EB/OL].http://globalnoc.iu.edu/uploads/tB/z8/tBz8316lo_75e-DSIfBIXg/IGP-Metrics.pdf,2010-03-05.
[76] China Education and Research Network[EB/OL]. http://www.edu.cn/english1369/index.shtml.2012-01-01.
[77] F. P. Kelly. Fairness and stability of end-to-end congestion control[J]. European Journal ofControl,2003,9(2-3):159-176.
[78] D.P.Bertsekas.Nonlinear Programming[M],2nded, Belmont, MA: Athena Scientific,1999.
[79] S. Boyd, L. Vandenberghe, Convex Optimization[M]. Cambridge, U.K.:CambridgeUniv.Press,2004.
[80] J. He, M. Bresler, M. Chiang, and J. Rexford. Rethinking Internet traffic management:From multiple decompositions to a practical protocol[A]. In Procedings of CoNEXT[C],December2007:1123-1145.
[81] J. He, M. Bresler, M. Chiang, and J. Rexford. Towards multi-layer traffic engineering:Optimization of congestion control and routing[J]. IEEE Journal on Selected Areas inCommunications, June2007:631-655.
[82] A. Mas-Colell, M. Whinston, J. Green. Microeconomic Theory[M].England: OxfordUniversity Press,1995.
[83] S. Kunniyur and R. Srikant. End-to-end congestion control schemes: utility function,random losses and ECN marks[A]. In Procedings of IEEE Infocom2000[C], vol.3,2000:1323-1332.
[84] Jeffrey M.Jaffe. Bottleneck flow control[J]. IEEE/ACM Transactionsons on Networking,Com-29(7), July1981:954-962.
[85] Howard Paul Hayden. Voice flow control in integrated Packet networks[M].Master Thesis,MIT Dept.of EECS, Cambridge MA,1981.
[86] D. Bersekas and R. Gallager. Data Networks[M]. Prentice Hall, second edition,1992.
[87] P. Dharwadkar, H. J. Siegel, E. K. P. Chong. A heuristic for dynamic bandwidth allocationwith preemption and degradation for prioritized requests[A]. In Proceedings of theInternational Conference on Distributed Computing Systems[C](ICDCS2001),2001:547-556.
[88] S. Zimmermann, U. Killat. Resource marking and fair rate allocation[A].In Procedings ofIEEE ICC2002[C], New York, USA,2002:1310-1314.
[89] C. S. Chang, Z.Liu. A bandwidth sharing theory for a large number of HTTP-likeconnections[J], IEEE/ACM Transactions on Networking,2004,12(5):952-962.
[90] L. Massoulie, J. Roberts. Bandwidth sharing:objectives and algorithms[J], IEEE/ACMTransactions on Networking,2002,10(3):320-328.
[91] L. Shi, C. Liu, B. Liu. Network utility maximization for triple-play services[J], ComputerCommunications,2008,3l(10):2257-2269.
[92] S. H. Low. Equilibrium bandwidth and buffer allocations for elastic traffics[J]. IEEE/ACMTransactions on Networking,2000,8(3):373-383.
[93] J. W. Lee, R.R.Mazumdar,N.B.Shroff. Non-convex optimization and rate control formulti-class services in the Intemet[J]. IEEE/ACM Transactions on Networking,2005,13(4):827-840.
[94] M． Fazel， M． Chiang． Nonconcave utility maximization through sum-of-squaresmethod[A].In Proceedings of the44th1EEE Conference on Decision and Contr01and theEuropean Control Conferenee(CDC-ECC2005)[C], Seville, Spain,2005:1867-1874.
[95] G. Abbas，A．K．Nagar, H．Tawfil, J．Y. Goulermas．Extended adaptive rate allocationfor distributed flow control of muiticlass services in the next generation networks[A].InProceedings of3rd International Conference on Next Generation Mobile Applications,Services and Technologies ('NGMAST2009)[C],2009:285-291.
[96] M. Chiang, S. Y. Zhang, P. Hande. Distributed rate allocation for inelastic flows:Optimization frameworks,optimality conditions,and optimal algorithms[A].In Proceedingsof IEEE INFOCOM2005[C], Miami, Florida, USA,2005:2679-2690.
[97] P. Hande, S. Zhang, M. Chiang. Distributed rate allocation for inelastic flows[J].IEEE/ACM Transactions on Networking,2007,15(6):1240-1253.
[98] F. P. Kelly. Charging and rate control for elastic traffic[J]. European Transactions onTelecommunications,1997,8(1):33-37.
[99] M. Q. Tang, C. N. Long, X. R. Guan. Nonconvex maximization for communicationsystems based on particle swarm optimization[J]. Computer Communications,2010,33(7):841-847.
[100] Hwnag M. l., Lin J. W. Neural fuzzy systems:A tutorial and application[J].Journal ofComputer Inofrmation Systems,2000,40(4):27-31.
[101]玄光男、程润伟.遗传算法与工程实现[M].北京：清华大学出版社:2005.
[102]蔡振兴、徐光佑.人工智能及其应用[M].北京：清华大学出版社:2004.
[103]施光燕、钱伟懿、庞丽萍.最优化方法[M].北京：高等教育出版社:2007.
[104] Xilinx. Virtex-5Family Overview [EB/OL]. http://www.xilinx.com/support/documentation/.
[105] Netlogic NS3300datasheet [EB/OL]. http://www.netlogic.com/documentation/.
[106] Spirent TestCenter[EB/OL].http://www.spirent.com/Solution-Directory/Spirent-Testcenter.
[107] RFC4460.Steam Control Transmission Protocol(SCTP)specification errata andissues[S],IETF,2006.
[108] MAGALHAES L, KRAVETS R. Transport level mechanisms for bandwidth aggregationon mobile hosts[A]．In Proceedings of ICNP[C], Riverside, Callforuia, USA,2001:165-171.
[2]中国互联网信息中心(CNNIC).第29次中国互联网络发展状况统计报告[EB/OL].http://www.cnnic.cn,2012.
[3] High Speed Broadband Services Demand Side Study [EB/OL].http://www.comcom.govt.nz/.
[4]黄孝建,陶蒙华． IPTV关键技术详解[M].北京:北京邮电大学出版社,2009:15-25.
[5] RFC2328. OSPF version2[S]. IETF,1988.
[6] RFC1195. Use of OSI IS-IS for Routing in TCP/IP and Dual Environments[S]. IETF,1990.
[7] Uhlig S, Quoitin B, Lepropre J, etal. Providing Public Intradomain Traffic Matrices to theResearch Community[J]. ACM SIGCOMM Computer Communication Review,2006,36(1):83-86.
[8]中华人民共和国国务院.推进三网融合总体方案[EB/OL]:三网融合12个试点城市名单和试点方案.
[9] Haim Zlatokrilov. Packet Dispersion and the Quality of Voice over IP Applications in IPnetworks[A]. In Proceedings of IEEE INFOCOM2004[C], Hong Kong, IEEE Press,2004:576-590.
[10]兰巨龙.国家高技术研究发展计划（863计划）课题申请书“快速自愈路由协议与试验系统”[R].郑州:解放军信息工程大学,2007-5-22.
[11]朱宣勇.国家高技术研究发展计划（863计划）课题申请书“一种基于节点势能导向的多路由产生机制”[R].郑州：解放军信息工程大学,2007.
[12]伊鹏.国家高技术研究发展计划（863计划）课题申请书“一种基于多下一跳路由的动态均衡路由交换机制”[R].郑州：解放军信息工程大学,2007.
[13] RFC2992. Analysis of an Equal-Cost Multi-Path Algorithm[S]. IETF.2002.
[14] T. Guven, C. Kommareddy, R. J. La, M. A. Shayman, and B. Bhattacharjee. Measurementbased optimal multi-path routing[A]. In Proceedings of IEEE INFOCOM2004[C], HongKong, IEEE Press,2004:187-196.
[15] P. Narvaez, K. Y. Siu. Efficient Algorithms for Multi-Path Link State Routing[C].ISCOM'99, Kaohsiung, Taiwan,1999.
[16] H. S. Palakurthi. Study of Multipath Routing for QoS Provisioning[J].EECS803-Introduction to Research, October5,2001:1-6.
[17] W. T. Zaumen and J.J. Garcia-Luna-Aceves. Loop-Free Multipath Routing UsingGeneralized Diffusing Computations. Proc. IEEE INFOCOM, March1998.
[18] S. Vutukury, J.J. Garcia-Luna-Aceves. A Simple Approximation to Minimum DelayRouting [A]. In Proceedings of ACM SIGCOMM[C].Cambridge, Massachusetts, USA,1999.
[19] Srinivas Vutukury, J.J. Garcia-Luna-Aceves. MDVA: A Distance-Vector Multipath RoutingProtocol [A]. In Proceedings of the INFOCOM2001[C],20th Annual Joint Conference ofthe IEEE Computer and Communications Societies[C], Anchorage, USA,2001.
[20] S. Vutukury and J.J. Garcia-Luna-Aceves. A Distributed Algorithm for MultipathComputation using Distance-Vectors with Predecessor Information[A]. In Proceedings ofGLOBECOM (Global Telecommunications Conference)[C], Volume3, IEEE Press,1999:1689-1693.
[21] S. Vutukury. Multipath Routing Mechanisms for Traffic Engineering and Quality ofService in the Internet[D]. PhD Thesis, Department of Computer Science, University ofCalifornia, Santa Cruz.2001.
[22] J.J. Garcia-Luna-Aceves. Loop-Free Routing Using Diffusing Computations[J].IEEE/ACM Transactions on Networking, February1993,1(1):130–141.
[23]陈文平.多下一跳快速自愈路由技术研究[D].解放军信息工程大学硕士学位论文,2009.6.
[24]张建辉.节点势能导向多下一跳路由协议研究与性能评价[D].解放军信息工程大学博士学位论文,2009.6.
[25] M.zhang, J.Lai, A.Krishnamurthy, L.Peterson, R.Wang. A transport layer approach forimproving end-to-end performance and robustness using redundant paths[A]. InProc.USENIX Annual Technical Conference[C]. Boston, USA,2004:99-112.
[26] A.Ford, C.Raiciu, S.Barre, J.Iyengar. Architectural guidelines for multipath TCPdevelopment, draft-ietf-mptcp-architecture-00[S].IETF,2010.
[27] H.Y.Hsieh, R.Sivakumar. A transport layer approach for achieving aggregate bandwidthson multi-homed mobile hosts[J]. Wireless Network,2005,11(1-2):99-114.
[28] RFC2960. Stream Control Transmission Protocol(SCTP)[S],IETF,2000.
[29] A.A.E.Al, T.Saadawi, M.Lee. LS-SCTP: a bandwidth aggregation technique for StreamControl Transmission Protocol[J]. Computer Communications,2004,27(10):1012-1024.
[30] A. E. Al, T.Saadawi, M.Lee. A transport layer load-sharing mechanism for mobile wirelesshosts[A]. In Proc.of the IEEE Annual Conference On Pervasive Computing andCommunications Workshops(PERCOMW)[C].Orlando,IEEE Press,2004:87-91.
[31] RFC3272. Overview and principles of Internet traffic engineering[S]. IETF,2010.
[32] Fortz B, Thorup M. Internet Traffic Engineering by Optimizing OSPF Weights[A]. InProceedings of IEEE INFOCOM[C],2000:519-528.
[33] Fortz B, Thorup M. Optimizing OSPF/IS-IS Weights in a Changing World[J]. IEEEJournal On Selected Areas In Communications,2002-5,20(4):756-767.
[34] Y.Wang,Z. Wang, and L. Zhang. Internet traffic engineering without full-meshoverlaying[A]. In Proceedings of INFOCOM2001[C], Apr.2001:565-571.
[35] S. Kandula, D. Katabi, B. Davie. Walking the Tightrope: Responsive yet Stable TrafficEngineering[A]. In Proceedings of SIGCOMM2005[C], Philadelphla, PA: ACM,2005:253-264.
[36] J. He, M. Chiang, and J. Rexford. DATE: Distributed Adaptive Traffic Engineering[A].InPoster session at INFOCOM2005[C] Miami, Florida, USA,2005:210-216.
[37] H. Wang, H. Xie, L. Qiu. Cope: Traffic engineering in dynamic networks[A]. InProceedings of the ACM SIGCOMM2006[C], Pisa, Italy: ACM,2006:99-110.
[38] D. H. Xu, M. Chiang, J. Rexford. DEFT: Distributed Exponentially-weighted FlowSplitting[A]. In Proceedings of the IEEE INFOCOM2007[C], Anchorage, AK, USA:IEEE, May2007:71-79.
[39] D. H. Xu, M. Chiang, J. Rexford. Link-State Routing with Hop-by-Hop Forwarding canAchieve Optimal Traffic Engineering[A]. In Proceedings of the IEEE INFOCOM2008[C],Phoenix, AZ: IEEE,2008:466-474.
[40] Elwalid A, Jin C, Low S, and Widjaja I. MATE: MPLS Adaptive Traffic Engineering.Anchorage[A]. In Proceedings of IEEE INFOCOM2001[C], AK, USA, IEEE Press,2001:1300-1309.
[41] MATTHEW W,CARLYLE R,KEVIN W.Near Shortest and K shortest Simple Paths[J]，Networks,2005,46(2):98-109.
[42] Roughan M, Thorup M, Zhang Y. Traffic Engineering with Estimated Traffic Matrices[A].In Proceedings of ACM IMC[C], Miami Beach, FL, USA,2003:248-258.
[43] Skivée F, Balon S, Leduc G. A Scalable Heuristic for Hybrid IGP/MPLS TrafficEngineering-Case Study on an Operational Network[A]. In Proceedings of IEEE ICON[C].Singapore, IEEE Press,2006:572-577.
[44] Pham H and Lavery B. Hybrid Routing for Scalable IP/MPLS Traffic Engineering[A]. InProceedings of IEEE ICC[C]. Anchorage, AK, USA, IEEE Press,2003:332-337.
[45] F. P. Kelly, A. Maulloo, D. Tan,. Rate control for communication networks: shadow prices,proportional fairness and stability[J].Operational Research Society,Mar.1998,49(3):237-252.
[46] M Chiang, S H Low, A R Calderbank and J C Doyle. Layering as optimizationdecomposition: A Mathematical theory of network architecture[A]. In Proceedings ofIEEE[C].2005,95(1):255-311.
[47] S. H. Low. A duality model of TCP and queue management algorithms[J]. IEEE/ACMTransactions on Networking, August2003,11(4):578-590.
[48] S. H. Low, D. E. Lapsley. Optimization flow control I: basic algorithm and convergence[J].IEEE/ACM Transactions on Networking, Dec1999,7(6):861-874.
[49] S. H. Low, L. Peterson, L. Wang. Understanding Vegas: A duality model[J].IEEE/ACMTransaction on Networking, August2003,11(4):525-536.
[50] Ao Tang, Krister Jacobsson, H Andrew, Steven H Low. An accurate link model and itsapplication to stability analysis of FAST TCP[A]. In Proceedings of IEEE INFOCOM2007[C], Anchorage, Alaska, May2007:1123-1135.
[51] L. H. Andrew, S. H. Low, B. P. Wydrowski. Understanding XCP:Equilibrium andfairness[J]. IEEE/ACM Transactions on Networking,2009,17(6):1697-1710.
[52] H. Han, S. Shakkottai, C. Hollot, R. Srikant, and D. Towsley. Overlay TCP for multi-pathrouting and congestion control[A]. In Proceedings of ENS-INRIA ARC-TCPWorkshop[C], Paris, France,2003:535-549.
[53] X. Lin and N. B. Shroff. Utility maximization for communication networks with multipathrouting[J].IEEE/ACM Transactions on Networking,2006,51(5):766-781.
[54] Wang J, Li Lt, Low S, et a1.Cross-Layer Optimization in TCP/IP Networks[J]. IEEE/ACMTransactions on Networking,2005,13(3):582-595.
[55] Key P, Massouli6L，Towsley D．Path Selection and Multipath Congestion Control[A]. InProceedings of IEEE INFOCOM2007[C], Anchorage, Alaska, May2007:143-151.
[56] T. Voice. Stability of multi-path dual congestion control algorithm[J]. IEEE/ACMTransactions on Networking,2007,15(6):1231-1239.
[57] J. Jin, W. H. Wang, M. Palaniswami. Utility max·min fair resource allocation forcommunieation networks with multipath routing[J]. Computer Communications,2009,32(17):1802-1809.
[58] Akon. M. M, Asaduzzaman. S, Rahman. Md. S. Proposal for st-Routing Protocol [J].Telecommunication Systems,2004,25(3-4):287-298.
[59] Y. Ohara, H. Kusumoto, O. Nakamura, and J. Murai. Drouting architecture: Improvementof failure avoidance capability using multipath routing[J]. IEICE Transactions,2008,91-B(5):1403-1415.
[60] Y. Ohara, Shinji Imahori, Rodney Van Meter. MARA: Maximum Alternative RoutingAlgorithm[A] In Proceedings of IEEE INFOCOM2009[C],2009:862-885.
[61] H. Nagamochi and T. Ibaraki. Computing edge-connectivity in multigraphs andcapacitated graphs[J]. SIAM J. Discret. Math,1992,5(1):54–66.
[62] H. Nagamochi and T. Ibaraki. Graph connectivity and its augmentation: applications ofMA orderings[J]. Discrete Appl. Math,2002,123(1-3):447–472.
[63] Z. Wang. On the complexity of quality of service routing[J]. Information Processing Leters,1999,69(3):111-114.
[64] Q.Ma.QoS Routing in the integrated services networks[D]. Ph.D.thesis. Carnegie MellonUniversity,1998.1.
[65] SSFNet1.5[EB/OL]. http://www.ssfnet.org/.
[66] BRITE Topology Generator [EB/OL]. http://www.cs.bu.edu/brite/.
[67] K. Ramakrishnan and M. Rodrigues. Optimal routing in shortest path data networks[J].Lucent Bell Labs Technical Journal,2001,6(1):772-785.
[68] A. Yuen T. Chung. Traffic Engineering for Multi-homed Mobile Networks[D]. AustraliaSydney: The university of new south wales sydney,2007.
[69]拉文德拉K.阿胡亚,托马斯L.马南提,詹姆斯B.沃林著,网络流:理论、算法及应用[M].北京:中国机械出版社,2005:337-385.
[70] G. Retvari and T Cinkler, Practical OSPF Trafic Engineering[J]. IEEE Communicationletter,2004,8(11):689-691.
[71] Zhang Y, Roughan M, Duffield N, et al. Fast Accurate Computation of Large-Scale IPTraffic Matrices from Link Loads[A]. In Proceedings of ACM SIGMETRICS2003[C],San Diego, CA, USA,2003:206-217.
[72] Zhang Y, Roughan M, Lund C, et al. Estimating Point-to-Point and Point-to-MultipointTraffic Matrices: An Information-Theoretic Approach[J]. IEEE/ACM Transactions onNetworks,2005,13(5):947-960.
[73] Abilene Backbone[EB/OL]. http://www.internet2.edu/network/.
[74] Zhang Y. Traffic Matrices of Abilene[EB/OL].http://www.cs.utexas.edu/~yzhang/research/AbileneTM,2009-11-29.
[75] The topology of internet2[EB/OL].http://globalnoc.iu.edu/uploads/tB/z8/tBz8316lo_75e-DSIfBIXg/IGP-Metrics.pdf,2010-03-05.
[76] China Education and Research Network[EB/OL]. http://www.edu.cn/english1369/index.shtml.2012-01-01.
[77] F. P. Kelly. Fairness and stability of end-to-end congestion control[J]. European Journal ofControl,2003,9(2-3):159-176.
[78] D.P.Bertsekas.Nonlinear Programming[M],2nded, Belmont, MA: Athena Scientific,1999.
[79] S. Boyd, L. Vandenberghe, Convex Optimization[M]. Cambridge, U.K.:CambridgeUniv.Press,2004.
[80] J. He, M. Bresler, M. Chiang, and J. Rexford. Rethinking Internet traffic management:From multiple decompositions to a practical protocol[A]. In Procedings of CoNEXT[C],December2007:1123-1145.
[81] J. He, M. Bresler, M. Chiang, and J. Rexford. Towards multi-layer traffic engineering:Optimization of congestion control and routing[J]. IEEE Journal on Selected Areas inCommunications, June2007:631-655.
[82] A. Mas-Colell, M. Whinston, J. Green. Microeconomic Theory[M].England: OxfordUniversity Press,1995.
[83] S. Kunniyur and R. Srikant. End-to-end congestion control schemes: utility function,random losses and ECN marks[A]. In Procedings of IEEE Infocom2000[C], vol.3,2000:1323-1332.
[84] Jeffrey M.Jaffe. Bottleneck flow control[J]. IEEE/ACM Transactionsons on Networking,Com-29(7), July1981:954-962.
[85] Howard Paul Hayden. Voice flow control in integrated Packet networks[M].Master Thesis,MIT Dept.of EECS, Cambridge MA,1981.
[86] D. Bersekas and R. Gallager. Data Networks[M]. Prentice Hall, second edition,1992.
[87] P. Dharwadkar, H. J. Siegel, E. K. P. Chong. A heuristic for dynamic bandwidth allocationwith preemption and degradation for prioritized requests[A]. In Proceedings of theInternational Conference on Distributed Computing Systems[C](ICDCS2001),2001:547-556.
[88] S. Zimmermann, U. Killat. Resource marking and fair rate allocation[A].In Procedings ofIEEE ICC2002[C], New York, USA,2002:1310-1314.
[89] C. S. Chang, Z.Liu. A bandwidth sharing theory for a large number of HTTP-likeconnections[J], IEEE/ACM Transactions on Networking,2004,12(5):952-962.
[90] L. Massoulie, J. Roberts. Bandwidth sharing:objectives and algorithms[J], IEEE/ACMTransactions on Networking,2002,10(3):320-328.
[91] L. Shi, C. Liu, B. Liu. Network utility maximization for triple-play services[J], ComputerCommunications,2008,3l(10):2257-2269.
[92] S. H. Low. Equilibrium bandwidth and buffer allocations for elastic traffics[J]. IEEE/ACMTransactions on Networking,2000,8(3):373-383.
[93] J. W. Lee, R.R.Mazumdar,N.B.Shroff. Non-convex optimization and rate control formulti-class services in the Intemet[J]. IEEE/ACM Transactions on Networking,2005,13(4):827-840.
[94] M． Fazel， M． Chiang． Nonconcave utility maximization through sum-of-squaresmethod[A].In Proceedings of the44th1EEE Conference on Decision and Contr01and theEuropean Control Conferenee(CDC-ECC2005)[C], Seville, Spain,2005:1867-1874.
[95] G. Abbas，A．K．Nagar, H．Tawfil, J．Y. Goulermas．Extended adaptive rate allocationfor distributed flow control of muiticlass services in the next generation networks[A].InProceedings of3rd International Conference on Next Generation Mobile Applications,Services and Technologies ('NGMAST2009)[C],2009:285-291.
[96] M. Chiang, S. Y. Zhang, P. Hande. Distributed rate allocation for inelastic flows:Optimization frameworks,optimality conditions,and optimal algorithms[A].In Proceedingsof IEEE INFOCOM2005[C], Miami, Florida, USA,2005:2679-2690.
[97] P. Hande, S. Zhang, M. Chiang. Distributed rate allocation for inelastic flows[J].IEEE/ACM Transactions on Networking,2007,15(6):1240-1253.
[98] F. P. Kelly. Charging and rate control for elastic traffic[J]. European Transactions onTelecommunications,1997,8(1):33-37.
[99] M. Q. Tang, C. N. Long, X. R. Guan. Nonconvex maximization for communicationsystems based on particle swarm optimization[J]. Computer Communications,2010,33(7):841-847.
[100] Hwnag M. l., Lin J. W. Neural fuzzy systems:A tutorial and application[J].Journal ofComputer Inofrmation Systems,2000,40(4):27-31.
[101]玄光男、程润伟.遗传算法与工程实现[M].北京：清华大学出版社:2005.
[102]蔡振兴、徐光佑.人工智能及其应用[M].北京：清华大学出版社:2004.
[103]施光燕、钱伟懿、庞丽萍.最优化方法[M].北京：高等教育出版社:2007.
[104] Xilinx. Virtex-5Family Overview [EB/OL]. http://www.xilinx.com/support/documentation/.
[105] Netlogic NS3300datasheet [EB/OL]. http://www.netlogic.com/documentation/.
[106] Spirent TestCenter[EB/OL].http://www.spirent.com/Solution-Directory/Spirent-Testcenter.
[107] RFC4460.Steam Control Transmission Protocol(SCTP)specification errata andissues[S],IETF,2006.
[108] MAGALHAES L, KRAVETS R. Transport level mechanisms for bandwidth aggregationon mobile hosts[A]．In Proceedings of ICNP[C], Riverside, Callforuia, USA,2001:165-171.