多级多平面分组交换技术研究
|
摘要
随着信息网络朝着传输高速化和接入宽带化方向演进,路由交换设备交换结构的扩展能力受到严峻挑战。多级多平面(MPMS)分组交换技术能够将多个小规模交换单元汇聚成大规模交换网络,从而突破单一交换单元的容量限制,极大地提高了路由交换设备的可扩展性。因此,多级多平面分组交换技术得到了学术界和产业界的广泛重视。但是,由于缺乏理论基础和数学模型,多级多平面分组交换技术的研究目前尚处于起步阶段,很多重要的技术难题尚未解决,严重影响了实际应用。
结合十一五国家973计划项目ǎ一体化网络体系结构模型及交换路由理论与技术ǐ的研究工作,针对路由交换设备对于交换技术的可扩展性需求,本文在深入分析功能实体和连接链路互连结构的基础上,提出了多级多平面分组交换系统的通用架构和数学模型,建立了多级多平面分组交换技术的模型分析方法和性能评估手段。在此基础上,提出两种缓存结构的多级多平面交换系统,并进行建模分析和性能评估。为了适应互联网中带宽敏感业务需求,提出一种多级多平面交换系统的带宽保证调度技术。本文的主要研究内容包括以下几个方面:
1.研究了多级多平面分组交换系统的通用架构,提出了一种基于有向图的MPMS交换结构理论分析模型。根据MPMS中功能子集和链路子集提出了MPMS交换系统的通用架构,分析了系统级和平面级通用架构的组织方式和连通结构。运用有向图建模理论,提出了MPMS交换结构的有向图DGM模型,定义了DGM模型的相邻连通性和端口可达性等模型特征,并提出了MPMS的模型拓扑图。基于模型特征,定义了模型顶点的竞争均衡性和交换路径,描述了可以定量描述MPMS交换系统可扩展能力的性能扩展比等参量。
2.提出了一种输入/输出级缓存Clos型MPMS(MSMC&MPMS)分组交换系统,给出了MSMC&MPMS交换系统的拓扑结构,建立了MSMC&MPMS交换系统的DGM模型。研究了MSMC&MPMS模型的拓扑图复杂性。相邻连通性和端口可达性等拓扑特征,提出了拓扑测度图。研究表明,MSMC&MPMS交换系统中的分路器和输入交换单元为均衡顶点,中间交换单元。输出交换单元和合路器为竞争顶点。MSMC&MPMS交换系统中分路器和合路器间的交换路径数SwPC值等于P×m(P为交换平面数,m为中间交换单元数);交换端口数量可以扩展至PN倍(PN为单一交换结构最大端口数),交换端口速率可以扩展至P倍,交换容量可以扩展至P×PN倍,交换结构复杂度仅随交换平面数呈线性提高。
3.提出了一种中间级缓存Clos型MPMS(CBC&MPMS)分组交换系统。提出了CBC&MPMS交换系统的拓扑结构,建立了CBC&MPMS交换系统的DGM模型。研究了CBC&MPMS模型的拓扑图复杂性。相邻连通性和端口可达性等拓扑特征,提出了拓扑测度图。研究表明,CBC&MPMS交换系统中的分路器。输入交换单元以及第I类中间交换单元为均衡顶点,第II类中间交换单元。输出交换单元和合路器为竞争顶点;CBC&MPMS交换系统中分路器与合路器之间的交换路径数为P×m×k,是MSMC&MPMS交换系统的k倍;CBC&MPMS交换系统与MSMC&MPMS交换系统具有相同的交换端口数量。交换端口速率。交换容量扩展能力;但交换结构复杂度比MSMC&MPMS高出约33.3%。
4.推导出MSMC&MPMS交换系统结构无阻塞需要的拓扑参数条件是P×m×k≥N或者P×m≥n(k为输入/输出交换单元数,N为交换系统端口数,n为输入/输出交换单元端口数);CBC&MPMS交换系统结构无阻塞需要的拓扑参数条件是P×m×k2≥N或者P×k×m≥n,需要更少的输入/输出交换单元即可实现交换结构无阻塞。推导出MSMC&MPMS模拟OQ交换结构所需的内部加速比S值约为S≥2/P或者S≥N/(P×m×k);CBC&MPMS交换结构模拟OQ交换结构需要的内部加速比S值为S≥1/P和拓扑参数条件为m≥N/(P×k),成本时空积TSP值仅为MSMC&MPMS交换系统的1/2P倍。
5.提出了一种MPMS交换系统的带宽保证调度技术。分析了Cell分组流在MPMS交换系统中链路和路径的带宽分布特征,提出了MPMS交换系统中分路器。合路器。输入/中间/输出交换单元的调度模型,设计了一种MPMS交换系统的支持带宽保证并发轮转(BG-CRRD)调度算法。BG-CRRD算法在Bernoulli均匀流量时可以获得100%的吞吐率,交换平面数P值增加至3时收敛至最优平均时延性能;在非均匀流量时可以获得的吞吐率性能明显优于CRRD算法,极坏情况下可以获得的吞吐率高达92%,比CRRD算法吞吐率高29%;在过载流量时根据预留带宽在各分组流间分配输出链路带宽,从而保证业务流的带宽需求和带宽分配的公平性。因此BG-CRRD调度算法满足业务带宽保证调度需求。
With the evolution towards high-speed transportation as well as access network, the scalability of network routers is challenged rigorously. The novel multiple plane and multiple stage (MPMS) packet switching technology can integrate multiple small-scale switching units into a large switching network, which is able to break the bottleneck of single switching fabric and increase the scalability of network routers. Therefore, the MPMS switching technology is causing more and more attention from academic and industry domains. The MPMS switching technology, however, is only at its initial research phase for lacking of theoretic basis and mathematics models. Many important technical issues of MPMS have not been studied deeply, which holds back its application in practical network routers seriously.
Combined with the research work of the National Basic Research Program of China (973 program) of“the integrated network architecture model and the switching and routing theory and technology”, regarding to the scalability requirement of router switching fabric, a universe architecture and mathematics model of the MPMS are proposed, and the analysis methods and performance evaluation techniques are built up, which are based the functional units and linking structure. Two novel MPMS switching system with different buffering methods are proposed and studied evaluated. To meet the bandwidth sensitive services in Internet, a bandwidth guaranteed scheduling technique is proposed. The main research work of this paper includes:
1. The universal architecture and the directed graph model (DGM) are proposed. The universal architecture and organization method are proposed and analyzed based on the functional unit subsets and linking connection subsets. With the directed graph theory, the DGM model of the MPMS switching system is proposed, and the characters including neighboring relations and port reachability are defined, and the model graph is also provided. Based on the defined model character, the vertex competing and balancing property and the switching path are defined. The performance expansive ratio is defined to describe the scalability accurately.
2. A novel input/output buffered Clos-type MPMS (MSMC&MPMS) packet switching system is studied, and its topological structure is proposed, and then its DGM model is built up. The topological characters, including graph complexity, neighboring connectivity, and port reachability, are studied, and then the topological measure graph is given of the MSMC&MPMS system. It is shown that, demultiplexors and input switching units belong to balancing vertex, while middle switching units, output switching units and multiplexors belong to competing vertex in the MSMC&MPMS system. The switching path count between any demultiplexor and multiplexor pair is equal to P×m, where P is the switching plane number and m is the middle switching unit number. The number of switching ports can be expanded to PN times, where PN refers to the maximum port count of single switching fabric, and the rate of switching ports to P times, and the switching capacity to P×PN times, while the fabric structure is only linearly increased with the switching plane numbers.
3. A novel central stage buffered Clos-type MPMS (CBC&MPMS) packet switching system is studied. Its topological structure is proposed, and then its DGM model is built up. The topological characters, including graph complexity, neighboring connectivity, and port reachability, are studied, and then the topological measure graph is given of the CBC&MPMS system. Demultiplexors, input switching units and middle switching units I belong to balancing vertex, while middle switching units II, output switching units and multiplexors belong to competing vertex. The switching path count between any demultiplexor and multiplexor is P×m×k, k times the MSMC&MPMS system. It has the same expansive parameters with that of MSMC&MPMS, but its fabric complexity is 33.3% higher than that of MSMC&MPMS.
4. MSMC&MPMS is proved to be fabric non-blocking under condition of P×m×k≥N or P×m≥n, where k is input/output switching unit count, N is system port count and n is input/ output switching port count, while CBC&MPMS is fabric non-blocking with parameters satisfying P×m×k2≥N or P×k×m≥n, needing much less input/output switching units. Meanwhile, MSMC&MPMS is proved to emulate an OQ switch with speedup factor satisfying S≥2/P or S≥N/(P×m×k), while CBC&MPMS can emulate an OQ switch if S≥1/P and m≥N/(P×k), whose TSP is only 1/2P times that of MSMC&MPMS.
5. A novel bandwidth guaranteed scheduling technique of the MPMS switching system is provided. The scheduling model of demultiplexors, multiplexors and input/output /middle switching units are provided, and a bandwidth guaranteed concurrent round-robin dispatching algorithm (called BG-CRRD) is also designed. Simulation results show that, the algorithm can achieve 100% throughput under Bernoulli uniform traffic, and the optimal delay can be achieved when the switching plane count is three. Under nonuniform traffic, it can gain a throughput much higher than CRRD, and can achive a throghput of 92% under worst case, which is 29% higher than that of the CRRD algorithm. Under overloaded traffic, it can allocate output-link bandwidth among Cell flows according to their reserved bandwidth, and therefore can satisfy the bandwidth requirement of service folw and share bandwidth fairly. So the BG-CRRD scheduling algorithm can satisfy the scheduling demands of different bandwidth sensitive services.
结合十一五国家973计划项目ǎ一体化网络体系结构模型及交换路由理论与技术ǐ的研究工作,针对路由交换设备对于交换技术的可扩展性需求,本文在深入分析功能实体和连接链路互连结构的基础上,提出了多级多平面分组交换系统的通用架构和数学模型,建立了多级多平面分组交换技术的模型分析方法和性能评估手段。在此基础上,提出两种缓存结构的多级多平面交换系统,并进行建模分析和性能评估。为了适应互联网中带宽敏感业务需求,提出一种多级多平面交换系统的带宽保证调度技术。本文的主要研究内容包括以下几个方面:
1.研究了多级多平面分组交换系统的通用架构,提出了一种基于有向图的MPMS交换结构理论分析模型。根据MPMS中功能子集和链路子集提出了MPMS交换系统的通用架构,分析了系统级和平面级通用架构的组织方式和连通结构。运用有向图建模理论,提出了MPMS交换结构的有向图DGM模型,定义了DGM模型的相邻连通性和端口可达性等模型特征,并提出了MPMS的模型拓扑图。基于模型特征,定义了模型顶点的竞争均衡性和交换路径,描述了可以定量描述MPMS交换系统可扩展能力的性能扩展比等参量。
2.提出了一种输入/输出级缓存Clos型MPMS(MSMC&MPMS)分组交换系统,给出了MSMC&MPMS交换系统的拓扑结构,建立了MSMC&MPMS交换系统的DGM模型。研究了MSMC&MPMS模型的拓扑图复杂性。相邻连通性和端口可达性等拓扑特征,提出了拓扑测度图。研究表明,MSMC&MPMS交换系统中的分路器和输入交换单元为均衡顶点,中间交换单元。输出交换单元和合路器为竞争顶点。MSMC&MPMS交换系统中分路器和合路器间的交换路径数SwPC值等于P×m(P为交换平面数,m为中间交换单元数);交换端口数量可以扩展至PN倍(PN为单一交换结构最大端口数),交换端口速率可以扩展至P倍,交换容量可以扩展至P×PN倍,交换结构复杂度仅随交换平面数呈线性提高。
3.提出了一种中间级缓存Clos型MPMS(CBC&MPMS)分组交换系统。提出了CBC&MPMS交换系统的拓扑结构,建立了CBC&MPMS交换系统的DGM模型。研究了CBC&MPMS模型的拓扑图复杂性。相邻连通性和端口可达性等拓扑特征,提出了拓扑测度图。研究表明,CBC&MPMS交换系统中的分路器。输入交换单元以及第I类中间交换单元为均衡顶点,第II类中间交换单元。输出交换单元和合路器为竞争顶点;CBC&MPMS交换系统中分路器与合路器之间的交换路径数为P×m×k,是MSMC&MPMS交换系统的k倍;CBC&MPMS交换系统与MSMC&MPMS交换系统具有相同的交换端口数量。交换端口速率。交换容量扩展能力;但交换结构复杂度比MSMC&MPMS高出约33.3%。
4.推导出MSMC&MPMS交换系统结构无阻塞需要的拓扑参数条件是P×m×k≥N或者P×m≥n(k为输入/输出交换单元数,N为交换系统端口数,n为输入/输出交换单元端口数);CBC&MPMS交换系统结构无阻塞需要的拓扑参数条件是P×m×k2≥N或者P×k×m≥n,需要更少的输入/输出交换单元即可实现交换结构无阻塞。推导出MSMC&MPMS模拟OQ交换结构所需的内部加速比S值约为S≥2/P或者S≥N/(P×m×k);CBC&MPMS交换结构模拟OQ交换结构需要的内部加速比S值为S≥1/P和拓扑参数条件为m≥N/(P×k),成本时空积TSP值仅为MSMC&MPMS交换系统的1/2P倍。
5.提出了一种MPMS交换系统的带宽保证调度技术。分析了Cell分组流在MPMS交换系统中链路和路径的带宽分布特征,提出了MPMS交换系统中分路器。合路器。输入/中间/输出交换单元的调度模型,设计了一种MPMS交换系统的支持带宽保证并发轮转(BG-CRRD)调度算法。BG-CRRD算法在Bernoulli均匀流量时可以获得100%的吞吐率,交换平面数P值增加至3时收敛至最优平均时延性能;在非均匀流量时可以获得的吞吐率性能明显优于CRRD算法,极坏情况下可以获得的吞吐率高达92%,比CRRD算法吞吐率高29%;在过载流量时根据预留带宽在各分组流间分配输出链路带宽,从而保证业务流的带宽需求和带宽分配的公平性。因此BG-CRRD调度算法满足业务带宽保证调度需求。
With the evolution towards high-speed transportation as well as access network, the scalability of network routers is challenged rigorously. The novel multiple plane and multiple stage (MPMS) packet switching technology can integrate multiple small-scale switching units into a large switching network, which is able to break the bottleneck of single switching fabric and increase the scalability of network routers. Therefore, the MPMS switching technology is causing more and more attention from academic and industry domains. The MPMS switching technology, however, is only at its initial research phase for lacking of theoretic basis and mathematics models. Many important technical issues of MPMS have not been studied deeply, which holds back its application in practical network routers seriously.
Combined with the research work of the National Basic Research Program of China (973 program) of“the integrated network architecture model and the switching and routing theory and technology”, regarding to the scalability requirement of router switching fabric, a universe architecture and mathematics model of the MPMS are proposed, and the analysis methods and performance evaluation techniques are built up, which are based the functional units and linking structure. Two novel MPMS switching system with different buffering methods are proposed and studied evaluated. To meet the bandwidth sensitive services in Internet, a bandwidth guaranteed scheduling technique is proposed. The main research work of this paper includes:
1. The universal architecture and the directed graph model (DGM) are proposed. The universal architecture and organization method are proposed and analyzed based on the functional unit subsets and linking connection subsets. With the directed graph theory, the DGM model of the MPMS switching system is proposed, and the characters including neighboring relations and port reachability are defined, and the model graph is also provided. Based on the defined model character, the vertex competing and balancing property and the switching path are defined. The performance expansive ratio is defined to describe the scalability accurately.
2. A novel input/output buffered Clos-type MPMS (MSMC&MPMS) packet switching system is studied, and its topological structure is proposed, and then its DGM model is built up. The topological characters, including graph complexity, neighboring connectivity, and port reachability, are studied, and then the topological measure graph is given of the MSMC&MPMS system. It is shown that, demultiplexors and input switching units belong to balancing vertex, while middle switching units, output switching units and multiplexors belong to competing vertex in the MSMC&MPMS system. The switching path count between any demultiplexor and multiplexor pair is equal to P×m, where P is the switching plane number and m is the middle switching unit number. The number of switching ports can be expanded to PN times, where PN refers to the maximum port count of single switching fabric, and the rate of switching ports to P times, and the switching capacity to P×PN times, while the fabric structure is only linearly increased with the switching plane numbers.
3. A novel central stage buffered Clos-type MPMS (CBC&MPMS) packet switching system is studied. Its topological structure is proposed, and then its DGM model is built up. The topological characters, including graph complexity, neighboring connectivity, and port reachability, are studied, and then the topological measure graph is given of the CBC&MPMS system. Demultiplexors, input switching units and middle switching units I belong to balancing vertex, while middle switching units II, output switching units and multiplexors belong to competing vertex. The switching path count between any demultiplexor and multiplexor is P×m×k, k times the MSMC&MPMS system. It has the same expansive parameters with that of MSMC&MPMS, but its fabric complexity is 33.3% higher than that of MSMC&MPMS.
4. MSMC&MPMS is proved to be fabric non-blocking under condition of P×m×k≥N or P×m≥n, where k is input/output switching unit count, N is system port count and n is input/ output switching port count, while CBC&MPMS is fabric non-blocking with parameters satisfying P×m×k2≥N or P×k×m≥n, needing much less input/output switching units. Meanwhile, MSMC&MPMS is proved to emulate an OQ switch with speedup factor satisfying S≥2/P or S≥N/(P×m×k), while CBC&MPMS can emulate an OQ switch if S≥1/P and m≥N/(P×k), whose TSP is only 1/2P times that of MSMC&MPMS.
5. A novel bandwidth guaranteed scheduling technique of the MPMS switching system is provided. The scheduling model of demultiplexors, multiplexors and input/output /middle switching units are provided, and a bandwidth guaranteed concurrent round-robin dispatching algorithm (called BG-CRRD) is also designed. Simulation results show that, the algorithm can achieve 100% throughput under Bernoulli uniform traffic, and the optimal delay can be achieved when the switching plane count is three. Under nonuniform traffic, it can gain a throughput much higher than CRRD, and can achive a throghput of 92% under worst case, which is 29% higher than that of the CRRD algorithm. Under overloaded traffic, it can allocate output-link bandwidth among Cell flows according to their reserved bandwidth, and therefore can satisfy the bandwidth requirement of service folw and share bandwidth fairly. So the BG-CRRD scheduling algorithm can satisfy the scheduling demands of different bandwidth sensitive services.
引文
[1]中国互联网络信息中心.第22次中国互联网络发展状况统计报告[EB/OL]. :中国互联网络信息中心官方网站,2008-07-25:
[2] F. Abel, C. Minkenberg, R. Luijten, M. Gusat, I. Iliadis: A Four-Terabit Packet Switch Supporting Long Round-Trip Times[J]. IEEE Micro Magazine, Jan-Feb 2003, 23(1):10-24.
[3] R. Ryf et al.1296-port MEMS transparent optical crossconnect with 2.07 petabit/s switch capacity[A]. In Proc. Optical Fiber Communication Conference and Exhibitp[C].Anaheim, California, Mar. 2001, 4:PD28-P1.
[4] K. Yamakoshi, K. Nakai, and N. Yamanaka. 5-Tbit/s frame-based ATM switching system using 2.5-Gbit/s/spl times/8 optical WDM[A]. In Proc. IEEE International Conference on Communications[C]. Helsinki, Finland, June 2001, 10:3117-3121.
[5] N. Huang, G. Liaw, and C. Wang. A novel all-optical transport network with time-shared wavelength channels[J]. IEEE Journal on Selected Areas in Communications, Oct. 2000, 18(10):1863-1875.
[6] Y. Chai, J. H. Chen, F. S. Choa, J. P. Zhang, J. Y. Fan, and W. Lin. Scalable and modularized optical random access memories for optical packet switching networks[A]. In Proc. CLEO’98[C]. San Francisco, California, May 1998:397-402.
[7] J. Leuthold, B. Mikkelsen and G. Raybon.All-optical wavelength conversion between 10 and 100 Gb/s with SOA delayed-interference configuration[J].Optical and Quantum Electronic. 2001, 33(7):939-952.
[8] S. Nakamura, Y. Ueno, and K. Tajima.168-Gb/s all-optical wavelength conversion with a symmetric-Mach-Zehnder-type switch[J]. IEEE Photonics Technology Letters. Oct. 2001, 13(10):1091-1093.
[9] A. Jajszczyk, Nonblocking, repackable, and rearrangeable Clos networks: fifty years of the theory evolution[J]. IEEE Communications Magazine, 2003, 41(10):28-33 .
[10] H. J. Chao, Z. Jing, and S.Y. Liew. Matching algorithms for three-stage bufferless Clos network switches[J]. IEEE Communications Magazine, Oct. 2003,41(10):46-54.
[11] M. Gupta and S. Singh. Greening of the Internet[A]. In Proc. ACM SIGCOMM03[C], Karlsruhe, Germany, Aug. 2003:19-26.
[12] Kumar Rangonothan. Trustworthy pervasive computing:The hard security problems[A]. IEEE Proceedings on Pervasive Computing and Communications Workshops[C]. Orlando, USA: IEEE, 2004:117-121.
[13] M Crovela, E Kolaczyk. Graph Wavelets for Spatial Traffic Analysis[A]. 2003 IEEE Proceeding of Infocom [C]. San Francisco, USA: IEEE, 2003:1848-1857.
[14] B Y Zhao, L Huang, J Stribling, S C Rhea, A D Joseph, J D Kubiatowicz.Tapestry:a global-scale overlay for rapid service deployment[J]. IEEE Journal on Selected Areas inCommunications. 2004, 22(1):41-53.
[15] Honglu Yeom, Wasung Kim. An efficient multicast mechanism for data loss prevention[A]. The 7th International Conference on Advanced Communication Technology[C]. Phoenix Park, Korea: IEEE, 2005:497-502.
[16] Gkantsidis C, Rodriguez P R. Network coding for large scale content distribution[A]. IEEE Proceeding of Infocom [C]. Miami, FL, USA: IEEE, 2005: 2235-2245.
[17] F. M. Chiussi, J. G. Kneuer, andV. P. Kumar. Low cost scalable switching solutions for broadband networking: the ATLANTA architecuture and chipset[J]. IEEE Communications Magazine, Dec. 1997, 35(12):44-53.
[18] C. S. Chang, D. Lee, and Y. J. Shih. Mailbox switch: A scalable two-stage switch architecture for conflict resolution of ordered packets[A]. In Proc. IEEE INFOCOM 04[C]. Hong Kong, Mar. 2004, 3:1995-2006.
[19] H. J. Chao, J. S. Park, S. Artan, S. Jiang, and G. Zhang. TrueWay: A highly scalable multi-plane multi-stage buffered packet switch[A]. In Proc. IEEE Workshop on High Performance Switching and Routing[C]. Hong Kong, May 2005:246-253.
[20] E. Oki, Z. Jing, R. Rojas-Cessa, and H. J. Chao. Concurrent round-robin-based dispatching schemes for Clos-network switches[J]. IEEE/ACM Transactions on Networking, Dec. 2002, 10(6):830-844.
[21] Chuan-Bi Lin and Roberto Rojas-Cessa. Frame Occupancy-Based Dispatching Schemes for Buffered Three-stage Clos-Network Switches[A]. IEEE 7th Malaysia International Conference on Communications[C]. Nov. 2005:354-362.
[22] Chao H J, Jinsoo Park. Flow Control in a Multi-Plane Multi-Stage Buffered Packet Switch[A]. IEEE International Conference on HPSR[C]. June, 2007:1-6.
[23] Rojas-Cessa R, Oki E, Chao H. J. Concurrent fault detection for a multiple-plane packet switch[J]. IEEE/ACM Transactions on Networking, 2003,11(4): 616-627.
[24] H. J. Chao. Next generation routers[J]. IEEE Proceedings, Sept. 2002, 90(9):1518-1558.
[25] H. J. Chao. Saturn: a terabit packet switch using dual round-robin[J].IEEE Communications magazine, Dec. 2000, 38(12):78-84.
[26] I. Keslassy and N. McKeown. Maintaining packet order in two-stage switches[A]. In Proc. IEEE INFOCOM’02[C]. NewYork, June 2002, 2:1032-1041.
[27] Y. Shen, S. Jiang, S. Panwar, and H. J. Chao. Byte-Focal: a practical load balanced switch[A].In Proc. IEEE Workshop on High Performance Switching and Routing (HPSR05)[C]. Hong Kong, May 2005:6-12.
[28] C. S. Chang, D. Lee, and Y. Jou. Load balanced Birkhoff-von Neumann switches. Part I: One-stage buffering[J ].Computer Communications, 2002, 25(6):611-622.
[29] S. Jiang, G. Hu, S.Y. Liew, and H. J. Chao. Scheduling algorithms for shared fiber-delay-line optical packet switches, Part II: The 3-stage Clos-Network case[J]. IEEE Journal of Lightwave Technology, Apr. 2005, 23(4):1601-1609.
[30] R. Sudan and W. Mukai. Introduction to the Cisco CRS-1 Carrier Routing System[M]. Cisco Systems Inc., Jan.1994.
[31] Implementing a Flexible Hardware-based Router for the New IP Infrastructure, Juniper Inc., White Paper.
[32] Hwang K, Xu Z. Scalable parallel computers for real-time signal processing[J]. IEEE Signal Processing, 1996, 13(4):50-66.
[33] F. T. Leighton. Introduction to Parallel Algorithms and Architectures: Arrays. Trees. Hypercubes[M]. Morgan Kaufmann, San Francisco, California, 1992.
[34] M. J. Karol, M. Hluchyj, and S. Morgan. Input vs. output queuing on a space-division packet switch[J]. IEEE Trans. on Communications, Dec. 1987, 35(12):1347-1356.
[35] C. Clos. A study of non-blocking switching network[J]. Bell System Technical Journal, Mar. 1953, 32(2):404-426.
[36] V. E. Benes. Optimal rearrangeable multistage connecting networks[J].Bell System Technical Journal, July 1964, 43:1641-1656.
[37] S.Iyer, N.McKeown. Analysis of a packet switch with the memories running slower than the line rate[A]. INFOCOM’00[C]. Tel Aviv, Israel, 2000, 2:529-537.
[38] S.Iyer, N.McKeown. Making parallel switches practical[A]. INFOCOM’00[C]. Tel Aviv, Israel, 2001, 3:1680-1687.
[39] D. A. Khotimsky, S. Krishnan. Stability Analysis of a Parallel Packet Switch with Bufferless Input Demultiplexors[A]. IEEE ICC’01[C], Helsinki, Finland, 2001:850-862.
[40] Walter Wang, Libin Dong and Wayne Wolf. A Distributed Switch Architecture with Dynamic Load-balancing and Parallel Input-Queued Crossbars for Terabit Switch Fabrics[A]. IEEE INFOCOM’02[C], 2002:689-699.
[41] A. Aslam, and K. Christensen. Parallel Packet Switching using Multiplexors with Virtual Input Queues[A]. Proceedings of IEEE LCN[C], Nov. 2002:270-277.
[42] S. Mneimneh, V. Sharma and K.-Y. Siu. Switching using parallel input-output queued switches with no speedup[J]. IEEE/ACM Trans. Networking, Oct. 2002, 10:653-665.
[43] Hyoung-II Lee and Seung-Woo seo. A practical approach for statistical matching of output queueing[J]. IEEE Journal on selected areas in communications, May 2003, 21(4):616-629.
[44] Vaidya A. K. and Pashun M. A. Technology advances in wideband packet switching, Proc. GLOBECOM’88, Hollywood, F.L., 1988, pp.668-671.
[45] Turner J. S. and Wyatt L. F. A packet network architecture for integrated service[A]. Proc. GLOBECOM’83[C]. San Diego, CA, 1983:211-216.
[46] Huang, A. and Knauer S. Starjite. A wideband digital switch[A], Proc. GLOBECOM’84[C]. Atlanta, GA, 1984:121-125.
[47] Kruskat C. P. and M. Snir. The performance of multistage inter-connection nelworks for multiprocessors[J]. IEEE Trans. on Comput, 1983, 32(12):1091-1098.
[48] Cherkassky V. S. Performance evaluation of nonregular multistage interconnectionnetworks[J], IEEE Trans. on Comput, 1988, 37(10):1269-1272.
[49] Kruskal C. P., Snir M. and Weiss A. The distribution of waiting times in docked multislage interconnection networks[J]. IEEE Trans. on Comput, 1988, 37(11):1337-1352.
[50] Lee T. H. Design and Analysis of a new Self-Routing Network[J]. IEEE Trans. on Commun, 1992, 40(1):l7l-177.
[51] Goke. L, Rondey Lipovski, G Jack. Banyan Networks for Partitioning Multiprocessor Systems[A]. In: Proc. 1st Annu. Symp. Comp. Arch[C]. Jerusalem, 1973:22-28.
[52] RaJa J, Shnamugavel S. Performance Studies of Banyan ATM Switching Networks using RS Codes[J]. Journal of the Institution of Engineers (India). Part CP: Computer Engineering Division. 2003, 84:9-14.
[53] Lee Yoo-Young, Jung Jae. Non-blocking Permutation Generator for Banyan Networks[J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2003. E58-A(6): 1480-1486.
[54] Pattavina Achille, Bison Claudio. Connectionless Switching by Asynchronous Banyan Networks[A]. In: Proc. Globlecom1994[C]. San Francisco, 1994:441-447.
[55] Kim H S. GarciaAL. Performance of Buffered Banyan Networks Under Non-uniform Traffic Patterns[J]. IEEE Transaction on Communications, 1990, 38(3):701-710.
[56] M.J.Narasimha. The Batcher-banyan Self-routing Network: Universality and Simplification[J]. IEEE Transaction on Communications, 1988, 36(10):1175-1178.
[57] H. J. Chao, K. Deng, Z. Jing. A Petabit Photonic Packet Switch (P3S)[A]. In: Proc. IEEE INFOCOM2003[C]. Francisco, 2003:1096-1112.
[58] Feng Wang, Wenqi Zhu, Mounir Hamdi. The Central-stage Buffered Clos-network to Emulate an OQ Switch[A]. In: Proc. IEEE Globecom2006[C]. Francisco, 2006:1-5.
[59] Jungang Yang, Zhiliang Qiu. Study on Distributed Scheduling Algorithm in Three-Stage Clos Networks[J]. Journal of Electronics (china), 2006, 34(4):590-594.
[60] Nikos Chrysos, Manolis Katevenisz. Scheduling in Non-Blocking Buffered Three-Stage Switching Fabrics[A]. IEEE Globecom’06[C].Francisco, 2006: 6-13.
[61] F. M. Chiussi, J. G. Kneuer, V. P. Kumar. Low-cost Scalable Switching Solutions for Broadband Networking: The ATLANTA Architecture and Chipset[J]. IEEE Communications Mag, 1997, 35(12): 44-53.
[62] F. Wang and M. Hamdi. Analysis on the Central-stage Buffered Clos-network for packet switching[A].IEEE ICC Proc.[C]. Korea, 2005: 322-335.
[63] F. Wang and M. Hamdi. Scalable Central-stage Buffered Clos Network Packet Switches with QoS[A]. IEEE HPSR Workshop[C]. Poland, 2006:455-468.
[64] S. T. Chuang, A. Goel, N. McKeown, and B. Prabhakar. Matching output queuing with a combined input/output-queued switch[J].IEEE Journal on Selected Areas in Communications, June 1999, 17(6):1030-1039.
[65] P. Krishna, N. Patel, A. Charny, and R. Simcoe. On the speedup required forwork-conversing crossbar switches[J]. IEEE Journal on Selected Areas in Communications, June 1999, 17(6):1057-1066.
[66] B. Prabhakar and N. McKeown. On the speedup required for combined input and output queued switching[J]. Automatica, Dec. 1999, 35(12):1909-1920.
[67] Y. Oie, M. Murata, K. Kubota, and H. Miyahara. Effect of speedup in nonblocking packet switch[A]. In Proc. ICC’89[C]. Boston, Massachusetts, June 1989:410-415.
[68] J. G. Dai and B. Prabhakar. The throughput of data switches with and without speedup[A]. In Proc. IEEE INFOCOM’00[C]. Tel Aviv, Israel, Mar. 2000:556-564.
[69] A. L. Gupta. Analysis of a packet switch with input and output buffers and speed constraints[A]. IEEE INFOCOM’91[A]. Florida, Apr. 1991, 2:694-700.
[70] J. S.-C. Chen and T. E. Stern. Throughput analysis, optimal buffer allocation, and traffic imbalance study of a generic nonblocking packet switch[J]. IEEE Journal on Selected Areas in Communications, Apr. 1991, 9(3): 439-449.
[71] P. Goli and V. Kumar. Performance of Crosspoint Buffered ATM Switch Fabric[A]. Proceedings of IEEE INFOCOM[C], May 1992:426-435.
[72] B. Zhou and M. Atiquzzaman. Performance of ATM Switch Fabrics Using Cross-Point Buffers[A], Proceedings of IEEE INFOCOM[C]. April 1995:16-23.
[73] V. Singhal and R. Le. High-Speed Buffered Crossbar Switch Design Using Virtex-EM Devices[C]. Xilinx Corp. March 14, 2000.
[74] I. Radusinovic and M. Pejanovic. Impact of Scheduling Algorithms on Performances of Buffered Crossbar Switch Fabrics[A]. IEEE ICC[C].April 2002:2416-2420.
[75] K. Yoshigoe and K. J. Christensen. A parallel-polled virtual output queued switch with a buffered crossbar[A]. In Proc. IEEE HPSR’01[C]. May 2001: 271-275.
[76] Y. Li, S. Panwar, and H. J. Chao. The dual round-robin matching switch with exhaustive service[A]. In IEEE HPSR’02[C]. Kobe, Japan, May 2002:362-373.
[77] R. J.Wilson. Introduction to Graph Theory[M].NewYork:Academic Press, 1972.
[78] Berge C. The theory of graphs and its applications[M]. Wiley Sons Press, 1962.
[79] Bondy J. A. Graph Theory with Applications[M]. North Holland, New York, 1976.
[80] R. Cole and J. Hopcroft. On edge coloring bipartite graph[J]. SIAM Journal on Computing, 1982, 11(3):540-546.
[81] J. Hopcroft and R. Karp. An n 5/2 algorithm for maximum matchings in bipartite graphs[J]. SIAM Journal on Computing, 1973, 2(4):225-231.
[82] C. Chang, D. Lee, and Y. Jou. Load balanced Birkhoff–von Neumann switche. Part II: Multistage buffering[M]. Computer Communications, 2002, 25(6): 623–634.
[83] Rojas-Cessa, E. Oki, and H. J. Chao. CIXOB-k: Combined input-crosspoint-output buffered packet switch[A]. IEEE GLOBECOM’01[C], Texas, 2001:2654-2660.
[84] B. Klein and J. Garza. Agere systems-communications optimized payload plus network processor architecture[A]. In Network Processor Design: Issues and Practices[C]. MorganKaufmann, San Francisco, California, 2002, 1:219-233.
[85] P. Crowley, M. E. Fiuczynski, J.-L. Baer and B. N. Bershad. Characterizing processor architectures for programmable network interface[A]. In Proc. International Conference on Supercomputing[C], Santa Fe, New Mexico, May 2000:54-65.
[86] S. Iyer and N. McKeown. Making parallel packet switches practical[A]. In Proc. IEEE INFOCOM’01[C]. Anchorage, Alaska, Apr.2000, 3:1680-1687.
[87] A. Mekkittikul, N. McKeown. A Practical Scheduling Algorithm for Achieving 100% Throughput in Input-queued Switches[A]. Proceeding of Infocom[C], San Francisco, USA, 2004: 792-799.
[88] S. T. Chuang, N. Mckeown. Practical algorithm for performance guarantees in buffered crossbars[A]. IEEE INFOCOM’05[C]. Florida, Mar. 2005, 2: 981-991.
[89] F. A. Marsan, A. Bianco and E. Neri. Packet scheduling in input queued cell-based switches[A]. IEEE INFOCOM’01[C]. Alaska, Apr. 2001, 2:1085-1094.
[90] F. A. Marsan, A. Bianco and F. Neri. Packet-mode scheduling in input-queued cell-based switches[J]. IEEE/ACM Trans. on Networking, Oct. 2002, 10(5):666–678.
[91] N. McKeown. Scheduling algorithms for input-queued cell switches[D]. Ph.D. Thesis, UC Berkeley, May 1995.
[92] N. McKeown. iSLIP: a scheduling algorithm for input-queued switches[J]. IEEE/ACM Transactions on Networking, Apr. 1999, 7(2):188-201.
[93] R. T.Vineet and A. Shelat. PMC-Sierra, Inc-ClassiPI[A]. In Network Processor Design, Issues and Practices[M]. Morgan Kaufmann, California, 2002, 1: 291-305.
[94] M. J. Miller. IDT network search engine with QDR LA-1 interface[A].In Network Processor Design, Issues and Practices[M]. California, 2003, 2:365-384.
[95] A. Parekh and R. Gallager. A generalized processor sharing approach to flow control in integrated services networks: the single node case[J]. IEEE/ACMTransactions on Networking, June 1993, 1(2):344-357.
[96] A. Parekh and R. Gallager. A generalized processor sharing approach to flow control in integrated services networks: the multiple node case[J]. IEEE/ACM Transactions on Networking, Apr. 1994, 2(2):137-150.
[97] H. T. Kung, T. Blackwell, and A. Chapman. Credit-based flow control for ATM networks: Credit update protocol, adaptive credit allocation, and statistical multiplexing[A].In Proc. ACM SIGCOMM[C]. London, Aug. 1994:101-115.
[98] I. Keslassy, S.-T. Chuang, K. Yu, et al. Scaling internet routers using optics[A]. In Proc. Of ACM SIGCOMM 2003[C].Karlsruhe, Germany, August 2003:189–200. Also in Computer Communication Review, October 2003, 33(4):189-200.
[99] Sundar Iyer and Nick McKeown. Analysis of the Parallel Packet Switch Architecture[A]. April 2003:256-262.
[100] Y. Dong, P. Yi and Y. Guo. On the Load Balancing of a Parallel Switch with InputQueues[A]. PDCAT 2003[C]. Chengdu China, Sept. 2003:301-305.
[101] D. A. Khotimsky, S. Krishnan. Stability Analysis of a Parallel Packet Switch with Bufferless Input Demultiplexors[A]. IEEE ICC’01[C]. Finland, 2001:223-228.
[102] Yi Peng, D Yuguo and G Yunfei. Analysis of Stable working for PPS with Bufferless Input Demultiplexers[J].HIGH TECHNOLOGY Letters, Aug. 2003, 13 (8):14-18.
[103] Qi Wangdong, Tian Chang, Chen Hua, Xu Bo. Reexamining the stability of a parallel switch with bufferless input demultiplexers[A]. ICCT 2003, Beijing, 2003: 514-520.
[104] L. Tassiulas. Linear complexity algorithms for maximum throughput in radio networks and input queued switches[A]. In Proc. IEEE INFOCOM 98[C]. San Francisco, California, Mar. 1998, 2:533-539.
[105] D. Stiliadis. Traffic scheduling in packet-switched networks: analysis, design, and implementation[D]. Ph.D. Dissertation, University of California, June 1996.
[106] J. Bennett, D. C. Stephens, and H. Zhang. High speed, scalable, and accurate implementation of fair queueing algorithms inATM networks[A]. In Proc. IEEE ICNP’97[C]. Atlanta, Georgia,1997:7-14.
[107] M. M. Buddhikot, S. Suri, and M.Waldvogel. Space decomposition techniques for fast layer-4 switching[J]. In Conf. Protocols for High Speed Networks, Holmdel, New Jersey, Aug. 1999, 66(6):277-283.
[108] Cherry S. The Battle for Broadband (Internet protocol television) [J]. IEEE Spectrum, 2006, 42(1):24-29.
[109]刘衡竹,陈旭灿,陈福接,视频服务器中视频流存储分配算法的研究.计算机学报,1998, 21(4): 289-295
[110] H. B. Newman, M. H. Ellisman, J. A. Orcutt. Data-intensive Escience Frontier Research[J]. Commun. of the ACM, 2005, 46(11):68-77.
[111] Anderson T, Owicki S, Saxes J, Thacker C. High Speed Switch Scheduling for Local Area Networks[J]. ACM Transactions on Computer Systems, 1993, 11(4): 319-352.
[112]林闯,单志广,盛立杰,吴建平. Internet区分服务及其几个热点问题研究[J].计算机学报,2000,23(4): 419-443.
[113] Yue Chen, Yuguo Dong. A Packet-Order-Keeping-Demultiplexer in Parallel-Structure Router Based on Flow Classification[A]. The International Conference on Computer Networks and Mobile Computing[C]. Shanghai, China, 2003:156-163.
[2] F. Abel, C. Minkenberg, R. Luijten, M. Gusat, I. Iliadis: A Four-Terabit Packet Switch Supporting Long Round-Trip Times[J]. IEEE Micro Magazine, Jan-Feb 2003, 23(1):10-24.
[3] R. Ryf et al.1296-port MEMS transparent optical crossconnect with 2.07 petabit/s switch capacity[A]. In Proc. Optical Fiber Communication Conference and Exhibitp[C].Anaheim, California, Mar. 2001, 4:PD28-P1.
[4] K. Yamakoshi, K. Nakai, and N. Yamanaka. 5-Tbit/s frame-based ATM switching system using 2.5-Gbit/s/spl times/8 optical WDM[A]. In Proc. IEEE International Conference on Communications[C]. Helsinki, Finland, June 2001, 10:3117-3121.
[5] N. Huang, G. Liaw, and C. Wang. A novel all-optical transport network with time-shared wavelength channels[J]. IEEE Journal on Selected Areas in Communications, Oct. 2000, 18(10):1863-1875.
[6] Y. Chai, J. H. Chen, F. S. Choa, J. P. Zhang, J. Y. Fan, and W. Lin. Scalable and modularized optical random access memories for optical packet switching networks[A]. In Proc. CLEO’98[C]. San Francisco, California, May 1998:397-402.
[7] J. Leuthold, B. Mikkelsen and G. Raybon.All-optical wavelength conversion between 10 and 100 Gb/s with SOA delayed-interference configuration[J].Optical and Quantum Electronic. 2001, 33(7):939-952.
[8] S. Nakamura, Y. Ueno, and K. Tajima.168-Gb/s all-optical wavelength conversion with a symmetric-Mach-Zehnder-type switch[J]. IEEE Photonics Technology Letters. Oct. 2001, 13(10):1091-1093.
[9] A. Jajszczyk, Nonblocking, repackable, and rearrangeable Clos networks: fifty years of the theory evolution[J]. IEEE Communications Magazine, 2003, 41(10):28-33 .
[10] H. J. Chao, Z. Jing, and S.Y. Liew. Matching algorithms for three-stage bufferless Clos network switches[J]. IEEE Communications Magazine, Oct. 2003,41(10):46-54.
[11] M. Gupta and S. Singh. Greening of the Internet[A]. In Proc. ACM SIGCOMM03[C], Karlsruhe, Germany, Aug. 2003:19-26.
[12] Kumar Rangonothan. Trustworthy pervasive computing:The hard security problems[A]. IEEE Proceedings on Pervasive Computing and Communications Workshops[C]. Orlando, USA: IEEE, 2004:117-121.
[13] M Crovela, E Kolaczyk. Graph Wavelets for Spatial Traffic Analysis[A]. 2003 IEEE Proceeding of Infocom [C]. San Francisco, USA: IEEE, 2003:1848-1857.
[14] B Y Zhao, L Huang, J Stribling, S C Rhea, A D Joseph, J D Kubiatowicz.Tapestry:a global-scale overlay for rapid service deployment[J]. IEEE Journal on Selected Areas inCommunications. 2004, 22(1):41-53.
[15] Honglu Yeom, Wasung Kim. An efficient multicast mechanism for data loss prevention[A]. The 7th International Conference on Advanced Communication Technology[C]. Phoenix Park, Korea: IEEE, 2005:497-502.
[16] Gkantsidis C, Rodriguez P R. Network coding for large scale content distribution[A]. IEEE Proceeding of Infocom [C]. Miami, FL, USA: IEEE, 2005: 2235-2245.
[17] F. M. Chiussi, J. G. Kneuer, andV. P. Kumar. Low cost scalable switching solutions for broadband networking: the ATLANTA architecuture and chipset[J]. IEEE Communications Magazine, Dec. 1997, 35(12):44-53.
[18] C. S. Chang, D. Lee, and Y. J. Shih. Mailbox switch: A scalable two-stage switch architecture for conflict resolution of ordered packets[A]. In Proc. IEEE INFOCOM 04[C]. Hong Kong, Mar. 2004, 3:1995-2006.
[19] H. J. Chao, J. S. Park, S. Artan, S. Jiang, and G. Zhang. TrueWay: A highly scalable multi-plane multi-stage buffered packet switch[A]. In Proc. IEEE Workshop on High Performance Switching and Routing[C]. Hong Kong, May 2005:246-253.
[20] E. Oki, Z. Jing, R. Rojas-Cessa, and H. J. Chao. Concurrent round-robin-based dispatching schemes for Clos-network switches[J]. IEEE/ACM Transactions on Networking, Dec. 2002, 10(6):830-844.
[21] Chuan-Bi Lin and Roberto Rojas-Cessa. Frame Occupancy-Based Dispatching Schemes for Buffered Three-stage Clos-Network Switches[A]. IEEE 7th Malaysia International Conference on Communications[C]. Nov. 2005:354-362.
[22] Chao H J, Jinsoo Park. Flow Control in a Multi-Plane Multi-Stage Buffered Packet Switch[A]. IEEE International Conference on HPSR[C]. June, 2007:1-6.
[23] Rojas-Cessa R, Oki E, Chao H. J. Concurrent fault detection for a multiple-plane packet switch[J]. IEEE/ACM Transactions on Networking, 2003,11(4): 616-627.
[24] H. J. Chao. Next generation routers[J]. IEEE Proceedings, Sept. 2002, 90(9):1518-1558.
[25] H. J. Chao. Saturn: a terabit packet switch using dual round-robin[J].IEEE Communications magazine, Dec. 2000, 38(12):78-84.
[26] I. Keslassy and N. McKeown. Maintaining packet order in two-stage switches[A]. In Proc. IEEE INFOCOM’02[C]. NewYork, June 2002, 2:1032-1041.
[27] Y. Shen, S. Jiang, S. Panwar, and H. J. Chao. Byte-Focal: a practical load balanced switch[A].In Proc. IEEE Workshop on High Performance Switching and Routing (HPSR05)[C]. Hong Kong, May 2005:6-12.
[28] C. S. Chang, D. Lee, and Y. Jou. Load balanced Birkhoff-von Neumann switches. Part I: One-stage buffering[J ].Computer Communications, 2002, 25(6):611-622.
[29] S. Jiang, G. Hu, S.Y. Liew, and H. J. Chao. Scheduling algorithms for shared fiber-delay-line optical packet switches, Part II: The 3-stage Clos-Network case[J]. IEEE Journal of Lightwave Technology, Apr. 2005, 23(4):1601-1609.
[30] R. Sudan and W. Mukai. Introduction to the Cisco CRS-1 Carrier Routing System[M]. Cisco Systems Inc., Jan.1994.
[31] Implementing a Flexible Hardware-based Router for the New IP Infrastructure, Juniper Inc., White Paper.
[32] Hwang K, Xu Z. Scalable parallel computers for real-time signal processing[J]. IEEE Signal Processing, 1996, 13(4):50-66.
[33] F. T. Leighton. Introduction to Parallel Algorithms and Architectures: Arrays. Trees. Hypercubes[M]. Morgan Kaufmann, San Francisco, California, 1992.
[34] M. J. Karol, M. Hluchyj, and S. Morgan. Input vs. output queuing on a space-division packet switch[J]. IEEE Trans. on Communications, Dec. 1987, 35(12):1347-1356.
[35] C. Clos. A study of non-blocking switching network[J]. Bell System Technical Journal, Mar. 1953, 32(2):404-426.
[36] V. E. Benes. Optimal rearrangeable multistage connecting networks[J].Bell System Technical Journal, July 1964, 43:1641-1656.
[37] S.Iyer, N.McKeown. Analysis of a packet switch with the memories running slower than the line rate[A]. INFOCOM’00[C]. Tel Aviv, Israel, 2000, 2:529-537.
[38] S.Iyer, N.McKeown. Making parallel switches practical[A]. INFOCOM’00[C]. Tel Aviv, Israel, 2001, 3:1680-1687.
[39] D. A. Khotimsky, S. Krishnan. Stability Analysis of a Parallel Packet Switch with Bufferless Input Demultiplexors[A]. IEEE ICC’01[C], Helsinki, Finland, 2001:850-862.
[40] Walter Wang, Libin Dong and Wayne Wolf. A Distributed Switch Architecture with Dynamic Load-balancing and Parallel Input-Queued Crossbars for Terabit Switch Fabrics[A]. IEEE INFOCOM’02[C], 2002:689-699.
[41] A. Aslam, and K. Christensen. Parallel Packet Switching using Multiplexors with Virtual Input Queues[A]. Proceedings of IEEE LCN[C], Nov. 2002:270-277.
[42] S. Mneimneh, V. Sharma and K.-Y. Siu. Switching using parallel input-output queued switches with no speedup[J]. IEEE/ACM Trans. Networking, Oct. 2002, 10:653-665.
[43] Hyoung-II Lee and Seung-Woo seo. A practical approach for statistical matching of output queueing[J]. IEEE Journal on selected areas in communications, May 2003, 21(4):616-629.
[44] Vaidya A. K. and Pashun M. A. Technology advances in wideband packet switching, Proc. GLOBECOM’88, Hollywood, F.L., 1988, pp.668-671.
[45] Turner J. S. and Wyatt L. F. A packet network architecture for integrated service[A]. Proc. GLOBECOM’83[C]. San Diego, CA, 1983:211-216.
[46] Huang, A. and Knauer S. Starjite. A wideband digital switch[A], Proc. GLOBECOM’84[C]. Atlanta, GA, 1984:121-125.
[47] Kruskat C. P. and M. Snir. The performance of multistage inter-connection nelworks for multiprocessors[J]. IEEE Trans. on Comput, 1983, 32(12):1091-1098.
[48] Cherkassky V. S. Performance evaluation of nonregular multistage interconnectionnetworks[J], IEEE Trans. on Comput, 1988, 37(10):1269-1272.
[49] Kruskal C. P., Snir M. and Weiss A. The distribution of waiting times in docked multislage interconnection networks[J]. IEEE Trans. on Comput, 1988, 37(11):1337-1352.
[50] Lee T. H. Design and Analysis of a new Self-Routing Network[J]. IEEE Trans. on Commun, 1992, 40(1):l7l-177.
[51] Goke. L, Rondey Lipovski, G Jack. Banyan Networks for Partitioning Multiprocessor Systems[A]. In: Proc. 1st Annu. Symp. Comp. Arch[C]. Jerusalem, 1973:22-28.
[52] RaJa J, Shnamugavel S. Performance Studies of Banyan ATM Switching Networks using RS Codes[J]. Journal of the Institution of Engineers (India). Part CP: Computer Engineering Division. 2003, 84:9-14.
[53] Lee Yoo-Young, Jung Jae. Non-blocking Permutation Generator for Banyan Networks[J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2003. E58-A(6): 1480-1486.
[54] Pattavina Achille, Bison Claudio. Connectionless Switching by Asynchronous Banyan Networks[A]. In: Proc. Globlecom1994[C]. San Francisco, 1994:441-447.
[55] Kim H S. GarciaAL. Performance of Buffered Banyan Networks Under Non-uniform Traffic Patterns[J]. IEEE Transaction on Communications, 1990, 38(3):701-710.
[56] M.J.Narasimha. The Batcher-banyan Self-routing Network: Universality and Simplification[J]. IEEE Transaction on Communications, 1988, 36(10):1175-1178.
[57] H. J. Chao, K. Deng, Z. Jing. A Petabit Photonic Packet Switch (P3S)[A]. In: Proc. IEEE INFOCOM2003[C]. Francisco, 2003:1096-1112.
[58] Feng Wang, Wenqi Zhu, Mounir Hamdi. The Central-stage Buffered Clos-network to Emulate an OQ Switch[A]. In: Proc. IEEE Globecom2006[C]. Francisco, 2006:1-5.
[59] Jungang Yang, Zhiliang Qiu. Study on Distributed Scheduling Algorithm in Three-Stage Clos Networks[J]. Journal of Electronics (china), 2006, 34(4):590-594.
[60] Nikos Chrysos, Manolis Katevenisz. Scheduling in Non-Blocking Buffered Three-Stage Switching Fabrics[A]. IEEE Globecom’06[C].Francisco, 2006: 6-13.
[61] F. M. Chiussi, J. G. Kneuer, V. P. Kumar. Low-cost Scalable Switching Solutions for Broadband Networking: The ATLANTA Architecture and Chipset[J]. IEEE Communications Mag, 1997, 35(12): 44-53.
[62] F. Wang and M. Hamdi. Analysis on the Central-stage Buffered Clos-network for packet switching[A].IEEE ICC Proc.[C]. Korea, 2005: 322-335.
[63] F. Wang and M. Hamdi. Scalable Central-stage Buffered Clos Network Packet Switches with QoS[A]. IEEE HPSR Workshop[C]. Poland, 2006:455-468.
[64] S. T. Chuang, A. Goel, N. McKeown, and B. Prabhakar. Matching output queuing with a combined input/output-queued switch[J].IEEE Journal on Selected Areas in Communications, June 1999, 17(6):1030-1039.
[65] P. Krishna, N. Patel, A. Charny, and R. Simcoe. On the speedup required forwork-conversing crossbar switches[J]. IEEE Journal on Selected Areas in Communications, June 1999, 17(6):1057-1066.
[66] B. Prabhakar and N. McKeown. On the speedup required for combined input and output queued switching[J]. Automatica, Dec. 1999, 35(12):1909-1920.
[67] Y. Oie, M. Murata, K. Kubota, and H. Miyahara. Effect of speedup in nonblocking packet switch[A]. In Proc. ICC’89[C]. Boston, Massachusetts, June 1989:410-415.
[68] J. G. Dai and B. Prabhakar. The throughput of data switches with and without speedup[A]. In Proc. IEEE INFOCOM’00[C]. Tel Aviv, Israel, Mar. 2000:556-564.
[69] A. L. Gupta. Analysis of a packet switch with input and output buffers and speed constraints[A]. IEEE INFOCOM’91[A]. Florida, Apr. 1991, 2:694-700.
[70] J. S.-C. Chen and T. E. Stern. Throughput analysis, optimal buffer allocation, and traffic imbalance study of a generic nonblocking packet switch[J]. IEEE Journal on Selected Areas in Communications, Apr. 1991, 9(3): 439-449.
[71] P. Goli and V. Kumar. Performance of Crosspoint Buffered ATM Switch Fabric[A]. Proceedings of IEEE INFOCOM[C], May 1992:426-435.
[72] B. Zhou and M. Atiquzzaman. Performance of ATM Switch Fabrics Using Cross-Point Buffers[A], Proceedings of IEEE INFOCOM[C]. April 1995:16-23.
[73] V. Singhal and R. Le. High-Speed Buffered Crossbar Switch Design Using Virtex-EM Devices[C]. Xilinx Corp. March 14, 2000.
[74] I. Radusinovic and M. Pejanovic. Impact of Scheduling Algorithms on Performances of Buffered Crossbar Switch Fabrics[A]. IEEE ICC[C].April 2002:2416-2420.
[75] K. Yoshigoe and K. J. Christensen. A parallel-polled virtual output queued switch with a buffered crossbar[A]. In Proc. IEEE HPSR’01[C]. May 2001: 271-275.
[76] Y. Li, S. Panwar, and H. J. Chao. The dual round-robin matching switch with exhaustive service[A]. In IEEE HPSR’02[C]. Kobe, Japan, May 2002:362-373.
[77] R. J.Wilson. Introduction to Graph Theory[M].NewYork:Academic Press, 1972.
[78] Berge C. The theory of graphs and its applications[M]. Wiley Sons Press, 1962.
[79] Bondy J. A. Graph Theory with Applications[M]. North Holland, New York, 1976.
[80] R. Cole and J. Hopcroft. On edge coloring bipartite graph[J]. SIAM Journal on Computing, 1982, 11(3):540-546.
[81] J. Hopcroft and R. Karp. An n 5/2 algorithm for maximum matchings in bipartite graphs[J]. SIAM Journal on Computing, 1973, 2(4):225-231.
[82] C. Chang, D. Lee, and Y. Jou. Load balanced Birkhoff–von Neumann switche. Part II: Multistage buffering[M]. Computer Communications, 2002, 25(6): 623–634.
[83] Rojas-Cessa, E. Oki, and H. J. Chao. CIXOB-k: Combined input-crosspoint-output buffered packet switch[A]. IEEE GLOBECOM’01[C], Texas, 2001:2654-2660.
[84] B. Klein and J. Garza. Agere systems-communications optimized payload plus network processor architecture[A]. In Network Processor Design: Issues and Practices[C]. MorganKaufmann, San Francisco, California, 2002, 1:219-233.
[85] P. Crowley, M. E. Fiuczynski, J.-L. Baer and B. N. Bershad. Characterizing processor architectures for programmable network interface[A]. In Proc. International Conference on Supercomputing[C], Santa Fe, New Mexico, May 2000:54-65.
[86] S. Iyer and N. McKeown. Making parallel packet switches practical[A]. In Proc. IEEE INFOCOM’01[C]. Anchorage, Alaska, Apr.2000, 3:1680-1687.
[87] A. Mekkittikul, N. McKeown. A Practical Scheduling Algorithm for Achieving 100% Throughput in Input-queued Switches[A]. Proceeding of Infocom[C], San Francisco, USA, 2004: 792-799.
[88] S. T. Chuang, N. Mckeown. Practical algorithm for performance guarantees in buffered crossbars[A]. IEEE INFOCOM’05[C]. Florida, Mar. 2005, 2: 981-991.
[89] F. A. Marsan, A. Bianco and E. Neri. Packet scheduling in input queued cell-based switches[A]. IEEE INFOCOM’01[C]. Alaska, Apr. 2001, 2:1085-1094.
[90] F. A. Marsan, A. Bianco and F. Neri. Packet-mode scheduling in input-queued cell-based switches[J]. IEEE/ACM Trans. on Networking, Oct. 2002, 10(5):666–678.
[91] N. McKeown. Scheduling algorithms for input-queued cell switches[D]. Ph.D. Thesis, UC Berkeley, May 1995.
[92] N. McKeown. iSLIP: a scheduling algorithm for input-queued switches[J]. IEEE/ACM Transactions on Networking, Apr. 1999, 7(2):188-201.
[93] R. T.Vineet and A. Shelat. PMC-Sierra, Inc-ClassiPI[A]. In Network Processor Design, Issues and Practices[M]. Morgan Kaufmann, California, 2002, 1: 291-305.
[94] M. J. Miller. IDT network search engine with QDR LA-1 interface[A].In Network Processor Design, Issues and Practices[M]. California, 2003, 2:365-384.
[95] A. Parekh and R. Gallager. A generalized processor sharing approach to flow control in integrated services networks: the single node case[J]. IEEE/ACMTransactions on Networking, June 1993, 1(2):344-357.
[96] A. Parekh and R. Gallager. A generalized processor sharing approach to flow control in integrated services networks: the multiple node case[J]. IEEE/ACM Transactions on Networking, Apr. 1994, 2(2):137-150.
[97] H. T. Kung, T. Blackwell, and A. Chapman. Credit-based flow control for ATM networks: Credit update protocol, adaptive credit allocation, and statistical multiplexing[A].In Proc. ACM SIGCOMM[C]. London, Aug. 1994:101-115.
[98] I. Keslassy, S.-T. Chuang, K. Yu, et al. Scaling internet routers using optics[A]. In Proc. Of ACM SIGCOMM 2003[C].Karlsruhe, Germany, August 2003:189–200. Also in Computer Communication Review, October 2003, 33(4):189-200.
[99] Sundar Iyer and Nick McKeown. Analysis of the Parallel Packet Switch Architecture[A]. April 2003:256-262.
[100] Y. Dong, P. Yi and Y. Guo. On the Load Balancing of a Parallel Switch with InputQueues[A]. PDCAT 2003[C]. Chengdu China, Sept. 2003:301-305.
[101] D. A. Khotimsky, S. Krishnan. Stability Analysis of a Parallel Packet Switch with Bufferless Input Demultiplexors[A]. IEEE ICC’01[C]. Finland, 2001:223-228.
[102] Yi Peng, D Yuguo and G Yunfei. Analysis of Stable working for PPS with Bufferless Input Demultiplexers[J].HIGH TECHNOLOGY Letters, Aug. 2003, 13 (8):14-18.
[103] Qi Wangdong, Tian Chang, Chen Hua, Xu Bo. Reexamining the stability of a parallel switch with bufferless input demultiplexers[A]. ICCT 2003, Beijing, 2003: 514-520.
[104] L. Tassiulas. Linear complexity algorithms for maximum throughput in radio networks and input queued switches[A]. In Proc. IEEE INFOCOM 98[C]. San Francisco, California, Mar. 1998, 2:533-539.
[105] D. Stiliadis. Traffic scheduling in packet-switched networks: analysis, design, and implementation[D]. Ph.D. Dissertation, University of California, June 1996.
[106] J. Bennett, D. C. Stephens, and H. Zhang. High speed, scalable, and accurate implementation of fair queueing algorithms inATM networks[A]. In Proc. IEEE ICNP’97[C]. Atlanta, Georgia,1997:7-14.
[107] M. M. Buddhikot, S. Suri, and M.Waldvogel. Space decomposition techniques for fast layer-4 switching[J]. In Conf. Protocols for High Speed Networks, Holmdel, New Jersey, Aug. 1999, 66(6):277-283.
[108] Cherry S. The Battle for Broadband (Internet protocol television) [J]. IEEE Spectrum, 2006, 42(1):24-29.
[109]刘衡竹,陈旭灿,陈福接,视频服务器中视频流存储分配算法的研究.计算机学报,1998, 21(4): 289-295
[110] H. B. Newman, M. H. Ellisman, J. A. Orcutt. Data-intensive Escience Frontier Research[J]. Commun. of the ACM, 2005, 46(11):68-77.
[111] Anderson T, Owicki S, Saxes J, Thacker C. High Speed Switch Scheduling for Local Area Networks[J]. ACM Transactions on Computer Systems, 1993, 11(4): 319-352.
[112]林闯,单志广,盛立杰,吴建平. Internet区分服务及其几个热点问题研究[J].计算机学报,2000,23(4): 419-443.
[113] Yue Chen, Yuguo Dong. A Packet-Order-Keeping-Demultiplexer in Parallel-Structure Router Based on Flow Classification[A]. The International Conference on Computer Networks and Mobile Computing[C]. Shanghai, China, 2003:156-163.