摘要
近年来，Internet经历了飞速的发展，已经深入到我们社会和生活的方方面面，从商务到通信，从教育到娱乐。许多新的应用不断产生，其中点对多点的数据传输应用，正变得越来越重要，如网络视频会议、网络音频／视频广播、股市行情发布、多媒体远程教育、CSCW协同计算、在线信息恢复，软件或代理缓存更新等。这就带来了带宽的急剧消耗和网络拥挤问题，而组播正是一种解决点到多点通信的非常有效的方式。在过去几年中，组播传输机制已经成为一个活跃的研究领域，IRTF和IETF(因特网研究和工程任务小组)在组播传输协议研究、开发、标准化等方面作了大量的工作。
然而，组播技术在Internet上的大规模开发所面临的一个主要挑战就是拥塞控制，为了实现传输层组播协议的开发，组播拥塞控制是一个必须深入研究的问题。IRTF已将组播拥塞控制作为一个优先发展的领域，同时IETF也指出在标准化组播协议之前，必须有效地解决拥塞控制问题。最近的研究和标准化过程主要致力于解决这个问题。
本文首先概要介绍了组播拥塞产生的背景、原因以及实施拥塞控制的必要性，探讨了组播拥塞控制技术的研究与发展现状，并分析了当前拥塞控制中存在的主要问题。
第2章着重研究了组播拥塞控制的几个关键问题以及相应的解决方案。首先深入分析了组播拥塞控制中存在的TCP友好、可扩展性、公平性等问题的产生的原因以及各种解决方法。然后讨论了组播拥塞控制算法分类的标准，比较和分析了现有组播拥塞控制算法的优缺点，指出了其中的不足之处。针对上述算法中存在的动态性、灵敏性以及由之引起的公平性等问题，本文第3章设计了一种新的基于速率的组播拥塞控制机制——RBMCC，该算法利用积极的显式拥塞指示，基于代表的反馈机制，通过调节包与包的发送间隔来改变数据的发送速率，动态地自适应网络拥塞状态的改变。
为了验证算法的合理性和有效性，本文在第4章中对RBMCC进行了大量的仿真实验来评价算法多方面的性能，仿真结果表明，与以往算法相比，RBMCC提高了动态性，对网络拥塞状态的变化能做出灵敏的反应，同时对协议内部和协议之间的公平性以及协议本身的可扩展性有较好的改善。
尽管所有的组播应用都要求通过拥塞控制机制来保证网络的安全性，但是不同的应用在数据传输的速度，质量和一致性上有不同的要求。例如实时视频音频等要求速度保证，而软件分发等应用对可靠性要求更高。因此，对不同类型的应用需要设计不同的方法。然而目前的许多组播传输协议中都没有提供明确的拥塞控制机制。本文中提出的RBMCC主要为大块数据可靠传输类型的组播应用来解决拥塞控制方面的问题。在第5章中研究了RBMCC在组播文件传输协议MFTP中的应用，提出了基于MFTP的TCP友好组播拥塞控制机制MFTP-CC，通过仿真实验可知，与原先的MFTP相比，降低了数据丢失率，提高了组播会话的有效吞吐量，同时改善了TCP友好性。
山东师范大学硕士学位论文
NS是目前国际上应用广泛的网络仿真软件，在分析和评价网络性能方面发挥了重要
作用，本文所有实验均是在NS中进行仿真分析的。
本文在组播拥塞控制技术方面进行了探讨，希望能够对组播拥塞控制技术的发展起
一定的推动作用。
The global information infrastructure has witnessed explosive growth in recent years. It has transformed society and pervaded every aspect of our lives, from business and communication to education and entertainment. This has given rise to an ever-increasing need to new applications, and especially applications involving the reliable transfer of large volumes of data from a source to multiple destinations across wide-area networks are expected to become increasingly important in the near future. A few examples are point-to-multipoint ftp, news distributions, Web caching and software updates. Multicast technology promises to enhance the capabilities of wide-area networks for supporting these applications. Multicast transport mechanisms have been a topic of intense research and development efforts over the past couple of years. Both the Internet Engineering and Internet Research Task Forces (IETF and IRTF) have been heavily involved in coordinating multicast transport protocol research, development and standar
dization.
However, congestion control for multicast protocols has emerged as one of the biggest challenges in the large-scale deployment of multicast applications in the Internet. It also is a hard problem and an active research area. Since developing congestion control mechanisms is crucial to enable reliable multicast transport protocols to be deployed for the Internet, the IRTF Reliable Multicast working group has considered it a priority area. At present, there are no standardized, Internet-based multicast transport protocols that provide effective, dynamic congestion control methods for safe wide-scale deployment of end-to-end rate adaptive applications. The IETF has pointed out that effective congestion control mechanisms must be proposed before standardizing multicast protocols. Recent researches and standardization efforts are addressing these issues.
In this paper, Chapter 1 gives a general introduction to multicast congestion control. First the background and the cause of multicast congestion are introduced, and then the necessity of implementing multicast congestion control is analyzed. We also discuss the research work related to multicast congestion control. Finally existing problems in current multicast congestion control are proposed.
Chapter 2 focuses on the principal problems such as TCP-friendly, scalability, fairness, and discusses kinds of solutions. Then we describe the lastest researches and developments on multicast congestion control algorithms and classify them from different aspects. Furthermore,
different algorithms are analyzed and compared, and some problems are pointed out. To order to solve above problems, we design a novel rate-based multicast congestion control scheme - RBMCC, which uses the active explicit congestion indication and representative-based feedback control scheme to inform the source of the status of the network, and alternate the send rate by adjusting the packet intervals between packets. The goal of the dynamic congestion control algorithm is to make the entire system responsive to the changes as rapidly as possible in the offered loads or available bandwidth without getting into an oscillating behavior.
We also present a number of simulations to demonstrate and evaluate the efficiency and performance of RBMCC in Chapter 4, including analysis TCP fairness, responsiveness, scalability and so on. The simulation results show that RBMCC improves the dynamics and sensitivity to response, and can adequately make use of the available resource of the network . Besides, it also has good TCP-friendliness.
Although congestion control is required by all applications to ensure network safety, different applications have various constraints in speed, quality and consistency of data delivery. For example, real-time video applications can trade quality for speed, while applications for software distributions can trade latency for reliability. One can not make a single multicast congestion control scheme to meet requirements of all applications. RBMCC is to a
引文
[1] V.Jacobson, J.Michael. Congestion avoidance and control. IEEE/ACM Transaction Networking, 1988,6(3):314-329
[2] D.Bersekas and R.Gallager. Data Networks. Prentice-Hall 1987
[3] Nagle J. Congestion Control in IP/TCP Internetworks. RFC 896, January 1984
[4] S.Deering. Host extensions for IP multicasting. RFC1112, Jan. 1989
[5] S.Floyd and V.Jacobson. Connection with multiple congested gateways in packet-switched networks, Part I: One-way traffic. ACM Computer Communication Review, 21(5):30-47, Aug. 1991
[6] A.Mankin, A.Romanow, S.Bradner and V.Paxson. IETF criteria for evaluating reliable multicast transport and application protocols. IETF RFC2357, June 1998.
[7] K.Obraczka. Multicast Transport Mechanisms: A Survey and Taxonomy. To appear in IEEE Communications, 1998.
[8] S.Paul, K.K.Sabnani, J.C.Lin, and S.Bhattacharyya. Reliable multicast transport protocol. IEEE Journal on Selected Areas in Communications, April 1997,15(3):407-421.
[9] S.Bhattacharyya, D.Towsley, and J.Kurose. The loss path multiplicity problem in multicast congestion control. Proceedings ofIEEE INFOCOM, New York, March 1999,vol.2,pp.856～863.
[10] B.Whetten and J.Conlan. A Rate Based Congestion Control Scheme for Reliable Multicast. Technical White Paper, GlobalCast Communication,Oct. 1998.
[11] M.Handley, S.Floyd, and B. Whetten. Strawman Specification for TCP Friendly (Reliable) Multicast Congestion Contro 1(TFMCC). RMRG Meeting, Pisa, Italy, June 1999.
[12] J.Mahdavi and S.Floyd. TCP-Friendly Unicast Rate-Based Flow Control. Technical note sent to the end2end-interest mailing list, 1997. http://www.psc.edu/networking/papers
[13] T. Ott, J.Kemperman, and M.Mathis. Window Size Behavior in TCP/IP with Constant Loss Probability. DIMACS Workshop on Performance of Real time Applications on the Internet, Plainfield NJ, November 6-8, 1996.
[14] J.Padhye, V.Firoiu, D.Towsley, J.Kurose. Modeling TCP Throughput: A Simple Model and its Empirical Validation. Proc of SIGCOMM'98, Vancouver,August 1998.
[15] S.Floyd and K.Fall. Router mechanisms to support end-to-end congestion control. ftp://fep.ee.lbl.gov/papers/collapse.ps.
[16] S.Bhattacharyya, D.Towsley, and J.Kurose. A novel loss indication filtering approach for multicast congestion control. Journal of Computer Communications, Special Issue on Multicast, 2000.
[17] S.J.Golestaniand, K.K.Sabnani. Fundamental observations on multicast congestion control in the internet. Proc.of IEEE Infocomm'99. Match 1999, vo12,pp.990～1000
[18] S.Floyd, M.Handley, J.Padhye, and J.Widmer. Equation-Based Congestion Control for Unicast Applications. Proc. ACM SIGCOMM, Stockholm, Sweden, Aug. 2000, pp.43-56.
[19] J.Widmer and M.Handley. Extending equation-based congestion control to multicast applications. In Proc. ACM SIGCOMM, San Diego, CA, Aug. 2001.
[20] S.Floyd, V.Jacobson, S.McCanne, C-G Liu, L.X.Zhang. A Reliable Multicast Framework for
Light-Weight Sessions and Application Level Framing. Proc. Of ACM Sigcomm, August 1995, pp.342～356
[21] H.A. Wang and M.Schwartz. Achieving Bounded Fairness for Multicast and TCP traffic in the Internet. Proc.of ACM SIGCOMM, 1998
[22] B.Rajagopalan. Reliability and Scaling Issues in Multicast Communication. Proc. Of ACM SIGCOMM'92, 1992,pp.188-198
[23] B.Cain, T.Speakman, and D.Towsley. Generic Router Assist GRA Building Block Motivation and Architecture. Mar 2000, Internet draft draft-ietf-rmt-gra-arch-01.txt
[24] S.Floyd and K.Fall. promoting the use of end-to-end congestion control in the Internet. IEEE/ACM Transactions on Networking, Aug 1999, 7(4):458-472
[25] I.Rhee, N.Ballaguru, G.N.Rouskas. MTCP: Scalable TCP-like Congestion Control for Reliable Multicast. Proc. IEEE INFOCOM'99, New York, USA, March 1999. vol.3,pp.1256-1273
[26] S.Kasera, S.Bhattacharyya, M.keaton, D.Kiwior, J.Kurose, D.Towsley and S.Zabele. Scalable fair reliable multicast using active services. IEEE Network Magazine(Special Issue on Multicast), Jan 2000, 14(1): 48-57
[27] D.Delucia and K.Obraczka. Multicast feedback suppression using representatives. In Proceedings of IEEE INFOCOM'97, 1997
[28] Luigi Rizzo. pgmcc: A TCP-Friendly Single rate Multicast Congestion Control Scheme. in Proc. ACM SIGCOMM, Stockholm, Sweden, August 2000,pp.17～28
[29] T.Montgomery. A loss tolerant rate controller for reliable multicast. Tech. Rep. NASA-IVV-97-011, West Virginia University, Aug.1997
[30] Delucia D, Obraczka K. A Multicast Congestion Control Mechanism for Reliable Multicast. IN: Proc. IEEE INFORCOM 1997.
[31] M.Kadansky, D.Chiu, J.Wesley, and J.Provino. Tree-based Reliable Multicast(TRAM). Jan,2000, INTERNET DRAFT draft-kadansky-tram-02.txt, Work in Progress.
[32] S.McCanne, V.Jacobson, and M.Vetterli. Receiver-driven layered multicast, in Proc. Of ACM SIGCOMM, Palo Alto, CA, USA, Aug. 1996, pp. 117-130
[33] L.Vicisano, L.Rizzo, J.Crowcroft. TCP-like Congestion Control for Layered Multicast Data Transfer. in Proc. Of IEEE INFOCOM, March 1998, vol.3, pp. 996-1003.
[34] J.Byers, M.Frumin, G.Horn, M.Luby, M.Mitzenmacher, A.Roetter, and W.Shaver. FLID-DL: Congestion control for layered multicast. in Proc. Second Int'l Workshop on Networked Group Communication (NGC 2000), Palo Alto, CA, USA, Nov. 2000.
[35] S.Jagannathana, K.Almeroth, and A.Acharya. Topology sensitive congestion control for real-time multicast. Proc. International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), June 2000.
[36] X.Li, M.Ammar, and S.Paul. Layered video multicast with retransmission (LVMR): Evaluation of hierarchical rate control. Proc. IEEE Infocom, Mar. 1998.
[37] X.Li, S.Paul, and M.Ammar. Multi-session rate control for layered video multicast. Proceedings of Symposium on Multimedia Computing and Networking, Jan. 1999.
[38] T. Turletti, S.Parisis, and J.Bolot. Experiments with a layered transmission scheme over the Internet. Tech. Rep. RR-3296, INRIA, France, Nov. 1997.
[39] D.Sisalem and A.Wolisz. MLDA: A TCP-friendly congestion control framework for heterogenous multicast environments. Eighth International Workshop on Quality of Service (IWQOS), June 2000.
[40] A.Legout and E. W. Biersack. PLM: Fast convergence for cumulative layered multicast transmission schemes. Proceedings of ACM Sigmetrics, June 2000.
[41] H.Schulzrinne, S.Casner, R.Frederick, and V.Jacobson. RTP: A transport protocol for real-time applications. RFC1889, January 1996.
[42] J.Byers, M.Luby, M.Mitzenmacher, and A.Rege. A Digital Fountain Approach to Reliable Distribution of Bulk Data. Proceedings of ACM SIGCOMM'98, Vancouver, August 1998.
[43] R.Jain, D.M.Chiu, and W.Hawe. A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer System. Digital Equipment Corp. Eastern Research Lab, DEC-TR-301, September 1984
[44] Lawrence S, Sean W, Larry L. TCP Vegas: New Techniques for Congestion Detection and Avoidance. In: Proc SIGCOMM'99
[45] S.Pingali, D.Towsley, J.Kurose. A Comparison of Sender-initiated and Receiver-Initiated Reliable Multicast Protocols. In Proc. INFORCOM, San Francisco, CA, October 1993.
[46] M.Handley et al. The Reliable Multicast Design Space for Bulk Data Transfer. IETF Internet Draft, draft-ietf-rmt-design-space-00.txt, October 1999.
[47] Adamson, Borman,Floyd,Handley, Macker. NACK-Oriented Reliable Multicast(NORM) Protocol Building Blocks. IETF draft-rmt-norm-bb-00.txt.
[48] J.Mogul and S.Deering. Path MTU Discovery. RFC 1191, November 1990
[49] K.Miller, K.Robertson, A.Tweedly, and M. White. Starburst multicast file transfer protocol (mftp) specification. Internet Draft, Internet Engineering Task Force, draft-miller-mftp-spec-02.txt, January 1997
[50] K.Miller, K.Robertson, A.Tweedly, and M. White. StarBurst Multicast File Transfer Protocol (MFTP) Specification. Internet Draft, draft-miller-mftp-spec-03,txt, April, 1998.
[51] M.Handley, Reference Simulations for Reliable Multicast Congestion Control Schemes. Draft Notes Presented at IRTF RM Group Meeting, London, United Kingdom, July 6-7 1998 http://north.east.isi.edu/rm/london/mgh.ps.gz
[52] M.Handley, An Examination of Mbone Loss Distributions, presentation at the 3rd RMRG meeting, February 1998.
[53] UCB/LBNL/VINT Network Simulator-ns(version 2). http://www.isi.edu/nsnam/ns
[54] 罗万明，林闯，阎保平．TCP／IP拥塞控制研究．计算机学报，2001．24(1)：1-18
[55] 翟明玉，吴国新，顾冠群．Internet可靠多点投递拥塞控制研究进展．计算机研究与发展，2000，28(2)：58～62
[56] 吴文峻，聂树宣．可靠组播研究综述．计算机科学．2001．28(2)：58-62
[57] 单玉峰，柴乔林．TCP友好拥塞／速率控制算法及其在多媒体数据传输中的应用．计算机学报．2001．38(8)：886-890
[58] 任立勇，卢显良．可靠组播拥塞控制最新研究进展．计算机科学．2002．29(2)：51-54
[59] 石峰，吴建平．组播拥塞控制综述．软件学报，2002，13(8)：1441-1449