【作者】 苏晓丽；

【导师】 郑明春；

【作者基本信息】 山东师范大学 ， 管理科学与工程， 2003， 硕士

【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。更多还原

【Abstract】 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 standardization.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更多还原