应用层组播研究进展

组播技术是一种针对多点传输和多方协作应用的组通信模型,有高效的数据传输效率,是下一代Internet应用的重要支撑技术。早期的组播技术研究试图在IP层提供组播通信功能,但IP组播的实施涉及到对现有网络基础设施的调整,因此,大规模应用受到限制。近两年来,随着Peer-to-Peer(P2P)研究的兴起,基于应用层的组播技术也逐渐受到广泛关注。应用层组播协议将组成员节点自组织成覆盖网络,在主机节点实现组播功能,为数据多点并发传输提供服务。将组播功能从路由器迁移到主机上能有效解决许多与IP组播有关的问题,但同时也带来了一些新的挑战。本文分析了目前应用层组播研究的主要内容及技术特点,描述了协议设计所涉及的关键技术及面临的主要挑战,总结了现有工作及相关进展。     

应用层组播用户的自私性研究

应用层组播(application-layer multicast,简称ALM)是网络层组播的重要补充.但与网络层组播不同的是,应用层组播结构的组成节点是具有独立利益和决策的主机用户.自私的主机用户为了提高自身利益,可能不严格遵守应用层组播协议的规定,从而对组播会话的整体性能带来影响.为了设计可信任的、鲁棒的应用层组播协议,对应用层组播的用户自私性进行研究是必要的.综述了这一领域的研究进展,并按照应用层组播协议的工作阶段把这些研究分为3类,即控制结构维护阶段的自私性研究、节点信息收集阶段的自私性研究以及数     

一个融合组播流媒体系统

文章对目前网络中IP 组播流媒体存在组播孤岛和不同接入带宽用户群组播数据不能共享等问题,提出了一种新的流媒体融合组播覆盖网络,研究通过P2P 互联不同IP 组播区,实现组播数据共享。每一个IP 组播区内有一个IP 组播源(IP-SM)和一到多个P2P 组播源(P2P-SM),所有的IP-SM 和P2P-SM 组成一个融合组播树,将不同的IP 组播区互联。IP 组播区内采用网络层组播技术,组播区之间采用应用层组播技术,实现不同组播模式的融合,使流媒体系统具有扩展性和网络适应能力。     

网络层组播在大规模流媒体直播系统中的研究与实现*

组播可以有效实现多点之间通信,如何利用网络层组播技术实现流媒体直播系统,是当前的研究热点之一。基于MixCast模型,提出并实现了一种新的基于网络层的安全组播模型。针对当前组管理协议IGMP不提供接入控制,任何端点用户可自由地加入组播组,缺乏安全控制问题提出了依靠应用层单播对接收者认证,提出一种解决网络层组播的安全性问题和可控性问题的方法。实验结果表明,本系统具有良好的安全通信效率和可控性。     

应用层组播稳定性提高技术综述

互联网上组通信应用的日益普及和传统IP组播发展面临的困境导致应用层组播逐步受到广泛关注.将组播功能从路由器迁移到主机能够有效解决许多与IP组播相关的问题,但同时也带来一些新的挑战,如应用层组播稳定性问题.文中概述了应用层组播的数据传输模型、组播树构造算法和协议性能评价标准,阐述了应用层组播稳定性问题产生的原因,提出了衡量应用层组播稳定性的标准,分析了影响应用层组播稳定性的因素,根据影响因素将应用层组播稳定性提高技术分类为降低节点离开事件发生频率的方法、缩小节点离开事件影响范围的方法以及缩短节点离开事件发生后组播树恢复时间的方法,并介绍了各种应用层组播稳定性提高技术,展望了该领域未来的研究工作.     

一种新的应用层组播实现方案

随着现代网络技术的不断发展,组播技术应用越来越广泛。而应用层组播由于比IP组播易于实现且扩展性优良,因而成为新的研究热点。本文提出一种新的应用层组播实现方案,它是一种两层结构体系:1、域间层次,每个自治域中设置组播代理,通过在代理间构建叠加网(OverlayNetwork)实现应用层组播;2、域内层次,在每个自治域内建立基于因特网间接通信基础框架(i3)的组播。最后用代理型应用层组播桥接每个域内的基于i3的组播,形成一种支持移动性的、适合大规模使用的应用层组播系统构架。     

基于加权选择函数的应用层组播路由算法

尽管IP组播是一种有效的多点通信方式,但在Internet范围内部署IP组播有着许多障碍.应用层组播可以在网络层不支持组播的情况下快速提供组播服务.提出了一种基于加权选择函数的分布式应用层组播路由算法,它在构造组播树时,能在尽量减少局部的三角路由同时兼顾节点之间的邻近性.模拟实验结果证明了该方案的有效性.     

基于双向压力模型的多源应用层组播拥塞控制方案

相比传统组播模式,多源应用层组播能用更少的网络资源实现多方交互式应用.但组播特性、应用层环境以及多源属性均会使得多源应用层组播的拥塞问题变得更加严重.因此,提出一种基于双向压力模型的多源应用层组播拥塞控制方案,该方案采用正反压的方式来避免组播流在节点上产生拥塞,并同时采用基于权重的缓冲转移策略来保证同一组内所有数据源的组播流在共享节点上公平地占用缓冲和带宽资源,并进一步讨论了环形拥塞问题的严重性和解决办法.PlanetLab实验网评测结果表明,该方案在实现多源应用层组播拥塞控制的同时,能够协调不同组播流的流量,实现其公平性和可扩展性.     

应用层的多播协议

传统的多播(multicasting)服务被实现在TCP／IP协议的网络层，但由于网络层的多播服务实现需要扩展网络层的路由与数据包收发协议，这在大多数的实际网络环境里并不是一件容易的事情。从最近几年来，研究人员开始重新审视多播服务的实现宿主层，并提出将多播服务实现在TCP／IP协议的应用层。应用层的多播在提供与网络层的多播的相近质量的服务情况下，具有更好的应用灵活性。本文介绍了应用层多播的定义和方法，及现阶段国内外已提出的应用层多播协议，并简要地讨论了应用层多播协议的性能评价问题。     

大规模应用层组播网络体系结构研究

阐述了IP组播发展所面临的问题、应用层组播发展现状和ScatterCast应用层组播网络，在对ScatterCast扩展的基础上，提出了一种新的支持大规模应用模式的应用层组播网络体系结构，以解决应用层组播通信的可扩展性及与IP组播的兼容性等问题。介绍了应用层组播网络的性能评价参数。     

应用层组播协议的研究

由于IP组播至今没能在Internet上大规模的应用,许多研究者提出了应用层组播的新方法来实现广域的组播服务。此方法中组播功能的实现是通过终端主机而不再依靠网络中的路由器。和IP组播不一样的是,应用层组播不需要底层架构的支持并且能够在Internet上很容易的实现。该文讨论了目前四种有代表性的应用层组播协议并且给出了这些协议的性能和应用的比较。     

Efficient Multiple Multicast on Heterogeneous Network of Workstations

In recent years, network of workstations/PCs (so called NOW) are becoming appealing vehicles for cost-effective parallel computing. Due to the commodity nature of workstations and networking equipment, LAN environments are gradually becoming heterogeneous. The diverse sources of heterogeneity in NOW systems pose a challenge on the design of efficient communication algorithms for this class of systems. In this paper, we propose efficient algorithms for multiple multicast on heterogeneous NOW systems, focusing on heterogeneity in processing speeds of workstations/PCs. Multiple multicast is an important operation in many scientific and industrial applications. Multicast on heterogeneous systems has not been investigated until recently. Our work distinguishes itself from others in two aspects: (1) In contrast to the blocking communication model used in prior works, we model communication in a heterogeneous cluster more accurately by a non-blocking communication model, and design multicast algorithms that can fully take advantage of non-blocking communication. (2) While prior works focus on single multicast problem, we propose efficient algorithms for general, multiple multicast (in which single multicast is a special case) on heterogeneous NOW systems. To our knowledge, our work is the earliest effort that addresses multiple multicast for heterogeneous NOW systems. These algorithms are evaluated using a network simulator for heterogeneous NOW systems. Our experimental results on a system of up to 64 nodes show that some of the algorithms outperform others in many cases. The best algorithm achieves completion time that is within 2.5 times of the lower bound.     

一种基于DHT的应用层多播方案

由于应用层多播相对于IP多播的易于部署,得到了国内外学术界的广泛研究。该文从经典的P2P搜索协议Chord入手,构建了基于P2P覆盖网的不定叉树,支持任意源多播,将节点的加入和根的发现结合起来,并对其网络动荡（节点加入与退出）实行制约限制,使网络环境保持基本稳定,达到负载平衡,并预测了本模型发展的方向。     

带度约束的最小直径应用层多播路由问题的启发式遗传算法

由于IP多播难以在因特网环境中配置，应用层多播作为IP多播的一种替代方案得到越来越多的研究。从网络设计的角度来看，应用层多播在网络代价模型及路由策略方面与传统的IP多播有很大区别。本文研究了带度约束的最小直径应用层网络多播路由问题，提出了解决该问题的启发式遗传算法。通过大量仿真实验，我们对比分析了两种贪婪算法法和遗传算法的性能。实验显示，启发式遗传算法具有较好的性能。     

一种基于DHT的应用层多播方案

由于应用层多播相对于IP多播的易于部署,得到了国内外学术界的广泛研究。该文从经典的P2P搜索协议Chord入手,构建了基于P2P覆盖网的不定叉树,支持任意源多播,将节点的加入和根的发现结合起来,并对其网络动荡(节点加入与退出)实行制约限制,使网络环境保持基本稳定,达到负载平衡,并预测了本模型发展的方向。     

Scalable Base-Station Model-Based Multicast in Wireless Sensor Networks

Multicast is essential for wireless sensor network (WSN) applications. Existing multicast protocols in WSNs are often designed in a P2P pattern, assuming small number of destination nodes and frequent changes in network topologies. In order to truly adopt multicast in WSNs, we propose a base-station model-based multicast, SenCast, to meet the general requirements of applications. SenCast is scalable and energy-effcient for large group communications in WSNs. Theoretical analysis shows that SenCast is able to approximate the Minimum Nonleaf Nodes (MNN) problem to a ratio of ln |R| (R is the set of all destinations), the best known lowest bound. We evaluate our design through comprehensive simulations and prototype implementations on Mica2 motes. Experimental results demonstrate that SenCast outperforms previous multicast protocols including the most recent work uCast.     

Comparison of recovery schemes to maximize restorable throughput in multicast networks

Multicast networks have many applications especially in real-time content delivery systems. For high-quality services, users do not expect to witness any interruption; thus, network link failure has to be handled gracefully. In unicast networks there are many approaches for dealing with link failures using backup paths. Recently, Cohen and Nakibly categorized these methods, provided linear programming formulations for optimizing network throughput under the assumption that the paths are splitable, and compared them experimentally. In this work, we take their approach and apply to the multicast failure recovery problem. We propose backup bandwidth allocation algorithms based on linear programs to maximize the throughput, and perform an experimental study on the performance of recovery schemes. We study many recovery schemes in multicast networks and propose a new recovery scheme that performs better than all other recovery scheme except the one that recomputed the whole multicast tree from scratch for each link failure.     

基于主机的跨网段多播系统设计

多播是一种重要的群组通信技术,在许多领域正得到越来越广泛的应用.传统的多播服务由于实现在TCP/IP协议的网络层,跨网段的多播需要路由器的支持.给出了一种基于主机端应用程序的跨网段多播解决方案,在不改变现有网络结构的基础上,为处于不同子网的主机提供了群组通信服务.详细阐述了该解决方案的设计思想以及适用情况.     

Buffer-assisted on-demand multicast for VOD applications

Multicast communications is widely used by streaming video applications to reduce both server load and network bandwidth. However, receivers in a multicast group must access the multicast stream simultaneously, and this restriction on synchronous access diminishes the benefit of multicast because users in a video-on-demand service usually issue requests asynchronously, i.e., at anytime. In this paper, we not only formulate this streaming problem but also propose a new multicast infrastructure, called buffer-assisted on-demand multicast, to allow receivers accessing a multicast stream asynchronously. A timing control mechanism is integrated on intermediate routing nodes (e.g., routers, proxies, or peer nodes in a peer-to-peer network) to branch time-variant multicast sub-streams to corresponding receivers. Besides, an optimal routing path and the corresponding buffer allocations for each request must be carefully determined to maximize the throughput of the multicast stream. We prove that the time complexity to solve this routing problem over general graph networks is NP-complete, and then propose a routing algorithm for overlay networks to minimize server load. Simulation results demonstrate that buffer-assisted on-demand multicast outperforms many popular streaming methods.     

A cross layer architecture for multicast and unicast video transmission in mobile broadband networks

This paper focuses on the transport of Unicast and Multicast traffic in the mobile broadband networks. The main objective is to allow video streaming applications to adapt its parameters according to 802.16MAC layer conditions and resource availability. For unicast traffic, we propose a cross layer optimizer, named XLO, between scalable video streaming application and IEEE 802.16 MAC layer. XLO uses the existing service flow management messages exchanged between a base station (BS) and a subscriber station (SS) and make them available to the video streaming application via a specific XLO interface. We implemented the XLO in the QualNet simulator and performed extensive simulations using a personalized scalable video traffic generator, capable of streaming video with different data rates and quality levels. We also introduce an enhanced admission control function at the BS that takes into account video adaptability property. The simulation results show the effectiveness of our XLO mechanism for delivering better quality of service. For multicast traffic, we propose a new solution based on superposition coding and make use of scalable video coding in order to optimize the network resources.