Distributed reformation of core-based group-shared multicast trees in mobile ad hoc networks

This paper proposes a method to reduce the cost of a core-based group-shared multicast tree, where the cost is evaluated by the total bandwidth consumption of multicasting packets among all group members. Due to the broadcast nature of radio transmissions, we find that the challenge of determining minimum cost multicast tree can be approximated by finding the multicast tree with a minimum number of non-leaves (the minimum non-leaf multicast tree problem). However, we also find that the minimum non-leaf multicast tree problem is NP-complete. Thus, a method is proposed to dynamically reduce the number of non-leaves in an existing multicast tree. Experimental results show that our method reduces the cost of the multicast tree in both geometrically and randomly distributed network models and the random waypoint mobility model.     

基因池操作遗传算法的应用层组播路由优化

在应用层组播系统中，负责数据转发的终端节点不具备线速转发能力，较重的转发负载会引起拥塞。以拥塞节点为根的整个子路由树将与源节点失联。为解决由拥塞导致应用层组播稳定性差的问题，将构造最优组播树的过程抽象为有度约束的最小代价Steiner树问题。提出了一种用于构造节点转发能力受限应用层组播树的遗传算法，算法以组播树上各节点的直接前驱对其进行遗传表达，便于节点出度的统计。为使遗传操作适用于直接前驱编码，引入了“基因池”的概念并以此为基础实现了交叉与变异。针对度约束导致产生非可行解的问题，提出将组播树对度约束的超出量作为一个新的优化目标，从而以多目标优化的方式得到Pareto前沿，并从Pareto前沿上截取满足度约束的解作为最终输出，避免了使用惩罚函数法的求得非可行解的风险。仿真实验表明，提出的遗传算法能够构造节点转发能力受限的应用层组播路由树，具有良好的求解可靠性。     

A Service-Centric Multicast Architecture and Routing Protocol

In this paper, we present a new multicast architecture and the corresponding multicast routing protocol for providing efficient and flexible multicast services over the Internet. Traditional multicast protocols construct and update the multicast tree in a distributed manner, which may cause two problems: first, since each node has only local or partial information on the network topology and group membership, it is difficult to build an efficient multicast tree and, second, due to the lack of complete information, broadcast is often used for sending control packets and data packets, which consumes a great deal of network bandwidth. In the newly proposed multicast architecture, a few powerful routers, called m-routers, collect multicast-related information and process multicast requests based on the information collected. The m-routers handle most of the multicast-related tasks, whereas other routers in the network only need to perform minimum functions for routing. The m-routers are designed to be able to handle simultaneous many-to-many communications efficiently. The new multicast routing protocol, called the Service-Centric Multicast Protocol (SCMP), builds a shared multicast tree rooted at the m-router for each group. The multicast tree is computed in the m-router by employing the Delay-Constrained Dynamic Multicast (DCDM) algorithm, which dynamically builds a delay-constrained multicast tree and minimizes the tree cost as well. The physical construction of the multicast tree over the Internet is performed by a special type of self-routing packets in order to minimize the protocol overhead. Our simulation results on ns-2 demonstrate that the new SCMP protocol outperforms other existing protocols and is a promising alternative for providing efficient and flexible multicast services over the Internet.     

<Emphasis Type="Bold">Ppssm:push/pull smooth video streaming multicast protocol design and implementation for an overlay network</Emphasis>

IP multicast is one of the best techniques for video streaming on the Internet. It faces issues with respect to address allocation, routing, authorization, group management, security, and scalability. By default, local Internet Service Providers did not enable IP multicast services, because of the cost incurred in using multicast-enabled routers. To solve these issues some of the IP layer functionalities have been shifted to the Application Layer, thus leading to Application Layer Multicast (ALM) protocols. However, ALM protocols face issues related to synchronous data delivery, scalability, link stress, link stretch and node failures. Some of the existing protocols are CoolStreaming, and mTreebone. A novel ALM protocol based Push/Pull Smooth video Streaming Multicast (PPSSM) protocol is proposed in this paper, to increase the throughput and reduce the packet loss rate. The PPSSM protocol involves three stages, such as tree-mesh construction, dynamic buffer management and network coding techniques. In the tree-mesh construction, a tree consists of stable nodes and a mesh consists of unstable nodes. The proposed PPSSM optimizes the stable nodes in the tree, which minimizes or eliminates the pull operations from the unstable mesh overlay nodes, by exploring the potential of the stable nodes. Dynamic buffer management is achieved by setting the optimal buffer threshold value, using the optimization of the sensitivity parameters, such as packet loss and packet workload/delay by the Infinitesimal Perturbation Analysis and Stochastic Approximation algorithms. In addition to the tree-mesh construction and buffer management, the introduction of the network coding technique will enhance the throughput and minimize the packet loss and delay. Finally, the performance of the proposed PPSSM protocol is compared with those of CoolStreaming, and mTreebone, and it shows improvement in respect of throughput, packet loss, and average decoding time.     

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。     

时延及时延抖动限制的最小代价多播路由策略

满足多种服务质量请求的多播路由问题是目前多播通信中的重要课题之一。该文作者在研究受端到端时延及时延抖动限制的多播路由问题的过程中，发现当前许多算法所普遍使用的两个最佳链路选择函数并不能完全体现路由的动态过程，同时它们还存在一定的缺陷。而正是由于这种缺陷，在某些情况下通过这两个最佳链路选择函数所得到的结果树可能不包含所有的目标节点，文中称这种情况为“多播不可达”。针对上述问题，该文提出了“多播可达”的假设条件以及一个新的最佳链路选择函数，并在此基础上提出了一个满足时延及时延抖动双重限制的最小代价多播树的建立算法（DDVBMRA）以及一种动态重组多播组目标节点的方法。仿真结果表明本算法具有很好的延抖动及代价性能。     

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.     

Parallel overlays for high data-rate multicast data transfer

Recently a number of application-layer multicast (ALM) protocols have been proposed as a promising alternative to deploying multicast services in the unicast-only Internet. Current ALM protocols work very well for low data-rate applications but can suffer from link-level load imbalance, and consequently link congestions, when applied to high data-rate applications. This work addresses this problem by extending the well-known NICE protocol to use multiple parallel overlays in the same ALM session to spread the data traffic across more available network links, and thus leading to significantly improved performance. Extensive simulation results show that the proposed protocol can support three times the data-rate compared to NICE and yet can reduce the end-to-end data delivery delay by more than 50%.     

一种高稳定性低延迟的应用层组播生成树算法

由于应用层组播技术依靠终端主机转发组播数据,任意中间节点的退出都将造成系统的稳定性问题。同时,应用层组播技术对延时有严格的要求。为了提高应用层组播系统的稳定性和数据传输效率,根据影响应用层组播稳定性和延时的因素,抽象出基于节点稳定概率的度约束的最小延时应用层组播生成树问题模型SDMD (Spanning tree based on stability probability,degree-constrained,and minimum diameter for ALM),并且证明了该问题属于NP-hard问题。为了解决该问题,给出了基于节点时间增益因子的TG-S近似算法。仿真实验表明,TG-S算法生成的组播树在平均延时、最大延时和累积中断次数等方面有明显优势。     

覆盖组播的最小覆盖代价路由算法

与IP组播相比,覆盖组播通常会消耗更多的底层网络资源。因此,在覆盖网中构造组播转发树时,考虑合理地利用底层网络资源具有一定的实际意义。给出覆盖代价的概念,把覆盖组播路由问题归结为求无向完全图的度和延迟受限、具有最小覆盖代价的生成树问题,求解的目标是在满足应用需求和端用户主机性能要求的同时使所消耗的底层网络资源最少。给出了求解该问题的启发式遗传算法,通过仿真实验验证了该算法的有效性。     

基于用户行为分析的应用层组播树生成算法

应用层组播采用终端主机转发数据的方式,在一对多的媒体内容分发方面具有广阔的应用前景．与IP组播相比,应用层组播具有灵活和易实施的特点,但是因为终端主机可以自由地退出组播树,应用层组播也存在数据传递易中断的缺点,这对实时性要求严格的视频直播应用的影响尤为严重．通过对超过1000万条实际视频直播系统的真实用户记录进行统计分析,发现用户平均剩余在线时间随着已经在线时间的增大而增大,并据此提出了一种适用于视频直播的应用层组播树生成算法．模拟结果表明,算法对减少视频直播应用下应用层组播树的数据传递中断次数有明显作用．     

基于主机邻域密度的QoS保证的应用层多播模型

提出了一种基于主机邻域密度的QoS保证的应用层多播模型MCT,模型设计为典型的树结构。主要阐述了多播节点的加入与退出过程,首先定义了主机邻域密度的概念,并以此为标准对所有节点进行初次择优,随后运用服务质量路由算法RDSS进行二次择优,得到多个网络参数限制条件下最满足QoS需求的接入路径,最终达到应用层多播(ALM)拓扑结构的整体优化。仿真结果证明,模型的建立方法可以平等且有效地控制多个网络参数,满足了ALM应用的QoS需求。     

Reconfigurable multicast routing for Networks on Chip

Several unicast and multicast routing protocols have been presented for MPSoCs. Multicast protocols in NoCs are used for cache coherency in distributed shared memory systems, replication, barrier synchronization, or clock synchronization. Unicast routing algorithms are not suitable for multicast, as they increase traffic, congestion and deadlock probability. Famous multicast schemes such as tree-based and path-based schemes have been proposed originally for multicomputers and recently adapted to NoCs. In this paper, we propose a switch tree-based multicast scheme, called STBA. This method supports tree construction with a minimum number of routers. Our evaluation results reveal that, for both synthetic and real traffic loads, the proposed scheme outperforms the baseline tree-based routing scheme in a conventional mesh by up to 41% and reduces power consumption by up to 29%.     

基于树与环应用层组播覆盖网的研究与比较

由于应用层组播在部署和实现方面的优势受到学术界的广泛关注.应用层组播协议在不同的覆盖网络拓扑结构(如树、网、环)下具有不同的性能特征.因此,比较应用层组播覆盖网的性能是评估覆盖网络拓扑优缺点的关键.在NS-2下对基于树、环的覆盖网络进行仿真.仿真结果表明,尽管环型覆盖网比树型覆盖网具有较高路径伸展度和较高链路强度,但在单个组播组成员失效或离开的情况下,它提供了恒定的、更低的节点度和较高数据传送率.     

QoS-DRMR：Ad Hoc网络中有QoS约束的组播协议

近年来,Ad hoc网络的组播路由协议研究受到广泛关注,其中QoS保障问题是关键技术之一。目前已经提出了许多组播路由协议,其中动态广播环组播路由协议(DRMR),在降低控制开销的基础上,能够取得较好的分组递交率和扩展性。但DRMR没有考虑 QoS 保证要求的问题,本文时DRMR协议进行了QoS保证的扩充,根据多目标约束条件,优化组播路由的选择,提出了一种保证最小带宽要求情况下取得整体优化延时和包丢失率条件的路由方案。最后,利用NS2仿真软件对新的QoS-DRMR协议进行仿真,结果表明:QoS-DRMR协议较好地实现了在多目标约束条件下的组播服务。     

结合集中式与分布式特征的多路径QoS组播路由协议

提出了一个结合集中式算法与分布式算法优点的多路径启发式QoS组播路由算法和协议,它以单播路由协议OSPF传播链路的代价信息为基础,运用最小代价Dijkstra算法计算端节点到当前在树节点的最小代价路径,然后启动一个分布式计算过程得到一个可选路径集,加入节点通过一个综合性启发式选择其中的最佳路径连接到组播树．算法能够有效地支持延时和带宽受限的代价优化组播树构造,具有无环选路、呼叫接收成功率高、呼叫建立时间短、伸缩性好等特点．     

基于局部信息的时延和时延差约束的组播路由

组播通信是从一个源节点同时向网络中的多个目的节点发送分组的通信服务,它一般提供一个以上的端到端的服务约束,实际的路由算法在应用时可以受到多重约束,解决这类问题的组播路由算法是NP完全的。在研究了构建组播树的相关算法后,提出了一种新的时延和时延差约束的低代价组播路由算法-DDVMC。该算法采用基于贪婪策略的Dijkstra最小生成树算法,利用局部信息来构建低代价组播树,很好地平衡了树的代价、时延和时延差。仿真表明,该算法能正确地构造出满足约束的组播树,同时还具有较低的代价和计算复杂度。     

QoS动态多播路由协议

保证服务质量的QoS（Quality of Service）路由是网络中解决OoS问题的一项关键技术．具有OoS约束的多播路由技术已成为网络领域的一个重要研究课题．该文研讨了具有QoS约束的动态多播路由问题．文中描述了一种适应于QoS多播路由的网络模型，提出了一种QoS动态多播路由协议（QDMRP）．QDMRP只要求网络链路（或节点）的局部状态信息，不需要维护全局状态信息．QDMRP较好地减少构造一棵多播树的开销．仿真实验结果表明：QDMRP具有较低的控制信息开销和节点加入时延，较好地适合于网络状态变化比较频繁的环境以及实时多媒体应用．     

一种动态负载均衡的P2P应用层组播方案

基于结构化的P2P基础设施,给出一种动态负载均衡的应用层组播方案--DLBMS.利用Tapestry协议的路由和定位机制,设计了延迟优化的组播转发树结构,采用根节点复制的方法生成多棵不相交的组播转发树,根据负载的变化动态调节组播转发树数目以实现负载均衡和降低源到组成员节点的端到端延迟.通过模拟实验说明了此方案在平均控制负载和端到端平均延迟方面的有效性.     

分布式QoS多播路由协议

研讨了具有QoS约束的分布式多播路由问题。描述了一种适应于QoS多播路由的网络模型,提出了一种分布式QoS多播路由协议（DQMRP）。DQMRP只要求网络链路（或节点）的局部状态信息,不需要维护全局状态信息。DQMRP可有效地减少构造一棵多播树的开销,多播组成员能动态地加入,退出一个多播会晤,且不干扰现有的多播树。给出了DQMRP的正确性证明。仿真实验结果表明：DQMRP具有较低的控制信息开销和节点加入时延,较其它协议更适合于网络状态变化比较频繁的环境以及实时多媒体应用。