移动Ad Hoc网络的可靠多播路由协议

在移动Ad Hoc网络环境中,分组的重传和路由的重构比有线网络更频繁。在网络多播树变化的情况下提供高的分组传输率是移动Ad Hoc网络多播路由的主要难题。文中提出了一种基于协议转接概念的移动Ad Hoc网络的可靠多播路由协议(RMRP),该协议较好地减少了移动Ad Hoc网络中大量的路由重构和数据分组的重传。仿真实验显示RMRP具有较高的传输率和较低的端到端分组延迟。     

基于能量优化的认知无线电网络组播路由协议

针对认知无线电网络节点动态频谱分配的特点,利用静态博弈方法,根据次用户占用频谱越宽所造成干扰越大,建立基于价格惩罚机制的古诺模型解决频谱分配问题,通过求解纳什均衡,频谱利用率达到最优。根据最小增量按需驱动思想建立了节约能量的组播树,提出基于能量优化的适用于认知无线电网络的按需组播路由协议。     

一种基于气泡流控的改进多播路由算法

多播通信在片上多核系统中占据很重要的地位,并会对多核系统上并行应用程序的性能产生很大影响。现有的多播路由算法大多存在资源利用不均衡的不足,从而导致片上缓存资源的利用率较低。提出一种新的基于气泡流控的多播路由算法,该方法充分利用了片上网络的缓存资源,并通过向网络注入气泡避免了死锁现象的产生。实验表明,该方法可以有效提高片上网络中多播通信的性能,在合成负载下,该方法相对于均衡自适应多播路由算法可以实现18.1%的网络平均时延的降低以及16.7%的网络饱和吞吐量的增加。     

无线传感器网络中组播路由协议分析

无线传感器网络由小型无线通信传感设备密集部署形成。组播是一种将数据包从源节点有效传递到一组目的节点的基本路由服务技术。组播协议中,源节点到目的节点的一些路径可由多个目的节点共享,所共享的路径越大,总带宽消耗越低。在分析无线传感器网络基本特征的基础上,对无线传感器网络中现有的组播路由协议进行了分类分析和比较,最后对无线传感器网络组播路由协议的未来发展趋势提出展望。     

几种Ad Hoc网络组播路由协议的分析与比较

Ad Hoc网络是一种不依赖于固定设施的,自组织的无线网络,其组网快捷、方便,具有广阔的发展前景.在典型的Ad Hoc网络应用中,网络主机通过按组工作来完成一项特定的任务.因此,组播在Ad Hoc网络中是一个十分重要的功能.按照参与组播路由的结点构成的网络拓扑结构的不同,分别介绍了基于树的组播路由协议AMRIS,基于格网的组播路由协议ODMRP、CAMP、FGMP,和基于混合的组播路由协议AMRoute,并对它们各自的工作方式进行了分析,最后对它们各自的特点进行了比较.     

基三分层网络中的受限多播路由算法

多播路由算法对互连网络的通信性能和多处理机系统性能的发挥起着重要作用。针对基三分层互连网络,在权衡性能、成本和实现的基础上,提出一种基于树的受限多播路由算法TRMA。该算法充分利用基三分层互连网络的层次特性和节点编码中所含的网络拓扑信息实现消息路由,算法设计简单,易于硬件实现。和其他基于树的多播路由算法相比,TRMA算法不需要源节点在发送消息前构建多播树,并将多播树的信息存放在消息中,大大降低了源节点的工作负载,提高整个系统的性能。通过仿真比较了TRMA和基于单播的多播路由算法,结果表明TRMA具有较低的网络延迟和较小的网络流量。     

DRMR: Dynamic-ring-based multicast routing protocol for Ad hoc networks

Recently a number of multicast routing protocols for ad hoc networks have been proposed, however,most of them do not provide proper tradeoffs between effectiveness, efficiency and scalability. In this paper, a novel multicast routing protocol is presented for ad hoc networks. The protocol, termed as dynamic-ring-base dmulticast routing protocol (DRMR), uses the concept of dynamic ring whose radius can be adjusted dynamically and DRMR configures this type of ring for all group member nodes. According to the principle of zone routing,two nodes whose rings overlap can create route to each other, thus, when the ring graph composed of all rings is connected, each member node has one or more routes to others. DRMR uses the method of expanding ring search (ERS) to maintain the connected ring graph, and also can decrease the radius of the ring to reduce the overhead. The performances of DRMR were simulated and evaluated with NS2, and results show that DRMR has a high data packet delivery ratio, low control overhead and good scalability.     

一种快速低代价延迟受限组播路由算法

为满足实时业务的QoS要求,在非延迟受限组播路由算法(Fast Low-cost Shortest Path Tree,FLSPT）的基础上添加了延迟约束,使得生成的组播树上,每条从源到目的地的路径都满足给定的延迟限制,同时保持了原算法计算复杂度低,代价性能优越的特点。仿真结果表明,本文算法的代价和时间性能均优于延迟受限最短路径(Delay-Constrained Shortest Path, DCSP),且更适合用于目的节点分布集中的密集模式下。     

An optimal multicast algorithm for cube-connected cycles

This paper presents an efficient algorithm that implements one-to-many,or multicast,communication in one-port wormhole-routed cube-connected cycles(CCCs) in the absence of hardware multicast support.By exploiting the propoeries of the switching technology and the use of virtual channels,a minimumtime multicast algorithm is presented for n-dimensional CCCs that use deterministic routing of unicast messages.The algorithm can deliver a multicast message to m-1 destinations in [log2m] message-passing steps,while avoiding contention among the constitutent unicast messages,Performance results of a simulation study on CCCs with up to 10,240 nodes are also given.     

一种移动网中的匿名组播通信协议*

基于典型的组播路由协议ODMRP,提出了一种移动自组网中的匿名组播路由协议——AODMRP。在AODMRP中,通过采用假名机制和加/解密机制,可以防范数据包窃听、泄密节点攻击和反向路径跟踪等匿名攻击,能够有效地提供组播发送者、接收者以及传输路径相邻节点间通信的匿名性。     

IP multicast routing through ATM networks

The purpose of this paper is to have a closer look at the ‘core’ technology providing interworking between connectionless TCP/IP internetworks and switched ATM networks. The scope of the paper is IP multicast, while the main focus is on the network side of multicast, more precisely, on layers three and two of Internet architecture dealing with IP multicast routing. The paper analyses both practically available solutions and those being currently under discussion in IETF as Internet drafts. As a background of this comparison, the possible convergence of IP and ATM multicast service models is discussed. Major conclusions, based on simulation studies and scalability analysis are: (i) the high mapping overhead requires a separate address resolution service for unicast and multicast addresses; and (ii) efficient convergence has to make obsolete classical IP over ATM (M. Laubach, Classical IP and ARP over ATM, Network Working Group, Request for Comments: 1577, Category: Standards Track, January, 1994 [1]) in order to permit ‘cut-through’ within the ATM domain.     

Fast multicast on multistage interconnection networks using multi-head worms

1IntroductionMulticastcommunication,whichreferstothedeliveryofamessagefromasinglesourcenodetoanumberofdestinationnodes,isfrequentlyusedindistributed-memoryparallelcomputersystemsandnetworks[1].Efficientimplementationofmulticastcommunicationiscriticaltotheperformanceofmessage-basedscalableparallelcomputersandswitch-basedhighspeednetworks.Switch-basednetworksorindirectnetworks,basedonsomevariationsofmultistageiDterconnectionnetworks(MINs),haveemergedasapromisingnetworkajrchitectureforconstruct…     

受时延约束的组播路由算法

提出了一种新的受时延约束的组播路由算法。算法借鉴了MPH算法的思想,最初的组播树只包含源结点,然后每次将到达组播树的代价最小且满足时延约束的结点及其相应的路径加入到组播树,直到所有的成员加入为止。谊算法能够快速地得到一棵满足时延约束的组播树,并且组播树的代价也很小。实验表明：该算法简单,复杂度低,性能良好,易于在分布式环境中实现,可应用于实际的应用系统中。     

一种具有时延约束的组播路由算法研究*

对于多媒体应用等实时组播业务而言,组播路由算法不仅要考虑优化代价,还要考虑时延约束。针对这一问题,提出一种支持动态组播的时延受限低代价组播路由启发式算法(delay-constrained multicast algorithm,DCMA)。该算法基于DDMC算法进行扩展,采用新的指示函数和链路选择函数,综合考虑了时延和代价,有效保证了组播树的性能,而且时间复杂度低,可用于实际的应用系统中。     

计算机网络中的多播路由问题

在计算机网络中,多播是目前研究最多、应用最广的连接方式。就目前存在的多播路由算法及路由协议进行了分析与总结,给出了解决多播问题的一般方法,提出了在光网络中推行多播的必要性。     

Ad-hoc网络组播路由协议的研究与设计

从无线自组网实际环境应用出发,提出了一种极大节省通信带宽并且实现简单的无线自组网组播路由协议.该协议充分利用了无线信道的广播特性,采用广播方式完成对网络内各节点的组播数据的分发,网络内各节点则根据组播数据的目的地址来判断是否应向自己直连的组播成员转发组播数据,并根据序列号决定是否将该组播数据再次广播出去以及防止收到重复的组播数据,因该协议不使用组播树,省却了建立与重建组播树的复杂过程,从而保证了对通信带宽的节省与实现的简便.现已在PowerPC平台上得到实际验证,运行效果良好.     

Unicast-based multicast communication in wormhole-routed networks

Multicast communication, in which the same message is delivered from a source node to an arbitrary number of destination nodes, is being increasingly demanded in parallel computing. System supported multicast services can potentially offer improved performance, increased functionality, and simplified programming, and may in turn be used to support various higher-level operations for data movement and global process control. This paper presents efficient algorithms to implement multicast communication in wormhole-routed direct networks, in the absence of hardware multicast support, by exploiting the properties of the switching technology. Minimum-time multicast algorithms are presented for n-dimensional meshes and hypercubes that use deterministic, dimension-ordered routing of unicast messages. Both algorithms can deliver a multicast message to m-1 destinations in [log ₂ m] message passing steps, while avoiding contention among the constituent unicast messages. Performance results of implementations on a 64-node nCUBE-2 hypercube and a 168-node Symult 2010 2-D mesh are given     

时延约束动态不重组组播路由优化

针对时延约束的组播路由问题,提出了一种动态不重组组播路由算法NDMADC。算法将DGA和Floyd最短路径优化算法相结合,确保节点在满足时延约束的前提下动态选择到组播树有最小代价的路径加入组播会话。由于采用贪心算法思想,NDMADC算法保证了节点加入组播树时不需要组播树重组。仿真表明,该算法能正确地构造出满足时延约束的组播树,具有较低的代价和计算复杂度。     

时延约束的链路选择平衡优化组播路由算法

针对时延约束的最小代价组播树生成方法,提出一种快速有效的时延约束组播路由算法。该算法改进了KPP算法,设计了代价和时延动态优化的链路选择函数。在选择路径时,该算法综合考虑了时延和代价两个参数,保证了组播树的性能,降低了时间复杂度低。仿真结果表明,该算法能正确地构造出时延约束组播树,同时还具有较低的代价和计算复杂度。