基于区分服务的层次环状结构应用层多播模型

为了提高应用层多播的传输效率,提出一种基于区分服务的层次环状结构的应用层多播模型HRM,该模型构建了一个多层的覆盖网络,每层节点构成环状结构,取消了层中控制节点,减小了控制开销;并在数据传输过程中,根据应用层多播业务实时性不同,采用Push或Pull传输策略,减小传输时延或提高带宽利用率.仿真结果表明,该模型具有较小时延和控制开销以及较低的链路压力,适用于大规模应用层多播环境.     

一种分层的环状应用层多播模型

提出了一种新型的适合于大规模应用层多播的模型VRBH(Virtual Ring-Based Hierarchy),它以环作为拓扑结构,同时引入了分层和虚拟环的概念。采用了基于优先级的动态规划方法使得该环状拓扑结构随时间的变化逐渐趋于合理,并且采取一定的措施使得当出现数据传输错误时可以进行快速的恢复。由仿真试验结果得知该模型具有较低的控制开销,较高的带宽利用率和较高的数据传输率,应用该多播模型可以较好地提高多播的性能。     

一种基于蚁群算法的分布式多播路由算法

随着计算机网络的不断发展,大量多媒体应用要求网络具有满足QoS约束的多播功能.应用多播的关键是确定有效的多播路由,即求解最优Steiner树.目前提出的大部分都是集中式的或本质上是集中式的启发式算法,关于分布式算法的研究还比较少.本文提出了一种基于蚁群算法的分布式多播路由算法.该算法在源节点不掌握整个网络信息的情况下,利用网络的局部启发式信息和蚂蚁留下的信息素建立最优的多播路由.结合多播路由问题的特点,对算法进行了改进,使算法的收敛速度和解的质量都得到了较大的提高.仿真实验结果验证了该算法的有效性.     

感知驱动的VST多源应用层多播问题研究

虚拟空间会议（VST,virtual space teleconferencing）是具有广泛应用前景的一种新兴CSCW工具，在当前没有IP多播支持以及大多数端用户访问带宽有限的互联网条件下，实现互联网上的VST应用缺乏有效的通信机制。针对这一问题，提出了一种感知驱动的VST多源应用层多播方法ESMVST，该方法采用了网优先的集中式策略，重点研究了ESMVST方法中的路由模型VSTMMR，提出一种启发式路由算法MDMM。实验结果表明MDMM算法有效降低了算法的拒绝率和数据分发树的最大延迟，ESMVST方法实用可行。     

BowCast：一种适应非对称链路延时网络的P2P多播路由协议

虽然IP多播的性能优势无可否认,但是它却面临着部署上的困难。近年来,P2P多播作为提供多播服务的另一可行途径正不断为人们所认可。研究非对称链路延时网络环境下P2P多播的路由问题,提出一个新的P2P多播路由协议：BowCast.该协议采用基于树（tree-based）的分布式路由策略,使多播组成员之间能自组织地构建一棵基于源的最小延时P2P多播树。BowCast主要利用范围受限的单向探测技术（BOW）来实现路由优化算法。BOW能提供端系统节点间的单向相对延时,无需全局的同步时钟。仿真实验表明,BowCast能很好地适应非对称链路延时环境。通过调节BOW的探测范围,BowCast能灵活地在路由性能和控制开销之间进行折中。     

支持延时约束的覆盖多播路由协议的研究

研究有度和延时约束的覆盖多播路由问题,提出了一个新的覆盖多播路由协议-延时受限的树协议(DBTP)。该协议采用分布式和树优先的策略,使多播组成员之间能自组织地构建一棵基于源的覆盖多播树。DBTP协议采用了一种新的启发式局部优化算法,通过调节启发因子,能灵活地在延时和代价之间进行折衷。仿真实验表明,无论在静态还是动态节点模型下,选择适当的启发参数,DBTP都能获得较高的节点接纳率。     

面向可重构基础网络的部分扇出组播交换阻塞率模型

传统网络采用调度前复制和扇出拷贝方式的多播交换模型不具备大规模可扩展能力。面向可重构基础网络,提出了一种部分扇出多播交换模型,该模型采用2×2布尔单元和布尔群组集线器建立基本交换结构,采用部分扇出拷贝方式和四状态分割编码实现自路由路径选择,进而推导了该模型在单多播混合业务源输入下的单播阻塞率、多播阻塞率和多播扇出率迭代过程。仿真实验表明:该模型在Bernoulli均匀业务源条件下,单播归一化负载强度为0.2时,多播阻塞率在10 10～10 2之间,多播时延总小于百纳秒量级上限,能够为到达业务提供时延上限保障。     

基于最优化的多媒体多播速率控制

传输多媒体流的一种有效方法是采用多速率多播,但多速率多播的速率控制面临许多挑战,如异构性、公平性、实时性及服务质量(QoS)等。提出了一种两阶段优化的策略进行多媒体多播速率控制。把问题公式化为求系统效用最大化的最优化问题,推导出有效的算法。方法综合考虑了服务质量、异构性等,且满足协议间的公平性和多播会晤内各接收者间的公平性。仿真实验表明算法的有效性,与现有的算法相比系统总效用大大提高。     

基于路径备用机制的应用层多播树重构方法

首先,将前向式树重构策略扩展应用于基于Chord的结构型多播树,提出了路径备用机制,该机制为多播树中每个节点预先寻找一条用于快速恢复与多播树连接的备用路径.接着,以路径备用机制为基础,进一步设计基于Chord的应用层多播协议ChordM-FR.仿真结果表明,ChordM-FR协议的多播树重构速度比采用后向式树重构策略的ChordM-SR协议平均快大约2.5倍.     

基于多源数据融合的城市轨道交通线网客流监测方法研究

针对目前单一历史客流数据分析结果已无法满足城市轨道交通业务应用对数据精准性、时效性的需求问题,提出了基于多源数据融合的城市轨道交通线网客流监测方法.首先采集城市轨道交通多源实时数据,数据源包括AFC系统数据、移动支付平台交易数据、车站视频数据、基于5G基站的人员定位数据、车辆称重系统数据、车载视频数据;然后采用分布式架...     

Scribe: a large-scale and decentralized application-level multicast infrastructure

This paper presents Scribe, a scalable application-level multicast infrastructure. Scribe supports large numbers of groups, with a potentially large number of members per group. Scribe is built on top of Pastry, a generic peer-to-peer object location and routing substrate overlayed on the Internet, and leverages Pastry's reliability, self-organization, and locality properties. Pastry is used to create and manage groups and to build efficient multicast trees for the dissemination of messages to each group. Scribe provides best-effort reliability guarantees, and we outline how an application can extend Scribe to provide stronger reliability. Simulation results, based on a realistic network topology model, show that Scribe scales across a wide range of groups and group sizes. Also, it balances the load on the nodes while achieving acceptable delay and link stress when compared with Internet protocol multicast.     

A reliable multicast framework for light-weight sessions andapplication level framing

This paper describes scalable reliable multicast (SRM), a reliable multicast framework for light-weight sessions and application level framing. The algorithms of this framework are efficient, robust, and scale well to both very large networks and very large sessions. The SRM framework has been prototyped in wb, a distributed whiteboard application, which has been used on a global scale with sessions ranging from a few to a few hundred participants. The paper describes the principles that have guided the SRM design, including the IP multicast group delivery model, an end-to-end, receiver-based model of reliability, and the application level framing protocol model. As with unicast communications, the performance of a reliable multicast delivery algorithm depends on the underlying topology and operational environment. We investigate that dependence via analysis and simulation, and demonstrate an adaptive algorithm that uses the results of previous loss recovery events to adapt the control parameters used for future loss recovery. With the adaptive algorithm, our reliable multicast delivery algorithm provides good performance over a wide range of underlying topologies     

流媒体分发系统关键技术综述

 流媒体将是未来通信中的杀手业务.本文讨论了流媒体分发系统的关键技术,阐述了基于CDN (Content Distributed Network)和基于P2P (Peer to Peer )的流媒体的研究现状,针对基于CDN的流媒体,研究了流媒体调度算法,代理服务器缓存算法,基于CDN的交互式操作.针对基于P2P的流媒体,研究了数据分配算法,激励机制,流媒体对象的放置,应用层组播,基于P2P的交互式操作.指出了流媒体的未来研究方向.     

A survey of active and router-assisted reliable multicast solutions

Group communications, so-called multicast communications, have been introduced as early as 1986 as an efficient way to distribute on a large-scale basis data packets on the whole Internet. With the emergence of new applications driven by the increase of bandwidth in the networks (such as grid computing, large database replication, etc.), reliable multicast is foreseen to be one of the most challenging technologies of the next generation Internet. However, group communications are much more complex than point-to-point communications and solutions that have been implemented and deployed in the unicast world for ensuring reliability can not be so simply applied to the multicast area. Recently, a new paradigm proposes to dynamically add additional functionalities into the routers, thus enabling a whole new range of distributed control mechanisms as opposed to the traditional end-to-end form of control. In this paper, we summarize the various active networking and router-assisted solutions for reliable multicast to avoid or limit the scalability problems of end-to-end approaches for loss recovery, congestion control and heterogeneity support. Then, with the hypothesis that active networking could be deployed on a large scale, we present how this technology could solve the remaining bottlenecks of multicast on wide-area networks.     

应用于多源SAR图像匹配的级联SIFT算法

针对多源SAR(Synthetic Aperture Radar)图像几何精处理需要大量离散控制点的问题,文章中提出一种级联SIFT(Scale Invariant Feature Transform)匹配算法.首先,采用大尺度自适应各向异性高斯SIFT(Adapted Anisotropic Gaussian-SIFT,AAG-SIFT)算法进行图像粗配准,大尺度AAG尺度空间可以在模糊不稳定局部纹理干扰的同时,保持图像的结构信息,提高算法的鲁棒性;其次,级联一种局部SIFT匹配算法,在粗配准后图像间进行局部匹配,避免不相关区域内重复纹理对特征匹配的影响;最后,通过尺度和旋转等先验条件筛选匹配点对,保证匹配结果的准确性.对比实验表明,级联SIFT处理可以增加提取同名点的数量和空间分布质量,而且匹配点定位准确.     

数据中心高压直流供电架构的优化研究

随着高压直流供电技术的不断完善,其在通信行业的应用日趋广泛。而对于大型数据中心等大容量、高密度用电机房,高压直流供电系统的应用却相对较少。文章从供电系统架构的角度出发,结合高压直流供电技术的现状,提出了适应当前大型数据中心供电需要的分散式高压直流供电解决方案,并通过工程案例分析,验证了新型分散式高压直流供电系统的优越性。     

Analysis of tree‐based multicast routing in wireless sensor networks with varying network metrics

Wireless ad hoc and sensor networks are emerging with advances in electronic device technology, wireless communications and mobile computing with flexible and adaptable features. Routing protocols act as an interface between the lower and higher layers of the network protocol stack. Depending on the size of target nodes, routing techniques are classified into unicast, multicast and broadcast protocols. In this article, we give analysis and performance evaluation of tree‐based multicast routing in wireless sensor networks with varying network metrics. Geographic multicast routing (GMR) and its variations are used extensively in sensor networks. Multicast routing protocols considered in the analytical model are GMR, distributed GMR, demand scalable GMR, hierarchical GMR, destination clustering GMR and sink‐initiated GMR. Simulations are given with comparative analysis based on varying network metrics such as multicast group size, number of sink nodes, average multicast latency, number of clusters, packet delivery ratio, energy cost ratio and link failure rate. Analytical results indicate that wireless sensor network multicast routing protocols operate on the node structure (such as hierarchical, clustered, distributed, dense and sparse networks) and application specific parameters. Simulations indicate that hierarchical GMR is used for generic multicast applications and that destination clustering GMR and demand scalable GMR are used for distributed multicast applications. Copyright © 2012 John Wiley & Sons, Ltd.     

Distributed formation of core-based forwarding multicast trees in mobile ad hoc networks

A core-based forwarding multicast tree is a shortest path tree rooted at core node that distributes multicast packets to all group members via the tree after the packets are sent to the core. Traditionally, the bandwidth cost consumed by transmitting a packet from the core via the tree is evaluated by the total weights of all the edges. And, the bandwidth cost is minimized by constructing the multicast tree that has minimum total weights of edges to span all group members. However, when the local broadcast operation is used to multicast a packet, we found that the bandwidth cost is supposed to be evaluated by the total weights of all senders that include the core and all non-leaves. Since the multicast tree with the number of nodes greater than or equal to three has minimum bandwidth cost only when the core is not a leaf, it leads us to find the multicast tree with the minimum number of non-leaves when each sender node has a unit weight. However, no polynomial time approximation scheme can be found for the minimum non-leaf multicast tree problem unless P = NP since the problem is not only NP-hard but also MAX-SNP hard. Thus, a heuristic is proposed to dynamically reduce the number of non-leaves in the multicast tree. Experimental results show that the multicast tree after the execution of our method has smaller number of non-leaves than others in the geometrically distributed network model.     

Ad Hoc网络中一种基于QoS的分布式多播路由算法

通过分析Ad Hoe网络的特点及基于QoS的多播路由问题，提出了一种新的分布式多播路由算法。实验和分析的结果表明，文中构造的路由方案成功地解决了Ad Hoe网中基于QoS的多播路由问题。当Ad Hoe网络的拓扑结构改变不太快时，本文提出的路由方案不仅满足了实时业务对网络带宽和端到端延时的要求，优化了路由树的代价，而且有效地控制了算法的复杂性并可适用于大规模的网络中。     

A Cross-Layer Optimization Framework for Multihop Multicast in Wireless Mesh Networks

The optimal and distributed provisioning of high throughput in mesh networks is known as a fundamental but hard problem. The situation is exacerbated in a wireless setting due to the interference among local wireless transmissions. In this paper, we propose a cross-layer optimization framework for throughput maximization in wireless mesh networks, in which the data routing problem and the wireless medium contention problem are jointly optimized for multihop multicast. We show that the throughput maximization problem can be decomposed into two subproblems: a data routing subproblem at the network layer, and a power control subproblem at the physical layer with a set of Lagrangian dual variables coordinating interlayer coupling. Various effective solutions are discussed for each subproblem. We emphasize the network coding technique for multicast routing and a game theoretic method for interference management, for which efficient and distributed solutions are derived and illustrated. Finally, we show that the proposed framework can be extended to take into account physical-layer wireless multicast in mesh networks