IP／DWDM光因特网中的一种支持柔性QoS的并行一体化多播路由算法

本文研究了IP／DWDM光因特网中支持柔性QoS的并行一体化多播路由算法。对IP／DwDM光因特网中的多播请求及用户提出的端到端延迟需求区间，提出的算法一体化地解决路由选择和波长分配问题。目标是在考虑网络负载均衡的前提下，寻找一棵费用次优的多播树，并且满足用户QoS需求。该算法基于粗粒度并行遗传模拟退火算法构造多播树，基于波长图思想在多播树上进行波长分配。仿真研究表明，该算法是可行的，并且具有较好的性能。     

汇聚组播:新型MPLS服务质量组播体系结构

为支持新兴网络应用,IP组播(multicast)和MPLS(multi-protocol label switching)技术分别从不同方向扩展了当前的IP路由和交换模式.MPLS和IP组播的结合是当前研究的一个热点,MPLS网络中的服务质量组播面临着标签资源匮乏、组播路由状态的可扩展性以及具体实现上的困难.针对这些问题,提出了基于汇聚方法的新型MPLS服务质量组播体系结构,提出在现有的路由控制平面上叠加一层面向IP组播服务的控制平面,取代组播路由协议并支持组播聚集,形成2层控制平面结构.定义了两平面之间的协作和交互方式,并通过扩展RSVP-TE(resource reservation protocol-traffic engineering) P2MP(point to multi-point)协议,在新的体系结构中融合了服务质量控制能力.另外,还探讨了汇聚组播中基于距离约束选择汇聚路由器的算法,实现了基于Linux的MPLS组播路由器和IP组播服务控制系统,并组建了实验平台.实验和模拟结果表明,基于汇聚组播的双平面网络控制结构能够适应组播用户和网络拓扑的动态变化,能够有效节省MPLS标签资源,平衡网络中组播流量的分布.     

支持流媒体的应用层组播研究

在当前没有IP组播支持以及大多数端主机访问带宽有限的Internet网络条件下,普通的端主机提供实时流媒体应用服务缺乏有效的通信手段,应用层组播是解决这一问题的有效通信技术.针对网络电视、视频点播类型的大规模实时流媒体应用,本文提出一个两层应用层组播框架结构ALMF,并对其中组播服务结点覆盖网络的构建和维护进行了研究,提出了一个覆盖网络路由组播模型MOSSMRM和基于智能蚁群的路由算法IACSMR,随后将该路由算法和几种启发式算法进行了比较.仿真实验结果表明,IACSMR算法是一个有效的应用层组播路由算法.     

DCS:一种实现NDN内容缓存的新方法

随着互联网内容分发效能要求的不断提高,内容中心网络研究已成为近年互联网体系结构研究的热点.针对现有路由器扩展支持内容中心网络路由引擎时缓存资源有限以及缓存管理操作困难等问题,提出一种新的内容缓存扩展方案DCS.该方案旨在不改变现有路由器硬件的前提下,利用用户终端空闲内存空间,通过软件升级的方式来支持NDN路由器的缓存功能.详细描述了DCS数据存取的算法流程,还对用户可提供出来作为网络缓存资源的空闲内存空间进行了统计和分析.     

基于蚁群算法的多参数模糊评判的路由算法

随着互联网络的快速发展和网络用户数量的不断攀升,用户对网络服务质量和网络性能等方面的需求也不断增强.智能路由选择问题正成为网络通信领域中的一个热点问题,本文提出了基于蚁群算法的多路由约束参数模糊评判的路由算法,该路由算法不但能够综合利用多个路由参数的组合优化作用求解最优路由,而且,又能充分利用蚁群算法的良好特性.该路由算法能够有效地解决用户对网络服务、网络性能等方面的需求问题.     

宽带QoS路由器体系结构关键问题分析

高速化和多媒体化成为未来网络发展的主要方向,而传统基于总线和中央处理器结构的路由器难以提供高速率和高可靠的端到端服务质量保证,必须对传统的路由器体系结构进行改造,提出分布式路由器的体系结构。该文分析了高速QoS路由器在路由查找、数据交换和阻塞控制等方面存在的问题,并给出了相应的解决方案。     

一种基于种族分类进化的QoS异构组播路由机制

随着新型网络应用的大量涌现,传统的网络技术已无法满足当前应用在带宽、延迟及出错率等方面的需求,IP over DWDM光互联网以其独特性能优势成为研究热点。基于种族分类进化算法,提出了一种IP over DWDM光互联网服务质量QoS异构组播路由机制。具体地,利用概率论方法处理网络状态参数信息的不确定性;引入模糊数学方法,确定用户对QoS的需求并提供柔性QoS支持;综合考虑网络提供方和用户方的利益,设计公平的带宽定价方法。仿真结果表明,该路由机制获得了良好的综合性能指标,可以有效地解决IP over DWDM光互联网中的柔性QoS异构组播路由选择问题。     

面向非全互连3D NoC可靠通信的分布式路由算法

针对非全互连三维片上网络架构中存在的硅通孔(TSV)寻找困难和可能产生层间IP核隔离等问题,提出一种分布式容错路由算法.通过在每个路由器中添加TSV上/下表,可使层间通信数据包在发送前找出最优TSV的地址,保证层间IP核的有效通信和数据包的最短路径传输.若数据包到达非目的层,则在TSV上/下表中找出最优TSV的地址后继续传输;若是到达目的层,则使用文中提出的平面容错路由算法找到目的节点.实验结果表明,在均匀流量模式下网络故障率达到25%时,该算法仍与无网络故障的传统XYZ算法性能相近,且在网络无故障时的延时及吞吐率均优于参考对象.     

地理异构的超级邻接路由算法

在结构化对等网络中,结点基于结点标识选择下一路由跳.路由过程与IP网络独立,路由时延较高.针对结构化对等网络路由时延较高的问题,提出了超级邻接路由算法,该算法在选择路由时同时考虑了对等网络路由表和IP网络的邻近性.把对等网络连接矩阵表示为R,IP网络连接矩阵表示为T.提出的超级邻接路由算法通过R×T2连接矩阵选择下一路由跳.实验结果表明,超级邻接路由算法极大地提高了路由效率、降低了对等结点平均负载.     

MPLS-VPN技术及市场

一、什么是MPLS-VPN MPLS-VPN是一种基于MPLS（Multiprotocol Label Switching,多协议标记交换）技术的IP-VPn,是在网络路由和交换设备上应用MPLS技术,简化核心路由器的路由选择方式,利用结合传统路由技术的标记交换实现的IP虚拟专用网络（IP-VPN）,可用来构造宽带的Intranet、Extranet,满足多种灵活的业务需求.     

Measurement and performance of a cognitive packet network

As the size of the Internet grows by orders of magnitude both in terms of users, number of IP addresses, and number of routers, and as the links we use (be they wired, optical or wireless) continuously evolve and provide varying reliability and quality of service, the IP based network architecture that we know so well will have to evolve and change. Both scalability and QoS have become key issues. We are currently conducting a research project that revisits the IP routing architecture issues and proposes new designs for routers. As part of this effort, this paper discusses a packet network architecture called a cognitive packet network (CPN), in which intelligent capabilities for routing and flow control are moved towards the packets, rather than being concentrated in the nodes. In this paper we outline the design of the CPN architecture, and discuss the quality-of-service based routing algorithm that we have designed and implemented. We then present our test-bed and report on extensive measurement experiments that we have conducted.     

Minimization of Multicast Traffic and Ensuring Its Fault Tolerance in Software-Defined Networks

In recent years, the widespread TCP/IP computer network model has been replaced by the software-defined network model, where the control plane is separated from the data plane and is logically centralized. The new model requires a revision of traditional network control protocols. One group of such revised protocols consists of multicast routing protocols. In this paper, the multicast routing protocols used in traditional TCP/IP networks are analyzed, and their basic disadvantages and difficulties in their application in software-defined networks are revealed. Multicast routing algorithms that use the capabilities of software-defined networks and ensure the optimization and reliability of routes in multicast routing are described. These algorithms are exempt from the drawbacks of traditional networks. The proposed algorithms are implemented as an application for the RunOS controller. This experimental study shows that the delays due to the use of the proposed algorithms for restructuring routes satisfy the requirements of telecommunications operators of large regional networks.     

IP QoS路由算法研究综述

传统上所采用的“尽力而为”转发机制,已经不能满足用户的要求。IP网络如何提供QoS(服务质量)支持这一问题现已成为业界关注的焦点。近几年的研究表明网络路由算法对实现QoS起到了非常关键的作用,同时网络路由算法也是平衡网络负载和充分利用网络资源的重要保证。该文对当前研究的主要路由算法进行了详细的分析与归纳,并对其发展前景进行了展望。     

SPAD: A distributed middleware architecture for QoS enhanced alternate path discovery

In the next generation Internet, the network will evolve from a plain communication medium into one that provides endless services to the users. These services will be composed of multiple cooperative distributed application elements. We name these services overlay applications. The cooperative application elements within an overlay application will build a dynamic communication mesh, namely an overlay association. The Quality of Service (QoS) perceived by the users of an overlay application greatly depends on the QoS experienced on the communication paths of the corresponding overlay association. In this paper, we present super-peer alternate path discovery (SPAD), a distributed middleware architecture that aims at providing enhanced QoS between end-points within an overlay association. To achieve this goal, SPAD provides a complete scheme to discover and utilize composite alternate end-to-end paths with better QoS than the path given by the default IP routing mechanisms.     

Interoperable routing for IN and IP Telephony

This paper discusses the problem of interoperability of Internet protocol (IP) telephony and switched-circuit networks (SCN) in the area of routing information. We describe and analyze a solution for directory-based routing. We will present an architecture based on a distributed database on the SCN and the IP network. The aim of the solution is to provide efficient service management, close to optimal routing for all calls including calls to 800- and cellular numbers and personal number portability between both the network technologies. The solution is based on similar, but differing in detail, approaches for each network. In the IP network, we use the telephony routing over IP (TRIP) protocol developed by Internet Engineering Task Force (IETF). Additionally, the described architecture is open for inclusion of the telephone number mapping (ENUM) protocol that is under development. For the circuit-switched network, we suggest a new protocol called circuit telephony routing IP (CTRIP). The protocol provides a distributed method for synchronizing routing information between databases. Furthermore, we propose numbering gateways for transferring number information between the two network types. We utilize the server cache synchronization protocol (SCSP) as the common element for data synchronization and replication among distributed entities. We also discuss briefly the design of a test implementation of the proposed infrastructure functions and protocols under development in our laboratory. In conclusion, we propose designing a common interoperable routing information infrastructure for the emerging hybrid SCN/IP telephony network.     

宽带IP城域网的路由设计

分析，比较了常用的网络路由算法，提出了在宽带IP城网中网络路由算法的选择问题，文章以一个电信宽带IP城域网为背景，介绍了大型城域网络系统中IP路由设计方案。     

基于RAM和TCAM存储结构的高速路由查找算法

由于因特网速度的不断提高,网络流量的不断增加和路由表规模的不断扩大,IP路由查找已经成为制约核心路由器性能的主要瓶颈。文章分析了两种常用的基于硬件存储器的路由查找算法,并结合它们各自优点,提出了一种基于RAM和TCAM存储结构的路由查找算法,该算法克服了上述两种算法的不足,具有查找速率高、更新时间快、存储代价低、易于实现等特点,是一种理想的适合于高速核心路由器环境的查找机制。     

基于群集智能技术的网络路由算法研究

Internet的巨大增长,使得路由体系在可扩展性、鲁棒性方面的要求不断提高.为了满足这一需求,本文在分析群集智能技术机理基础上,介绍了基于该技术的网络路由体系基本思想及算法描述.为了进一步提高算法性能,对路由算法实现中的几个关键问题进行了研究分析.     

卫星路由算法研究

对目前几种主流的组网技术,包括异步传输模式(ATM),网际互连协议的协议栈(IP),多协议标签交换(MPLS),卫星网络与地面网络的网络构成、拓扑以及通信时延等特点作了分析比较,同时对地面网络上的主要的路由算法进行了分析,主要包括距离向量算法和链路状态算法等：给出了运行于卫星网络上的路由算法,并对路由算法的三种策略进行了分类分析,其中基于虚拟拓扑路由策略的路由算法多用于基于像ATM等面向连接的网络;而采用虚拟节点概念的路由算法常用于基于IP的路由;基于拓扑依赖策略的路由算法,对于特定的星座网络将会有较高的效率。     

A conceptual framework for multiple‐criteria routing in QoS IP networks

The provision of quality of service (QoS) in IP‐based networks, namely QoS IP networks, has led to new demands for routing methods, protocols and algorithms. It is widely recognized that such QoS routing should take into account multiple criteria. In this case, contemporary approaches in multiple‐criteria analysis should be taken into account, and they differ essentially from classical routing approaches. An alternative to classical routing algorithms that are not quite able to respond to all the challenges of QoS IP networks, especially from the perspective of Future Internet, is to change routing approaches and algorithms to provide for consistent multiple‐criteria routing approaches. This is also related to the understanding of the concept of hierarchy in routing, discussed in the paper. The paper recalls the concept of objective ranking, shows its appropriateness for consistent multiple‐criteria routing and presents a conceptual framework for routing based on objective ranking, including hierarchy of routing optimization and multiple routing tables. The paper has a conceptual nature, with the purpose of analyzing possible approaches to multiple‐criteria routing that might be useful if not today, then in the engineering of future networks. However, a network engineering interpretation of the concepts proposed here is also presented.