高性能并行分组交换结构的研究

随着高速宽带通信网络的发展,网络设备的交换能力正成为制约现代网络发展的主要瓶颈之一.并行交换结构能够极大提升网络设备的交换能力,使网络设备拥有更高的交换容量和交换速率,以支持更多的网络业务.本文从交换结构模型的角度较深入的研究了高速路由器调度算法,并在基于参考交换结构和库存论原理对并行分组交换(PPS)结构稳定工作进行定义的基础上,分别分析了无输入缓存PPS和带输入缓存PPS稳定工作的充要条件.     

一种基于输入排队的并行交换结构

并行交换结构能够将多个G比特级的交换结构组建成T比特级(甚至更高级)的交换系统,从而极大提升网络设备的交换能力.本文基于输入排队提出一种只需要低速率缓存和支持包保序的新型并行交换结构VOIQ-PSA,对该交换结构的稳定性进行了理论分析,并通过仿真实验将VOIQ-PSA与目前已提出的其它并行交换结构在时延性能方面进行比较.实验结果表明,VOIQ-PSA交换结构的时延性能优于其它并行交换结构,并且非常适合高速网络环境.     

并行分组交换中负载平衡充要条件的分析

负载平衡是并行分组交换(PPS-parallelpacketswitch)结构的一项关键技术,该文对带缓存PPS结构中负载平衡的充要条件进行了研究。首先基于守恒原理建立流体并行交换的流量守恒方程,并分析流体并行交换中负载平衡的充要条件,在此基础上建立PPS的流量守恒方程,并定义PPS负载平衡,分析PPS负载平衡算法应该满足的充要条件。     

支持多优先级分组交换调度算法研究及其调度器设计

输入缓存交换结构的特点是缓存器和交换结构的运行速率与端口速率相等、实现容易,但存在队头阻塞。如果采用虚拟输出排队方法和适当的分组调度算法可予以消除,使吞吐率达到100%。文章首先研究讨论了并行迭代匹配算法,滑动迭代匹配调度算法的基本原理、迭代仲裁步骤及其硬件实现;对高速分组交换调度算法的性能进行了分析比较。然后给出了在高速输入队列交换机中实现多优先级调度算法的调度器设计与实现方案。经设计实现证明高速分组交换调度算法不仅硬件实现简单,而且具有良好的特性。     

输入缓存Clos网络中分布式正交分路路由算法

提出了一种采用输入缓存MSM结构的Clos网络,该结构适用于高速交换网络。提出了这一结构中的路由算法,该算法采用正交分路的方法来减小网络内部的冲突,引入路由优先级来提高网络内部的链路利用率,使用优先级轮转来均衡网络内部负载。针对这一路由算法,还给出了与之对应的信元调度算法。仿真表明,尽管采用共享缓存的MSM结构内部使用了很高的加速比,但是采用了正交分路的路由算法后,输入缓存MSM结构,可以获得比共享缓存MSM结构更好的时延及吞吐性能,更适合在高速大容量多端口的路由器或交换机中采用。     

基于输入排队的高速交换调度算法研究

高速交换网络一般采用基于定长信元的交换结构,其性能决定于排队策略和信元调度算法.输入排队策略只有和一个有效的调度算法相结合,才能保证交换结构具有良好的吞吐率和时延等性能.主要阐述了基于VOQ的最大数量匹配算法,最大权重匹配算法,稳定结合算法,神经网络算法等输入排队调度算法,分别从技术特点,性能指标和实现复杂度等多个方面进行比较和分析.分析了分布式和集中式两大类调度算法的工作方式,并根据各类算法的特点提出,神经网络算法可以通过定义其优先级函数实现其余各类算法.     

一种可提供QoS保证的交换结构

面向以太网的物理帧时槽交换（EPFTS）是四川省网络与通信技术重点实验室提出的“单物理层用户数据传输平台网络”中的关键技术,它是以“面向以太网的帧”为数据传输单元的高速交换技术,正是针对实现EPFTS而提出的交换结构方案。在对常用的交换结构和调度算法进行分析的基础上,针对EPFTS要达到的目标和技术特点,提出了一种能够在物理层交换中保证服务质量的交换结构,称为基于总线的、每输入-输出独立的输出缓存交换结构,同时提出了逻辑队列的排队策略,并对该结构进行了软件仿真。仿真结果表明,使用加权公平调度算法,提出的交换结构对实时业务可提供端到端的QoS保证,对非实时业务可提供最大-最小公平服务。     

一种无权重的高性能CICQ结构调度算法

在Crossbar交换单元的交叉节点加少量缓存的组合输入交叉节点排队(CICQ)结构，具有调度算法简单、性能优良、适于高速大容量路由器实现的特点。在总结现有研究成果的基础上，提出了一种避免仲裁指针同步的异步指针轮询算法。该算法将所有的输入、输出仲裁器的指针全部设置为异步，每个时隙静态地更新所有的仲裁器的指针，以达到网络指针去同步的目的。仿真结果表明，该算法在保持无权重算法简单性同时对不同业务流下的时延和吞吐率性能均有明显改善。     

一种新的PPS流量分配算法及分析

该文提出并分析一种新的并行分组交换(PPS)流量分配算法NF-UA,首先证明NF-UA算法是均匀流量分配算法,在计算出输入端口高速缓存写入Cell的速度的基础上确定了高速缓存的最小值和PPS结构的相对时延,与已有的算法相比,NF-UA算法性能良好。     

高性能路由器输入排队模型的研究与实现

目前基于输入队列技术的路由器研究日益活跃。本文讨论了路由器的交换方式、阻塞问题、调度算法等设计高速路由器的输入排队模型时所要考虑的关键问题,通过对相关的技术进行比较和选择,给出了一个交换式高速路由器中输入排队模型的设计方案。     

A terabit multiservice switch

This article describes a terabit multiservice switch architecture. Because of its multiterabit switching speed, quality of service (QoS) support capability, multiprotocol capability including TDM, and scalability, the Cyclone switch architecture is directly applicable in the following areas and many more: multiterabit switching at the Internet core, terabit routers and carrier-class ATM or MPLS switches; aggregation for all optical networks; unified packet/circuit switching platform; and high-end enterprise applications. The Cyclone switch architecture enables a scalable switching platform from multiple Gbits to multiple Tbits per second in five custom 0.18-micron CMOS ICs. A wire-speed scheduling capability supports eight quality of service classes and a million flows     

利用Windows失效恢复机制的网络冗余快速切换的实现

为了保证网络服务的稳定性,提高网络冗余链路的切换速度,文中分析了Windows驱动程序接口规范中的失效恢复机制以及网络冗余链路切换过程中数据包丢失的原因。通过采用主动发送ARP广播和重发数据的方法提高网络链路冗余切换速度,获得了快速切换的效果。在实际应用中,使用这种方法能够将网络冗余链路的切换时间降低到4ms。     

A neural-network contention controller for packet switchingnetworks

A novel approach to solving the output contention in packet switching networks with synchronous switching mode is presented. A contention controller has been designed based on the K-winner-take-all neural-network technique with a speedup factor to achieve a real-time computation of a nonblocking switching high-speed high-capacity packet switch without packet loss. Simulation results for evaluation of the performance of the K-winner network controller with 10 neurons are presented to study the constraints of the "frozen state" as well as those of same initial state. An optoelectronic contention controller constructed from a K-winner neural network is proposed.     

分组交换网络中的调度算法研究分析

该文讨论了分组交换网络中的调度算法,从交换结构模型的角度对现有的调度算法进行了分类和比较,对该领域的成果进行了较全面的总结,对当前研究的新热点进行了重点分析,为进一步的研究提出了新的课题和思路。     

分组交换网络中分布式调度控制算法研究

文章首先对目前分组交换网络中支持QoS的队列调度算法进行了比较研究,分析了其性能指标和技术特点。然后以Internet核心路由器中线卡级和交换级的队列调度设计为例,从控制论的角度提出了一种支持QoS的分布式加权轮询调度控制算法,同时对交换网络进行了仿真实验,吞吐率达到96％的仿真实验结果表明所提出的算法是有效的,最后,文章认为在实际应用中,应针对不同情况设计不同的调度控制算法,以便在复杂性、公平性、快速性及有效性等特性方面取得了一个折衷方案,以使分组交换网络的整体性能更好。     

The pipeline bus: An interconnection network for multiprocessor systems

The design of a network switch for synchronously clocked packet switching networks is presented. The switch includes the node interface and logic handling of the arbitration and routing for a large class of network topologies, namely n-dimensional rectangular grids including hypercubes and other highly efficient topologies. In the context of the SUPRENUM project the paper concentrates on two-dimensional meshes. Routing, arbitration, blocking, and fault tolerance issues are discussed.     

An algorithm for architecture partitioning in high-speed networks with bursty traffic

This paper analyzes the performance of a switching architecture. The performance measures include the elapsed time of packet transfer and the waiting time to begin transfer. The architecture is partitioned depending on the type of network used and the expected traffic in the network. Every partition has a switch with a buffer that can absorb surges of bursty traffic within the network partition. The buffer size depends on the type of the network and incoming traffic. The partition size depends on the network bandwidth, network traffic, packet size and buffer size. Examples of different networks are used to show the applications of the model. The results show that the elapsed time of packet switch transfer depends exponentially on the number of partitions in the network.     

QoS-aware path switching for VoIP traffic using SCTP

Voice over Internet protocol (VoIP) has been a prevalent multimedia service nowadays. It allows us to transmit voice data over IP networks. However, quality of service (QoS) is a major challenge to VoIP services. It must provide similar quality to traditional public switched telephone network or cellular phone services. Therefore, QoS related protocols have become important for real-time applications. Multi-protocol label switch (MPLS) is one of the important techniques to improve the network performance from QoS point of view. It employs label swapping to speed up packet forwarding. However, when a large number of users utilize VoIP services, the network congestion issue still exists. It causes delay, jitter and packet loss that affect VoIP QoS. In this paper, we propose a QoS-aware path switching strategy by using stream control transmission protocol (SCTP) in MPLS network to improve the VoIP traffic. This was done by employing SCTP selective acknowledgment mechanism to report the transmission parameters of primary path and to determine the criteria to switch to backup path. Simulation results show significant improvement in VoIP QoS.     

用多路分段式环形总线实现的ATM交换机

众所周知,异步传输模式（ＡＴＭ）网络的带宽可以满足多媒体应用的需求。在ＡＴＭ网络中,交换机是一个主要的瓶颈。本文中,我们准备采用多路分段式环形总线网（ＭＰＣＢＮ）来构造ＡＴＭ交换机,它采用多路总线来提供并提供并行传输,并可以通过有限投影平面来使硬件复杂度由一般多路总Ｏ（Ｎ＾２）降低到Ｏ（Ｎ,√Ｎ）,并且可以使信元丢失率维持在几乎不变的水平上。     

Switch cost and packet delay tradeoff in data center networks with switch reconfiguration overhead

Cost minimization is a major concern in data center networks (DCNs). Existing DCNs generally adopt Clos network with crossbar middle switches to achieve non-blocking data switching among the servers, and the number of middle switches is proportional to the number of ports of the aggregation switches in a fixed manner. Besides, reconfiguration overhead of the switches is generally ignored, which may contradict the engineering practice. In this paper, we consider batch scheduling based packet switching in DCNs with reconfiguration overhead at each middle switch, which inevitably leads to packet delay. With existing state-of-the-art traffic matrix decomposition algorithms, we can generate a set of permutations, each of which stands for the configuration of a middle switch. By reconfiguring each middle switch to fulfill multiple configurations in parallel with others, we reveal that a tradeoff exists between packet delay and switch cost (denoted by the number of middle switches), while performance guaranteed switching with bounded packet delay can be achieved without any packet loss. Based on the tradeoff, we can minimize the number of middle switches (under a given packet delay bound) and an overall cost metric (by translating delay into a comparable cost factor), as well as formulating criteria for choosing a proper matrix decomposition algorithm. This provides a flexible way to reduce the number of middle switches by slightly enlarging the packet delay bound.