PIPIO：一个新的面向区分服务确保转发的主动队列管理算法

RIO是用于支持区分服务确保转发逐跳行为的主动队列管理算法，该算法是对RED算法的简单扩充。由于RED算法的性能对配置参数敏感，因此基于RED算法的RIO算法必然具有配置参数敏感的特点。PI算法是基于控制论的主动队列管理算法，具有队列长度抖动小的特点。PIP算法是PI算法的改进，比PI具有更快的收敛速度。本文基于PIP算法设计了一个新的主动队列管理算法PIPIO。该算法队列长度抖动小，同时能保护高优先级报文。     

Assured forwarding fairness using equation-based packet marking and packet separation

Fairness is one of the important problems in assured forwarding (AF) performance in the differentiated services (DiffServ) framework [An architecture for differentiated services, RFC 2475, IETF, December 1998; A two-bit differentiated services architecture for the Internet, Internet-draft, draft-nichols-diff-svc-arch-02.pdf, IETF, April 1999]. In this paper we present a two-part solution for the fairness problem in AF. The first part is a new packet marking algorithm called equation-based marking (EBM) and is based on the TCP model given by Padhye et al. [Modeling TCP throughput: A simple model and its empirical validation, in: Proceedings of ACM SIGCOMM ’98, October 1998]. EBM is to handle the problems found in other marking schemes regarding fairness among heterogeneous TCP flows through a tight feedback-loop operation and adaptation of the packet marking probability to network conditions. The second part is called packet separation used at routers to handle the fairness between responsive and non-responsive traffic. We evaluate the performance of a packet marker that uses EBM as the marking algorithm using in-depth simulation. We prove, analytically and using simulation, the correctness of the marking algorithm and compare it with other marking schemes for different network scenarios. We also use simulation to show the effectiveness of the packet separation mechanism in solving the fairness problem between responsive and non-responsive traffic. Our evaluation results demonstrate the effectiveness of EBM along with packet separation in providing the required fairness among heterogeneous flows and ensuring protection against non-assured traffic.     

A novel framework for IP DiffServ over optical burst switching networks

This paper presents a novel framework for IP Differentiated Services (DiffServ) over optical bursts witching (OBS), namely, DS-OBS. The network architecture, functional model of edge nodes and core nodes,the control packet format, a novel burst assembly scheme at ingress nodes and scheduling algorithm of core nodes are presented. The basic idea is to apply DiffServ capable burst assembly at ingress nodes and perform different per hop behavior (PHB) electronic treatments for control packets of different QoS class services at core nodes. Simulation results show that the proposed schemes can provide the best differentiated service for expedited forwarding (EF), assured forwarding (AF) and best effort (BE) services in terms of end-to-end delay, throughput and IP packet loss probability.     

TCRED:一种基于DiffServ的队列管理算法

AF PHB的实现机制是DiffServ网络的重要研究课题，目前的多数实现采用了RED或类似的队列管理技术，在分析了RED及其改进算法在公平性及分组优先级等方面存在的不足后，提出了一种采用同一组RED参数对三色分组实行队列管理的TCRED算法．TCRED对不同颜色的分组分别计算平均队列长度，并考虑了分组的到达和离去对平均队长的影响，据此计算出各色分组的丢弃几率，该算法能实现分组的相对优先级，保证用户所预定的带宽，同时能实现分组优先级的平滑升级和降级，因而很好地满足了AF PHB的要求。     

一种基于区分服务模型的分组丢弃算法

分组丢弃算法是区分服务模型中“逐跳行为”(PHB)的重要控制策略。目前Internet网络中采用的分组丢弃策略大多为尾部丢弃(DropTail),不能适应区分服务模型的要求;而RED及其改进算法也不能提供公平性和相对优先级的保证。文章简要分析了目前常见分组丢弃算法所存在的不足之处,提出了一种基于区分服务模型的新型分组丢弃算法----TCRED算法,该算法采用同一组RED参数对三种颜色的分组进行队列管理。实验表明,TCRED算法很好地满足了AFPHB的要求。     

区分服务网络中主动队列管理算法

现有区分服务网络的保证转发服务可提供稳定的带宽保证,但缺乏保证时延和分组丢失性能的有效方案.基于对RIO队列的稳态性能分析,提出两种自适应调整控制策略的主动队列管理算法(ARIO-D和ARIO-L).仿真结果表明,这两种算法在保持RIO算法带宽保证能力的同时,还可以提供稳定的和可区分的时延和分组丢失性能.采用ARIO-D和ARIO-L的保证转发服务可以为多媒体流量提供多种服务质量的定量保证.     

区分服务下RIO算法改进研究

对于目前区分服务下RIO算法中参数难配置等问题,提出一种基于区分服务的自适应的RIO算法--ARIO.该算法不但能很好地适应区分服务网络,而且能在不同的订购条件下获得更低的分组丢失率.     

一种适合MPEG-4传输的IP区分服务网络模型

文章提出了一种改进的适合MPEG-4视频传输区分服务的模型。根据MPEG-4视频流特点和网络的拥塞程度,视频服务器中,采用笔者提出的区分服务标记算法。边缘路由器中,采用笔者提出的区分服务调度算法犤1犦,设计了一种新的区分服务调度器,它动态调节加权服务量,适合在IP区分服务网络中运用,降低实时变比特率突发业务的延时和抖动。实验结果表明,在网络带宽不能保证实时MPEG-4传输所需带宽时,采用该文提出的网络模型,实时传输MPEG-4视频序列,恢复序列的主观效果以及峰值信噪比PSNR都优于传统的尽力而为(Best-effort)方法,并且端对端延时和延时抖动也达到实时传输的要求。     

区分服务网络中基于主动队列管理的病态流控制

在区分服务（Differentiated Services,DiffServ）网络中,为了消除病态流对确定性转发（Assured Forwarding,AF）服务的不良影响,提出了一种基于RIO（RED IN and OUT）的主动队列管理机制RIO SD。这种机制不需要在核心路由器维护每一个流的状态,而是通过观测虚拟队列的丢包历史记录来鉴别病态流,并通过虚拟队列的前置滤波器加大病态流的丢包率,实现对病态流的控制。仿真结果表明RIO SD可以有效抑制病态流对带宽的占用,提高其他正常流的性能。     

Fuzzy logic controlled RED: congestion control in TCP/IP differentiated services networks

The use of the Internet for time-sensitive services, such as voice and video applications, requires a predictable quality of service. The TCP/IP differentiated services (Diff-Serv) architecture was introduced to achieve such performance. Network congestion control, however, still remains a critical and high priority issue. A number of researchers are looking at alternative schemes such as random early detection (RED) and its variants to handle congestion. In this paper we present the results of a fuzzy logic control approach to the implementation of RED – Fuzzy-RED. We believe that with fuzzy logic we are able to use linguistic knowledge to implement better understood nonlinear probability discard functions, achieve better differentiation for packet discarding behaviors for aggregated flows, and so provide better quality of service to different kinds of traffic whilst maintaining high utilization.     

Design and analysis of a self-tuning feedback controller for the Internet

Active queue management (AQM) is an effective method used in Internet routers for congestion avoidance, and to achieve a tradeoff between link utilization and delay. The de facto standard, the random early detection (RED) AQM scheme, and most of its variants use average queue length as a congestion indicator to trigger packet dropping. This paper proposes a novel packet dropping scheme, called self-tuning proportional and integral RED (SPI-RED), as an extension of RED. SPI-RED is based on a self-tuning proportional and Integral feedback controller, which considers not only the average queue length at the current time point, but also the past queue lengths during a round-trip time to smooth the impact caused by short-lived traffic dynamics. Furthermore, we give theoretical analysis of the system stability and give guidelines for selection of feedback gains for the TCP/RED system to stabilize the average queue length at a desirable level. The proposed method can also be applied to the other variants of RED. Extensive simulations have been conducted with ns2. The simulation results have demonstrated that the proposed SPI-RED algorithm outperforms the existing AQM schemes in terms of drop probability and stability.     

基于模糊RED算法的IP拥塞控制机制

TCP／IP拥塞控制不能有效地支持Internet多媒体业务，模糊逻辑提供了解决复杂性、动态性和健壮性问题的一种非解析方法，文章基于模糊RED算法和区分服务提出了新的IP拥塞控制机制。与丢尾算法和普通RED算法相比，在保证QoS的同时，该算法不仅改善了TCP的吞吐量，而且使流量抖动较平缓，并克服了区分服务对连接公平性差的缺点。     

区分服务中的分组标记策略研究

区分服务是近两年的一个研究热点,其目的是为用户提供较大粒度的服务质量(QoS)保证.与集成服务模型相比,区分服务不仅具有良好的可扩展性,而且更容易在传统IP分组交换网络上实现.研究了区分服务的一个关键机制——分组标记策略,并提出了一个具有公平性的分组标记算法(fairmarkingpacketalgorithm,简称FMPA),通过仿真把该算法与现有的等比例的标记算法进行比较.此外,还提出了一种分组再标记(remarking)算法,该算法可尽可能地维护分组原有的服务语义.通过仿真对该算法进行了验证.     

A distributed-request-based CDMA CAC for DiffServ multimedia services in wireless cellular mobile networks

In this paper, a distributed-request-based CDMA DiffServ (differentiated service) call admission control (CAC) scheme is proposed to provide various multimedia services seamlessly in wireless mobile Internet. Conventional CDMA CAC schemes cannot fully support DiffServ QoS (Quality of Service) and seamless handoff due to lack of consideration on service priority and seamless mobility. Therefore, in order to achieve QoS guarantee for each service class, seamless fast-handoff, and high utilization of the scarce wireless resource, we define a code assignment policy and an adaptive access permission scheme taking each user’s service priority and mobility into consideration. For that purpose, in the proposed scheme, the DQRUMA/CDMA is combined with the new code assignment scheme and the adaptive access permission probability (APP). Numerical examples show that the forced termination ratio of handoff calls is guaranteed to be much less than the blocking ratio of new calls for a seamless fast-handoff while proposed scheme provides QoS guarantee for each service class efficiently.     

区分服务的动态队列管理策略

提出了一种区分服务的动态队列管理策略—BDRED。该策略根据聚集间的丢包比率在聚集间动态地分配缓存,保证了不同服务之间带宽资源的公平分配。仿真试验结果表明,该策略能根据网络实时环境动态调整聚集间的带宽分配并且有效地降低了TCP分组丢失率。     

一种支持DiffServ模型的全分布式调度算法

调度算法设计对于网络路由设备实现区分服务(DiffServ)模型的单跳行为(per hop behavior,简称PHB)至关重要.现有支持DiffServ模型的调度算法普遍基于输出排队(output queued,简称OQ)或是输入排队(input queued,简称IQ)交换结构进行设计,均无法在高速环境下提供高性能的调度.基于联合输入/交叉节点排队(combinedinput-crosspoint-queued,简称CICQ)交换结构提出一种支持DiffServ模型的全分布式调度算法DDSS (distributed DiffServ supporting scheduling),并通过理论分析对其公平性进行了验证.DDSS算法采用基于预约带宽的逐级流量控制机制实现所有预约带宽在快速转发(expedited forwarding,简称EF)业务与确保转发(assured forwarding,简称AF)业务之间的分配,采用优先级调度机制为EF业务提供低延迟服务,算法复杂度为O(log N).仿真结果表明,DDSS算法具有良好的时延性能和公平特性,与现有算法相比,能够更好地支持DiffServ模型.     

Stability of TCP/RED systems in AQM routers

By applying the time-delay control theory to a TCP/RED dynamic model, this note establishes some explicit conditions under which the TCP/RED system is stable in terms of the average queue length. Then, the stability region is discussed. Finally, the results are illustrated by using ns2 simulations, which demonstrates that it is able to choose an appropriate control parameter max/sub p/ of RED based on the stability conditions derived in this note, to achieve satisfactory network performance. It is found, by comparison, that this improved performance is better than that of three other typical active queue management (AQM) schemes-the random exponential marking (REM), proportional-integral (PI) controller, and adaptive virtual queue (AVQ) schemes.     

基于反馈的区分服务网络拥塞管理方案研究

为了有效解决RED算法拥塞响应滞后以及在聚集类之间公平性不足的问题,提出建立一种基于早期拥塞指示反馈的区分服务网络模型,并在该模型上采用优先级早期随机检测算法。在网络入口节点对分组进行分类、聚集与监测,各队列按优先级设置不同队列长度阈值,当平均队列长度或各队列长度达到相应阈值范围时,立即触发不同程度拥塞指示包向源端反馈。使用改进的NS进行了仿真实验,实验结果表明该算法使得拥塞指示能尽可能快地到达TCP源,有效地降低路由器中的丢包率。提高网络利用率,并且为不同的聚集类提供不同优先级服务,保障了聚集类的公平性。     

区分服务网络中带宽利用的公平性

为了解决DiffServ网络中带宽利用的不公平性 ,该文提出了一种自适应的数据包标记算法AFM(AdaptiveFairMarker) .与现有的标记算法相比 ,它有两个显著的不同 :( 1)增加了一种带宽估计机制 ,对网络中可使用的带宽进行动态估计 ,并将所估计的带宽以按比例的方式公平地分配给各个汇聚流 ;( 2 )对TCP协议作了一个微小而又非常有效的改进 ,在控制TCP拥塞窗口的同时尽量避免TCP协议的AIMD机制 .该文通过仿真试验对算法进行了验证 ,结果证实AFM算法比其它几种算法具有更好的公平性     

主动队列管理中P I 字节模式和包模式

主动队列管理(AQM)是近年来TCP端到端拥塞控制的一个研究热点，其中PI拥塞控制机制是建立在RED拥塞控制基础上的一种控制机制．PI机制基于两种方法控制网络拥塞现象：跟踪实时队列长度及拥塞情况下以一定概率丢弃到达队列的数据包．以上方法的计算可以基于包数目或字节数，而方法选择的不同对网络会产生不同的影响．仿真量化性地测定使用不同队列计算和标注方法情况下对通信性能产生的影响．同时，PI控制器与RED控制器在相同模式和参数设置下进行比较，可显示出PI控制具有一定的优越性．