时延及时延抖动限制的最小代价多播路由策略

满足多种服务质量请求的多播路由问题是目前多播通信中的重要课题之一。该文作者在研究受端到端时延及时延抖动限制的多播路由问题的过程中，发现当前许多算法所普遍使用的两个最佳链路选择函数并不能完全体现路由的动态过程，同时它们还存在一定的缺陷。而正是由于这种缺陷，在某些情况下通过这两个最佳链路选择函数所得到的结果树可能不包含所有的目标节点，文中称这种情况为“多播不可达”。针对上述问题，该文提出了“多播可达”的假设条件以及一个新的最佳链路选择函数，并在此基础上提出了一个满足时延及时延抖动双重限制的最小代价多播树的建立算法（DDVBMRA）以及一种动态重组多播组目标节点的方法。仿真结果表明本算法具有很好的延抖动及代价性能。     

一种时延受限的最优时延抖动路由算法

研究多播端到端时延受限条件下的最优时延抖动问题,提出一种有效的多播路由算法。通过修改源节点到目的节点的路径,使时延较小的目的节点获得尽可能大的时延值,时延较大的目的节点获得尽可能小的时延值。仿真结果表明,该算法能获得较小的时延抖动。     

多链路时延反馈共享令牌流量拥塞控制

流量调度的目标是提高网络资源的利用率,改善网络应用的性能,针对多链路环境下流量控制机制存在的问题,设计了一种多链路共享令牌缓冲池流量调度模型,分析了链路中数据传输时延特点,提出一种基于时延反馈信息的共享令牌流量拥塞控制算法,根据链路时延选择函数对多链路进行反馈流量调度。实验结果表明,该算法可以有效地减少数据在链路访问延时,而且链路流量的平滑性、带宽利用率等都比其他传统调度算法要好,适合于高性能宽带接入链路流量控制的应用。     

基于关键节点时延约束低代价组播路由算法

针对时延约束下低代价组播树的构建方法,提出了一种基于关键节点的时延约束低代价组播路由算法.该算法对已有的动态时延优化的链路选择函数进行改进,并加入关键节点和关键次数的概念.在首次选择目的节点时,重点考虑关键节点和关键次数因素,降低了选择低代价链路的时间复杂性,再利用改进后的链路选择函数依次选择节点加入树中,进而产生满足要求的组播树.实验仿真结果表明,该算法不仅能正确构建出时延约束低代价组播树,且与其他算法相比,构成组播树所需平均时间更少.     

基于链路循环的网络时延模拟方法研究

针对当前网络时延模拟软件量程窄、精度低、资源占用高的问题，提出一种基于链路循环的网络时延模拟方法。该方法将时延模拟分为两个阶段：第一阶段通过链路循环实现宽量程的时延模拟，第二阶段通过内存队列缓冲数据实现精度优化。实验结果表明，该方法能够以微秒级精度实现秒级时延模拟。此外，相较于主流时延模拟软件NetEm，该方法能在各个带宽下降低55%～80%的内存占用，在满足精度需求的同时极大地降低系统成本。     

基于排队时延主动探测的多路传输拥塞控制

为解决传统基于时延的MPTCP拥塞控制算法被动地等待重传超时或重复确认来确认链路拥塞,不能及时避免拥塞的问题,提出以满足多路径流公平性为基础,实施链路RT T主动探测,设计并实现一种基于排队时延主动探测的拥塞区分链路质量优化协议PPQD,以排队时延预测结果及其均值比较为依据实施拥塞窗口动态调整.实验结果表明,该方法可大幅减少窗口抖动,在吞吐量较LIA提升超20％ 的同时进一步保障了用户体验质量.     

面向时延的NoC映射技术研究

针对NoC任务映射问题中时延难以预测和启发式算法效率低的问题,提出一个时延改进模型和近邻随机遗传算法。该模型从宏观的链路负载分布和单个节点的排队时延两方面来构建NoC映射的时延模型,通过引入时延因子、权重系数来刻画不同映射方案对时延性能的影响,避免了NoC通信时延精确建模的难题。提出近邻随机思想来构建遗传算法的初始种群,并且运用该算法实现了面向时延的NoC映射,在达到全局最优的情况下,比经典遗传算法效率提升将近20%。实验结果表明,该算法优于现有的经典遗传算法和随机映射方案。     

基于网络演算的卫星网络端到端时延上界北大核心

针对卫星网络链路传播时延周期性变化且变化量不可忽略,传统时延边界计算过于放大排队时延等问题,提出了一种卫星网络端到端时延上界分析方法。通过计算星间链路长度推算链路传播时延,并将链路处于峰值速率时的排队时延作为链路排队时延最大值,计算卫星网络端到端时延上界。进一步,分别研究端到端路径包含节点数目、节点服务速率、业务流权重值以及突发量等对卫星网络端到端时延上界的影响。仿真结果表明,在铱星拓扑结构下,卫星网络的端到端时延上界比基于令牌桶模型计算的端到端时延上界更接近于仿真值。     

一种满足时延和时延抖动约束的多播路由算法

多播路由已有广泛的应用,但对于实时多播应用,多播路由的同时必须提供QoS保证。为此,论文研究带有时延和时延抖动约束的多播路由问题,通过对Dijkstra最短路径算法的扩展,提出一个快速有效的满足时延和时延抖动约束的多播路由算法EDDVCMR。实验结果表明,对解决带有时延和时延抖动约束的多播路由问题,该算法与DVMA算法相比,有高出7%的求解成功率,同时,算法执行的CPU时间减少36%。     

以太网时延仿真与性能分析

通信时延是衡量网络性能的重要指标之一。分析了以太网通信网中影响通信时延的有关因素,以太网络拓扑结构为高校校园网络模型,借助Opnet仿真并分析了不同节点数目、不同链路传输速率以及不同中心服务器配置对网络时延的影响。     

Delay-jitter control in multimedia applications

The growing needs of multimedia communications are leading to new developments in providing real-time communication with guarantees. Several extensions have been proposed for different layers of the Open Systems Interconnection Reference Model to accomodate these needs. In this paper, we study methods for guaranteeing delay jitter bounds for high-speed networks in the network and application layers of this model. The method proposed for the network layer provides distributed jitter control. The method proposed for the application layer allows the destination application to control delay jitter. We use a simulation to compare the effects on delay jitter in each method for various scenarios, such as constant bit rate, cross traffic, and bursty data. In addition, the buffer space requirements for accommodating real-time channels are monitored at each node in the network.     

无线传感器网络实时媒体传输速率控制机制

无线传感器网络(Wireless Sensor Network,WSN)传输实时媒体面临带宽受限,时变和高误码等信道特征的挑战,常采用自适应速率控制技术并结合链路层重传机制,但增大了传输时延.本文采用IEEE802.11构建WSN,分析引发链路层重传的原因,推导满足重传时延最小的传输层包长调整方程和结合TFRC(TCP Friendly Rate Control)建立WSN实时媒体传输的速率控制机制(WSN Rate Control,WSNRC).仿真结果表明,该机制能有效改善降低丢包率(Packet Loss Rate,PLR),实时媒体帧平均传输时延和帧时延抖动等指标和具备传感器节点间的公平特征.     

基于行动预测的支持移动自组网QoS的路由方案

从研究高斯-马尔可夫运动模型出发，提出了一个可用于预测移动自组网中节点间最大链路有效时间的模型。从提供Qos路由度量和改进被动路由协议两个方面阐述了提供移动自组网Qos支持的机制。仿真实验表明，新的路由方案具有网络吞吐量大、抖动小和时延可控制的特点。     

Design novel weighted rating of multiple attributes scheme to enhance handoff efficiency in heterogeneous wireless networks

With the availability of multiple access interfaces, mobile device users can move between heterogeneous wireless networks. Service providers now must try harder to satisfy their users by ensuring connection service quality. The vertical handoff scheme plays an important role in this endeavor. We propose a novel handoff scheme that features two operating processes: attributes rating and network ranking. A self-developed WRMA (Weighted Rating of Multiple Attributes) method is used to rate attributes. TOPSIS is employed to rank networks. The WRMA-based handoff scheme, as we shall call it hereafter, select an AHP-SAW handoff model to compare with. The WRMA, which rates attributes directly, is relatively simple to use. Further, TOPSIS was found to be more precise than SAW in ranking networks. We also compared our handoff scheme with the traditional NIST signal handoff model. Four Key Performance Indicators of packet drop ratio, delay, jitter and throughput were applied in our experiments. Results demonstrate our handoff scheme outperformed the NIST model in lowering packet drop ratio for all four traffic types. Higher average throughput is achieved. Experiments also show improvements on packet delay and jitter. Such improvements can significantly enhance link service quality, making it more suitable for voice and video traffic applications.     

Storage space estimation for videos using fading channels

In this paper, we propose a model for estimating the buffer storage for providing continuous delivery of the video data to users. The model incorporates the jitter delay, which is a switching delay between two consecutive video segments being transmitted through a logical channel. The jitter delay is assumed to be Rayleigh distributed as it characterizes the channel fading.     

Reducing Queue Oscillation at a Congested Link

Queue length oscillation at a congested link causes many undesirable properties such as large delay jitter, underutilization of the link and packet drops in burst. The main reason of this oscillation is that most queue management schemes determine the drop probability based on the current traffic without consideration on the impact of that drop probability on the future traffic. In this paper, we propose a new active queue (AQM) scheme to reduce queue oscillation and realize stable queue length. The proposed scheme measures the current arrival and drop rates, and uses them to estimate the next arrival rate. Based on this estimation, the scheme calculates the drop probability which is expected to realize stable queue length. We present extensive simulation with various topologies and offered traffic to evaluate performance of the proposed scheme. The results show that the proposed scheme remarkably reduces queue length oscillation compared to other well-known AQMs. It is also shown that the proposed scheme improves fairness among TCP flows due to the stable drop probability, and maintains high utilization with small queue length.     

A distributed fair scheduling scheme in wireless LAN

This paper proposes an algorithm named WLFVC, which is a fully distributed wireless packet scheduling algorithm based on LFVC (Leap Forward Virtual Clock), to provide streams with fairness, especially in the short time scale. This algorithm is able to allocate band-width to streams proportional to their weights. Thus, better delay and jitter performance can be achieved. Since collisions and wireless link error degrade the performance of MAC protocols in the WLAN environment, WLFVC also takes them into consideration. Finally,this algorithm works in a fully distributed way and it can coexist with other stations that only support DCF (Distributed Coordination P-hnction).     

Control of perceived quality of service in multimedia retrieval services: prediction-based mechanism vs. compensation buffers

In multimedia systems end-to-end delay jitter has a great impact on the continuity of information playback. Therefore, it is necessary to introduce appropriate mechanisms to compensate for delay variations, so that the intramedia and intermedia temporal relationships can be preserved. In this paper, two methods for compensation of the network delay jitter in a distributed multimedia retrieval service are compared: the first is based on prediction of the network delay jitter suffered by each information unit and retrieval time modification at the source site; the second is based on a compensation buffer at the destination site. Comparison is made by assuming a master/slave relationship between the monomedia streams composing the multimedia data flow.     

KNX/EIB通信协议的实时性分析与改进

KNX/EIB通信协议在其链路层使用CSMA/CA机制解决通信冲突问题,虽然提高了KNX/EIB网络防冲突能力,却造成同等级命令帧数据传输时延抖动非常大,传输实时性大打折扣。提出对KNX/EIB实时性的改进方法KNX/EIB-A,在不改变原有的通信协议栈的基础上,将一个调度程序应用于KNX/EIB通信协议的应用层与用户应用程序之间;将原有的分布式平等结构划分为分级主从结构,对数据命令帧的发送进行调度。最后通过对KNX/EIB-A进行分析及原型实现,证明了该方法通过有效地减轻传输时延的抖动从而改进了协议的实时性。     

Dejittering in the transport of MPEG-2 and MPEG-4 video

When multimedia information is transported over a packet-switched network, the quality of presentation can be degraded due to network delay variation or jitter. This paper presents a dejittering scheme that can be used in the transport of MPEG-4 and MPEG-2 video to absorb any introduced network jitter, thus preserving the presentation quality of transported media streams. The dejittering scheme is based on the statistical approximation of delay variation in the arrival times of video packets carrying encoded clock reference values and a filtering and re-stamping mechanism. In addition, a brief overview of the MPEG-4 system is presented.