首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到19条相似文献,搜索用时 187 毫秒
1.
TCP流自相似性与网络性能关系的研究   总被引:2,自引:0,他引:2  
对TCP流自相似的原因进行了分析研究,讨论了TCP/IP协议与TCP流自相似特性的关系,用ON/0FF模型从理论上解释了TCP拥塞控制机制导致自相似现象的原因.通过基于NS平台的模拟试验,比较了自相似性与丢失率、重传初值的设定及其链路延迟的不同关系,从模拟结果可以看出,TCP流的分形程度和丢失率及超时重传有着直接的关系.  相似文献   

2.
随着以太网技术的迅速发展,基于以太网的链路层流量控制技术成为流量工程的一个重要组成部分。针对传统的基于漏桶式的以太网流控算法对于TCP性能影响较大的问题,论文提出了一种改进的漏桶式流控算法,该算法通过减少丢弃属于同一轮次的TCP报文来提高TCP的传输性能。仿真结果验证了该算法的有效性。  相似文献   

3.
精确的TCP丢包率上界对无线环境下TCP协议的性能改进具有指导意义;对进入无线自组网节点的TCP数据流进行漏桶管制,节点为TCP流提供基于速率-延迟(Rate-Latency)模型的服务保障,在已有无线自组网链路吞吐量模型的基础上利用网络演算理论推导了TCP数据流的丢包率上界模型;在网格拓扑的无线自组网环境下,TCP数据流丢包率的仿真结果都在数值计算的上界范围之内,表明基于网络演算的无线自组网TCP丢包率性能上界模型具有较好的性能.  相似文献   

4.
陈果  李庆华 《计算机工程》2010,36(18):95-97
对进入无线自组网节点的TCP数据流进行漏桶管制,节点为TCP提供基于速率-延迟模型的服务保障,在已有无线自组网链路吞吐量模型的基础上利用网络演算理论推导TCP数据流的吞吐量上界模型。在网格拓扑的无线自组网环境下,TCP数据流的仿真结果都在数值计算的上界范围内,从而表明基于网络演算的无线自组网TCP吞吐量性能上界模型具有较好的性能,同时也表明现有TCP协议在无线环境下还存在较大的改进空间。  相似文献   

5.
随着以太网技术的迅速发展,基于以太网的链路层流量控制技术成为流量工程的一个重要组成部分,基于漏桶式流控的以太网带宽控制算法被应用于驻地同环境当中。考虑到互联同中长时TCP业务流量增长迅速这一背景,评估以太网流量控制算法对长时TCP性能的影响有其积极意义。论文通过建模分析的方法,对于NewReno TCP算法在漏桶式带宽控制机制下的性能进行了分析,并通过仿真对结论进行了说明。  相似文献   

6.
论文对自相似网络环境中通用处理器共享(GeneralizedProcessorSharing,GPS)系统的性能进行分析研究,使用分形漏桶的包络轨迹曲线对进入GPS系统的自相似流整形,给出了利用自相似流量作为输入流的GPS系统的队列长度和时延的上界。数值分析显示,该模型具有较好的性能。  相似文献   

7.
区分服务是目前在IP网络服务质量控制方面被广泛采用的一种体系结构,它在网络边界对用户数据流聚集进行分类、测量、标记和整型,在网络核心转发,实现PHB,从而达到对不同类型的业务进行区别对待的目的.本文通过对UDP和TCP混合聚集流的行为特性分析,指出将UDP和TCP业务进行分离的必要性.通过对TCP聚集流的仿真实验和分析,阐述了TCP聚集流和单个TCP的行为差异、聚集流中具有不同RTT的TCP流的速率差别,以及聚集流中的流的数目和链路带宽对链路利用率的影响.最后通过对TSW2cm标记算法的仿真实验,分析了该算法在公平性方面的弱点,提出了一种基于TCP流状态信息的聚集流标记算法f-TSW2cm,并对算法进行了对比实验和结果分析.  相似文献   

8.
许多研究者已经发现,在无线链路上使用链路层自动请求重传(ARQ)来恢复无线链路差错,会在无线链路上和TCP源端产生大量的突发性流,从而使路由器拥塞,导致分组丢失和吞吐量下降.本文提出了一种解决方案,在ARQ的接收端,利用漏桶对接收确认分组进行平滑,使分组的发送能保持一定的间隔.仿真结果表明,平滑能提供更好的吞吐量性能和更低的丢失率。  相似文献   

9.
许玲 《微机发展》2003,13(8):98-100
提出了为网络多媒体应用程序提供服务质量(QoS)保障的4条基本原则与网络分组流管理的标准,分析了带权公平排队(WFQ)规则与漏桶管理机制,进一步深入讨论了将漏桶管理机制与WFQ规则结合的方式,为若干个不同的网络数据流在提供QoS的前提下公平合理地共享一定的网络带宽资源,提出了一种可行的方案,最后对漏桶 带权公平排队的调度管理方式中分组在WFQ队列中将经历的最大延迟时间进行了分析与证明。  相似文献   

10.
TCP流的宏观平衡性   总被引:4,自引:2,他引:2  
龚俭  彭艳兵  杨望  刘卫江 《计算机学报》2006,29(9):1561-1571
TCP流显式的连接建立和关闭过程决定了完整的TCP流的不同类型TCP报文之间在数量关系间保持一种宏观平衡性,这种数量间的约束所表现出的宏观平衡性可以用来揭示网络流量行为规律,识别网络流量行为异常的存在,从而可以成为网络安全监测和网络管理的有效手段之一.文章定义了TCP流宏观平衡性的相关测度,根据TCP流的到达模型和流长模型建立了测量误差的模型,并以此导出了实际测量模型和判断正常与异常的临界点.通过实验和仿真对这些测度进行了分析,证明了这些测度和临界点的可用性.  相似文献   

11.
论文对网络队列系统性能定量分析新型数学工具——网络微积分学进行了归纳和总结,利用网络微积分学证明了利用分形漏桶整形器对自相似业务进行整形不会增加网络端到端延迟上界,计算了通用处理器共享下以分形漏桶包络轨迹为到达曲线和以速度等待时间函数为服务曲线的端到端延迟确定性上界。  相似文献   

12.
This paper introduces a novel policing mechanism, called Packet Leaky Bucket in which all cells of a frame are marked with the same level of priority. Moreover, it discusses the need for having a frame discard mechanism in cell-switched networks when frame-oriented policing mechanisms are used.  相似文献   

13.
In this paper we present a solution for the IEEE 802.11e HCCA (Hybrid coordination function Controlled Channel Access) mechanism which aims both at supporting strict real-time traffic requirements and, simultaneously, at handling TCP applications efficiently. Our proposal combines a packet scheduler and a dynamic resource allocation algorithm. The scheduling discipline is based on the Monolithic Shaper-Scheduler, which is a modification of a General Processor Sharing (GPS) related scheduler. It supports minimum-bandwidth and delay guarantees and, at the same time, it achieves the optimal latency of all the GPS-related schedulers. In addition, our innovative resource allocation procedure, called the territory method, aims at prioritizing real time services and at improving the performance of TCP applications. For this purpose, it splits the wireless channel capacity (in terms of transmission opportunities) into different territories for the different types of traffic, taking into account the end-to-end network dynamics. In order to give support to the desired applications, we consider the following traffic classes: conversational, streaming, interactive and best-effort. The so called territories shrink or expand depending on the current quality experienced by the corresponding traffic class. We evaluated the performance of our solution through extensive simulations in a heterogeneous wired-cum-wireless scenario under different traffic conditions. Additionally, we compare our proposal to other HCCA scheduling algorithms, the HCCA reference scheduler and Fair Hybrid Coordination Function (FHCF). The results show that the combination of the MSS and the territory method obtains higher system capacity for VoIP traffic (up to 32 users) in the simulated scenario, compared to FHCF and the HCCA reference scheduler (13 users). In addition, the MSS with the territory method also improves the throughput of TCP sources (one FTP application achieves between 6.1 Mbps without VoIP traffic and 2.1 Mbps with 20 VoIP users) compared to the reference scheduler (at most 388 kbps) and FHCF (with a maximum FTP throughput of 4.8 Mbps).  相似文献   

14.
基于混合预测模型的VBR流拥塞控制机制   总被引:1,自引:0,他引:1       下载免费PDF全文
李捷  吕冰  韩志杰 《计算机工程》2008,34(24):34-37
针对VBR多媒体流量的数字特征,在混合网络流量预测模型的基础上,结合小波分析和卡尔曼滤波,提出一种多媒体流自适应带宽分配算法,以合理分配网络带宽,利用双重漏桶控制网络流量。在NS网络仿真平台上进行的仿真实验表明,该算法能有效避免网络拥塞,降低网络传输时延和数据丢包率,提高带宽利用率。  相似文献   

15.
基于预测的最长队列优先调度算法   总被引:1,自引:0,他引:1       下载免费PDF全文
提出了一个基于预测的最长队列优先(PLQF)调度算法,该算法不仅考虑队列当前长度,还考虑了即将到来的流量信息,根据这一信息,资源被分配给最可能发生溢出的用户,通过预先调整队列长度以满足即将到来的流量,降低了丢包率(CLR),同时提高了缓存的利用率。理论分析表明,PLQF算法可以获得比传统LQF算法更低的CLR,仿真结果证实了PLQF算法的CLR只有传统LQF算法的10%~60%。  相似文献   

16.
Hybrid optical-wireless networks provide the inexpensive broadband bandwidth, vital for modern applications, as well as mobility, and scalability required for an access network. However, in order to provide satisfactory Quality of Service (QoS) on such a non-homogeneous network, innovative designs are required.This paper proposes a novel scheduling mechanism to significantly improve the delay guarantee, while maintaining high-level throughput, by predicting the incoming traffic to optical network units (ONU). The proposed scheduler managed to exploit the available information in hybrid optical-wireless networks, to enhance the ONU scheduler. This results in accurate prediction of incoming traffic, which leads to intelligent and traffic-aware, scheduling and dynamic bandwidth assignment (DBA).Based on the proposed architecture, two DBA algorithms are proposed and their performance is evaluated by extensive simulations. Moreover, the maximum throughput of such network is analyzed. The results show that by using the proposed algorithms, the delay bound of delay-sensitive traffic classes can be decreased by a factor of two, without any adverse effect on the throughput.  相似文献   

17.
18.
With the advent of home networking and widespread deployment of broadband connectivity to homes, a wealth of new services with real-time Quality of Service (QoS) requirements have emerged, e.g., Video on Demand (VoD), IP Telephony, which have to co-exist with traditional non-real-time services such as Web browsing and file downloading over the Transmission Control Protocol (TCP). The co-existence of such real-time and non-real-time services demands the residential gateway (RG) to employ bandwidth management algorithms to control the amount of non-real-time TCP traffic on the broadband access link from the Internet Service Provider (ISP) to the RG so that the bandwidth requirements of the real-time traffic are satisfied. In this paper we propose an algorithm to control the aggregate bandwidth of the incoming non-real-time TCP traffic at the RG so that QoS requirements of the real-time traffic can be guaranteed. The idea is to limit the maximum data rates of active TCP connections by dynamically manipulating their flow control window sizes based on the total available bandwidth for the non-real-time traffic. We show by simulation results that our algorithm limits the aggregate bandwidth of the non-real-time TCP traffic thus granting the real-time traffic the required bandwidth.  相似文献   

19.
《Computer Networks》2005,47(1):1-21
Field measurements have always been the starting point for network design and planning; however, their statistical analysis beyond simple traffic volume estimation is not so common. In this paper we present and discuss Tstat, a tool for the collection and statistical analysis of TCP/IP traffic, which, in addition to recognized performance figures, infers TCP connection status from traces. Besides briefly discussing its rationale and use, we present part of the performance figures that can be obtained, and we highlight the insight that such figures can give on TCP/IP protocols and the Internet, thereby supporting the usefulness of a widespread use of Tstat or similar tools.Analyzing Internet traffic is difficult because a large amount of performance figures can be devised in TCP/IP networks, but also because many performance figures can be derived only if both directions of bidirectional traffic are jointly considered. Tstat automatically correlates incoming and outgoing packets. Sophisticated statistics, obtained through data correlation between incoming and outgoing traffic, give reliable estimates of the network performance also from the user perspective.Tstat computes over 80 different performance statistics at both the IP and TCP layers, allowing a good insight in the network performance. To support the latter statement, we discuss several of these figures computed on traffic measurements performed for a time period equivalent to more than three months spread during the years 2000–2003 on the access link of Politecnico di Torino.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号