共查询到19条相似文献,搜索用时 125 毫秒
1.
周屹然 《电信工程技术与标准化》2004,(9):87-90
TCP友好的速率控制(TFRC)主要适用于实时数据传输的一种拥塞控制机制,具有突出的TCP友好性即在相同的环回时间(RTT)下可以和TCP流享有近乎相同的带宽,从而避免了由于UDP等传输层协议缺乏拥塞控制而带来的网络拥塞甚至崩溃.本文简要介绍了它的协议机制并通过一些仿真和试验的结果初步讨论了其性能. 相似文献
2.
本文分析了TFRC(TCP-Friendly Rate Control)协议在慢启动阶段采用类似TCP协议的倍增发送速率机制存在的问题,提出了一种利用回路响应时间(Round Trip Time,RTT)来自适应调节慢启动阶段速率的算法.通过分析实际RTT值和EWMA(Exponentially Weighted Moving Average)处理后的平均RTT值来感知网络当前的拥塞状况,以调节发送速率的激进程度.仿真实验表明,该方法对TFRC协议具有明显的改进作用,减少了慢启动阶段结束时的报文丢失率,提高了协议的传输平稳度和吞吐量,从而能更有效地适应多媒体流的传输要求. 相似文献
3.
4.
流媒体分发的一种典型实现方法是采用具有接收方驱动拥塞控制机制的分层组播.由于目前分层组播拥塞控制协议缺乏对用户行为的限制,接收方可违规订阅上层组播组发起自利型攻击,导致非公平的带宽利用.本文提出了一种较通用的安全分层组播协议SLM(Secure Layered Multicast).在路由器辅助拥塞控制条件下,在边界路由器采用基于Shamir秘密共享体制的拥塞状态相关访问控制(CR-AC,Congestion state Related Access Control)算法,管理用户组订阅行为,避免了用户自利型攻击,并使服务提供商可根据其与用户的协约限定不同用户的最高订阅级别.分析和仿真实验表明,该协议可实时保证网络流量安全共享带宽并具有较好的可扩展性. 相似文献
5.
本文针对TFRC(TCP-Friendly Rate Control)流与TCP流竞争带宽时的友好性问题,分析了影响TFRC协议TCP友好性的因素,通过对TFRC速率计算公式中丢包率的不同幂级项引入权重系数,增加网络拥塞严重时的发送速率,减少网络拥塞较轻时的发送速率,从而降低了网络拥塞程度对TFRC流传输速率的影响.仿真实验表明该方法对TFRC协议具有较明显改进作用,提高了TFRC流的传输平稳度和TCP友好性,从而能更有效地适应多媒体流的传输要求. 相似文献
6.
本文针对Internet传输协议TCP的和式增加积式减少(AIMD)拥塞控制机制不适应多媒体通信,而目前拥塞控制的研究又大多集中在尽量做好(Best-effort)服务上的问题,结合Internet上多媒体通信的特点及其对QoS的要求,提出了一种将多媒体通信服务质量(QoS)控制和基于速率拥塞控制结合起来的拥塞控制的新机制.本文详细地研究了这一机制,并提出了源端多媒体数据流的带宽控制策略、基于动态部分缓存共享(DPBS)的数据包丢失控制方案和接收端计算包丢失率p的方法.最后给出了整个拥塞控制机制的系统结构. 相似文献
7.
提出了一种新的自适应分层多播拥塞控制方案(ALM)。ALM是发送方与接收方共同驱动、由路由器辅助流量控制的拥塞控制方案,通过把发送方的动态分层和接收方的自适应速率调整有机结合,不仅增强了分层多播的适应能力,提高了系统的吞吐量,而且较好地满足了TCP友好性。仿真实验表明,ALM能有效地利用网络带宽,解决网络带宽的异构性问题,并能通过接收端计算TCP友好速率,使接收端达到与TCP流公平竞争网络资源的目的。 相似文献
8.
本文通过对传输控制协议/网际协议(TCP/IP)与面向连接传输层协议/无连接网络层协议(COTP/CLNP)中拥塞控制方法的比较分析,基于随机早期检测算法(RED)提出一种新的网络拥塞控制模型—早期随机拥塞控制模型(ERCCM),适用于所有采用绝对门限拥塞控制的网络系统.基于该模型和RED算法提出了一种适用于航空电信网(ATN)的随机早期置位方法(REM),并对该方法在ATN中的实现进行了仿真,仿真结果表明采用随机置位的方法可以解决绝对门限置位的三个主要问题,极大改善了网络的性能. 相似文献
9.
在IEEE 802.11b协议中有四种速率用于数据传输,节点可根据信道情况选择传输速率,致使802.11DCF公平的退避机制不再适用.为了让高速节点能更容易的竞争到信道以体现多速率协议的优势,提出了基于拥塞控制的速率自适应机制.竞争信道的节点根据拥塞情况来选择合适的退避窗口.通过NS2软件仿真证明该机制进一步提高了竞争窗口自适机制的性能. 相似文献
10.
11.
The Mulitplicative Increase Multiplicative Decrease (MIMD) congestion control algorithm in the form of Scalable TCP has been
proposed for high speed networks. We study fairness among sessions sharing a common bottleneck link, where one or more sessions
use the MIMD algorithm. Losses, or congestion signals, occur when the capacity is reached but could also be initiated before
that. Both synchronous as well as asynchronous losses are considered. In the asynchronous case, only one session suffers a
loss at a loss instant. Two models are then considered to determine which source looses a packet: a rate dependent model in which the packet loss probability of a session is proportional to its rate at the congestion instant, and the independent loss rate model. We first study how two MIMD sessions share the capacity in the presence of general combinations of synchronous and
asynchronous losses. We show that, in the presence of rate dependent losses, the capacity is fairly shared whereas rate independent
losses provide high unfairness. We then study inter protocol fairness: how the capacity is shared in the presence of synchronous
losses among sessions some of which use Additive Increase Multiplicative Decrease (AIMD) protocols whereas the others use
MIMD protocols. 相似文献
12.
As a prevalent reliable transport protocol in the Internet, TCP uses two key functions: AIMD (Additive Increase Multiplicative Decrease) congestion control and cumulative ACK technique to guarantee delivery. However, with these two functions, TCP becomes lowly efficient in ad hoc networks that have a much lower BDP and frequent packet losses due to various reasons, since TCP adjusts its transmission window based on packet losses. In this paper, we present that, provided that the BDP is very small, any AIMD-style congestion control is costly and hence not necessary for ad hoc networks. On the contrary, a technique to guarantee reliable transmission and to recover packet losses plays a more critical role in the design of a transport protocol over ad hoc networks. With this basis, we propose a novel and effective datagram-oriented end-to-end reliable transport protocol for ad hoc networks, which we call DTPA. The proposed scheme incorporates a fixed-size window based flow control and a cumulative bit-vector based selective ACK strategy. A mathematical model is developed to evaluate the performance of DTPA and to determine the optimum transmission window used in DTPA. The protocol is verified using GloMoSim. The simulation results show that our proposal substantially improves the network performance. 相似文献
13.
针对目前Internet中TCP拥塞控制和式增加、积式减小和窗口变化机制,分析了TCP流量控制带宽分配的公平性问题。 相似文献
14.
15.
This paper proposes an approach called PC-CORP (Power Control based Cooperative Opportunistic Routing Protocol) for WSN (Wireless Sensor Networks), providing robustness to the random variations in network connectivity while ensuring better data forwarding efficiency in an energy efficient manner. Based on the realistic radio model, we combine the region-based routing, rendezvous scheme, sleep discipline and cooperative communication together to model data forwarding by cross layer design in WSN. At the same time, a lightweight transmission power control algorithm called PC-AIMD (Power Control Additive Increase Multiplicative Decrease) is introduced to utilize the cooperation of relay nodes to improve the forwarding efficiency performance and increase the robustness of the routing protocol. In the simulation, the performance of PC-COPR is investigated in terms of the adaptation of variations in network connectivity and satisfying the QoS requirements of application. 相似文献
16.
17.
Panagiotis Papadimitriou Vassilis Tsaoussidis Chi Zhang 《Telecommunication Systems》2010,43(3-4):295-312
Video delivery in heterogeneous wired/wireless networks is challenging, since link errors commonly degrade throughput performance, smoothness, and eventually impair the playback quality. We present an end-to-end Loss Differentiation Mechanism (LDA) which effectively decouples congestion from wireless loss in order to abolish the damage of error-induced multiplicative decrease on flow throughput and smoothness. The proposed LDA relies on Round Trip Time measurements to estimate the queuing delay and determine the appropriate error-recovery strategy. This mechanism can be easily adapted and incorporated into existing Additive Increase Multiplicative Decrease (AIMD) protocols, enabling them to utilize the available resources more efficiently. In this context, we incorporate the LDA into AIMD-based Scalable Streaming Video Protocol (SSVP), an end-to-end TCP-friendly protocol optimized for video streaming applications. Based on simulation results, we show that the combined approach provides the desired functionality to bind operationally wired and wireless links, within the framework of bandwidth efficiency, smoothness, and fairness. 相似文献
18.
基于显式速率的TCP友好的UDP拥塞控制策略 总被引:2,自引:0,他引:2
本文提出了一种基于显式速率的UDP拥塞控制策略:通过源端和网络中的路由器相互配合,使得实时UDP应用能够根据网络的反馈以瓶颈链路的公平带宽为速率发送数据。此种控制策略对TCP应用是友好的,并且提高了网络的吞吐量和利用率。仿真结果表明:基于显式速率的UDP拥塞控制策略与采用TFRC(TCP—Friendly Rate Control)的UDP拥塞控制策略相比,在吞吐量、TCP友好性等方面性能有较大提高。 相似文献
19.
In this paper, we explore end-to-end loss differentiation algorithms (LDAs) for use with congestion-sensitive video transport protocols for networks with either backbone or last-hop wireless links. As our basic video transport protocol, we use UDP in conjunction with a congestion control mechanism extended with an LDA. For congestion control, we use the TCP-Friendly Rate Control (TFRC) algorithm. We extend TFRC to use an LDA when a connection uses at least one wireless link in the path between the sender and receiver. We then evaluate various LDAs under different wireless network topologies, competing traffic, and fairness scenarios to determine their effectiveness. In addition to evaluating LDAs derived from previous work, we also propose and evaluate a new LDA, ZigZag, and a hybrid LDA, ZBS, that selects among base LDAs depending upon observed network conditions. We evaluate these LDAs via simulation, and find that no single base algorithm performs well across all topologies and competition. However, the hybrid algorithm performs well across topologies and competition, and in some cases exceeds the performance of the best base LDA for a given scenario. All of the LDAs are reasonably fair when competing with TCP, and their fairness among flows using the same LDA depends on the network topology. In general, ZigZag and the hybrid algorithm are the fairest among all LDAs. 相似文献