A rate-based flow control mechanism for avoiding congestion

The rate-based flow control mechanisms for the Available Bit Rate(ABR)service are used to share the available badwidth of a bottleneck switch connected to a bottleneck link fairly and reasonably among many competitive users,and to maintain the buffer queue length of the witch at a desired level in order to avoid congestion in Asynchronous Transfer Mode(ATM)networks.In this Paper,a control theoretic approach that uses a Deadbeat-Response(DR) controller to the desing of a rate-based flow control mechanism is presented.The mehanism has a simple structure and is robust in the sense that its stability is not sensitive to the change of the number of active Virtual Connections(VCs),Simulation results show that this mechanism not only ensures fair share of the bandwidth for all active VCs regardless of the nmuber of hops they traverse but also has the advantages of fast convergence ,no oscillation,and high link bandwidth utilization.     

Convergence, stability and robustness analysis of the OFEX controller for high-speed networks

The OFEX (Optimal and Fully EXplicit) rate controller is able to provide not only the optimal bandwidth allocation but also the fully explicit congestion signal to sources. It exercises link-wise proportional fairness and network-wise max-min fairness, which enables the controller to feed the congestion signal back from the most congested link, instead of using the networkwise proportional fairness which feeds back the congestion signal summed along a flow path. As a result, the OFEX controller overcomes the drawbacks of the relatively explicit controllers that 1) bias the multi-bottlenecked users in terms of their source sending rate and convergence speed, 2) are not adaptable to varying link bandwidth and 3) can potentially incur large queue size upon congestion. In this paper, we first prove that the OFEX controller can converge to its equilibrium at least as fast as a geometric series in a link. Then we analyze the system stability with time delay in a single bottleneck network and show that the OFEX controller can achieve local stability under certain conditions. Besides, the robustness analysis of the OFEX controller shows how the dynamics of link bandwidth may affect the revenue of a link. Finally, with the OPNET modeler, we evaluate the performances of the OFEX controller and verify its effectiveness.     

Binary ABR flow control over ATM networks with uncertainty using discrete-time variable structure controller

A binary available bit rate （ABR） scheme based on discrete-time variable structure control （DVSC） theory is proposed to solve the problem of asynchronous transfer mode （ATM） networks congestion in this paper. A discrete-time system model with uncertainty is introduced to depict the time-varying ATM networks. Based on the system model, an asymptotically stable sliding surface is designed by linear matrix inequality （LMI）. In addition, a novel discrete-time reaching law that can obviously reduce chatter is also put forward. The proposed discrete-time variable structure controller can effectively constrain the oscillation of allowed cell rate （ACR） and the queue length in a router. Moreover, the controller is self-adaptive against the uncertainty in the system. Simulations are done in different scenarios. The results demonstrate that the controller has better stability and robustness than the traditional binary flow controller, so it is good for adequately exerting the simplicity of binary flow control mechanisms.     

Fuzzy-Based Dynamic Distributed Queue Scheduling for Packet Switched Networks

Addressing the problem of queue scheduling for the packet-switched system is a vital aspect of congestion control. In this paper, the fuzzy logic based decision method is adopted for queue scheduling in order to enforce some level of control for traffic of different quality of service requirements using predetermined values. The fuzzy scheduler proposed in this paper takes into account the dynamic nature of the Internet traffic with respect to its time-varying packet arrival process that affects the network states and performance. Three queues are defined, viz low, medium and high priority queues. The choice of prioritizing packets influences how queues are served. The fuzzy scheduler not only utilizes queue priority in the queue scheduling scheme, but also considers packet drop susceptibility and queue limit. Through simulation it is shown that the fuzzy scheduler is more appropriate for the dynamic nature of Internet traffic in a packet-switched system as compared with some existing queue scheduling methods. Results show that the scheduling strategy of the proposed fuzzy scheduler reduces packet drop, provides good link utilization and minimizes queue delay as compared with the priority queuing (PQ), first-in-first-out (FIFO), and weighted fair queuing (WFQ).     

基于ECN的单播流与多播流间带宽共享算法

An ECN-based implementing bandwidth-sharing algorithm for unicast and multicast flows is presented.The algorithm uses a bandwidth allocation strategy to give an incentive to multicast flows in bandwidth allocation according to algorithm of the number of receivers, and to assure the unicast flows get their bandwidth shares fairly.Provided best-effort networks, an ECN-based congestion control algorithm is used to implement differentiated service in bandwidth allocation between unicast flows and multicast flows. In implementation, we solve the problems such asreceiver‘s number estimation, the RTT estimation and compromise between convergence and stability.The simulation results show that the algorithm can implement bandwidth sharing for TCP flows and multicast flows. Atthe same time, the algorithm not only allocates more bandwidth to multicast flows, but promises TCP flows to get their fair bandwidth share.     

FastQueue：一种高性能的磁盘队列存储管理机制

High reliability is the primary requirement for messaging system. Messaging system always utilizes disk queue to temporarily store message to be delivered. Experiments show that Disk queue I/O is the primary performance bottleneck in the messaging system. In this paper we present a high performance disk queue storage management mechanism-FastQueue. The FastQueue utilizes a large file to serve as disk queue to reduce file manage overhead, in which adjacent messages are stored in adjacent disk block. Several messages are written to disk queue in a one large write by Lazy Gathering Write. Several adjacent messages are read into buffer in a one read by Sequential Grouping Prcfetch. The Lazy Gathering Write and Sequential Grouping Prefetch policies take full advantage of the disk bandwidth. Experiment shows that performance of the FastQueue is more than an order of magnitude higher than that of traditional disk queue.     

Provisioning QoS guarantee by multipath routing and reservation in Ad hoc networks

In this paper, a QoS multipath source routing protocol (QoS-MSR) is proposed for ad hoc networks. It can collect QoS information through route discovery mechanism of multipath source routing (MSR) and establish QoS route with reserved bandwidth. In order to reserve bandwidth efficiently, a bandwidth reservation approach called the multipath bandwidth splitting reservation (MBSR) is presented, under which the overall bandwidth request is split into several smaller bandwidth requests among multiple paths. In simulations, the anthors introduce Insignia, an in-bind signaling system that supports QoS in ad hoc networks, and extend it to multipath Insignia (M-Insignia) with QoS-MSR and MBSR. The results show that QoS-MSR routing protocol with the MBSR algorithm can improve the call admission ratio of QoS traffic, the packet delivery ratio, and the end-to-end delay of both best-effort traffic and QoS traffic. Therefore, QoS-MSR with MBSR is an efficient mechanism that supports QoS for ad hoc networks.     

A new fast friendly window-based congestion control for real-time streaming media transmission

1 Introduction In the current Internet, not all applications use TCP and they do not follow the same concept of fairly sharing the available bandwidth. The rapid growing of real-time streaming media applications will bring much UDP traffic without integrating TCP compatible congestion control mechanism into Internet. It threats the quality of service (QoS) of real-time applications and the stability of the current Internet. For this reason, it is desirable to define appropriate rate rule…     

Blind estimation of multipath delays in OFDM systems

In order to coherently detect the transmitted data symbols,an orthogonal frequency division multi-plexing (OFDM) receiver requires reliable identification and equalization of the experienced wireless multipath fading channels.The information of path delays plays an important role in the procedure of identification and equalization.The need for high data rates motivated the search for blind identification and equalization methods because they save bandwidth by avoiding the use of training sequences.In OFDM systems,multipath fading channels introduce interference between adjacent symbols which can be prevented by inserting a cyclic prefix (CP) before each symbol.In this paper,we find that the power of the interference in the CP interval can be estimated by using the circular convolution and based on the variations of the interference power,the time delay of each path can be estimated blindly.     

A multi-step standard-cell placement algorithm of optimizing timing and congestion behavior

The timing behavior and congestion behavior are two important goals in the performance-driven standard-cell placement. In this paper, we analyze the relationship between the timing and congestion behavior. We bring up a multi-step placement algorithm to reach the two goals. First, the timing-driven placement algorithm is used to find the global optimal solution. In the second step, the algorithm tries to decrease the maximum congestion while not deteriorating the timing behavior. We have implemented our algorithm and tested it with real circuits. The results show that the maximum delay can decrease by 30% in our timing-driven placement and in the second step the maximum congestion will decrease by 10% while the timing behavior is unchanged.     

基于ATM单瓶颈节点模型的PID拥塞控制器设计

针对ATM单瓶颈节点网络模型，提出ABR业务拥塞控制方案，给出使系统闭环稳定PID参数应满足的约束条件。设置前馈环节以抑制带宽波动对缓冲区队列长度的影响。仿真结果表明，业务服务质量得到了保证，系统具有较好的动态性能。     

A neural-fuzzy system for congestion control in ATM networks

We propose the use of a neural-fuzzy scheme for rate-based feedback congestion control in asynchronous transfer mode (ATM) networks. Available bit rate (ABR) traffic is not guaranteed quality of service (QoS) in the setup connection, and it can dynamically share the available bandwidth. Therefore, congestion can be controlled by regulating the source rate, to a certain degree, according to the current traffic flow. Traditional methods perform congestion control by monitoring the queue length. The source rate is decreased by a fixed rate when the queue length is greater than a prespecified threshold. However, it is difficult to get a suitable rate according to the degree of traffic congestion. We employ a neural-fuzzy mechanism to control the source rate. Through learning, membership values can be generated and cell loss can be predicted from the status of the queue length. Then, an explicit rate is calculated and the source rate is controlled appropriately. Simulation results have shown that our method is effective compared with traditional methods.     

A novel self-tuning feedback controller for active queue management supporting TCP flows

Wireless access points act as bridges between wireless and wired networks. Since the actually available bandwidth in wireless networks is much smaller than that in wired networks, there is a bandwidth disparity in channel capacity which makes the access point a significant network congestion point. The recently proposed active queue management (AQM) is an effective method used in wired network and wired-wireless network routers for congestion control, and to achieve a tradeoff between channel 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. In this paper, we propose a Novel autonomous Proportional and Differential RED algorithm, called NPD-RED, as an extension of RED. NPD-RED is based on a self-tuning feedback proportional and differential controller, which not only considers the instantaneous queue length at the current time point, but also takes into consideration the ratio of the current differential error signal to the buffer size. Furthermore, we give theoretical analysis of the system stability and give guidelines for the selection of feedback gains for the TCP/RED system to stabilize the instantaneous queue length at a desirable level. Extensive simulations have been conducted with ns2. The simulation results have demonstrated that the proposed NPD-RED algorithm outperforms the existing AQM schemes in terms of average queue length, average throughput, and stability.     

改进的基于带宽估计的Ad Hoc网拥塞控制策略研究

为解决Ad Hoc网络中路由协议在通信过程中存在拥塞问题,提出了一种基于带宽估计的拥塞控制策略.该策略通过结合一阶低通数字滤波算法和算数平均值滤波算法,有效提高可用带宽估计的精确度;采用主动队列管理算法实施拥塞控制,实现对包的选择性丢弃策略,达到了较优的控制效果.实验结果表明,该算法在各项重要指标上都有较好性能.     

一种提高稳定性和公平性的主动队列管理机制

结合平均队列和负载衡量拥塞,实现选择性丢包,提出早期选择性丢包算法(ESD)．ESD采用指数函数计算丢包概率,使丢包概率随拥塞程度增大而指数递增;引入记录活跃连接状态信息的虚队列,并在虚队列上假轮转,以检测发送速率大的连接;区分非响应性连接和响应性连接,挑选丢包的候选连接,拥塞时优先丢弃候选连接在队列头部的数据包．实验结果表明,ESD可提高队列稳定性,降低Web流和RTT较大连接的丢包率,提高连接占用带宽的公平性,缩短应用响应时间．     

Distributed bandwidth allocation based on alternating evolution algorithm

In a network, end nodes have to compete for bandwidth through some distributed congestion control algorithms. It is a great challenge to ensure the efficiency and fairness of the distributed control algorithms. TCP congestion control algorithms do not perform well in terms of their efficiency and fairness in high speed networks. In this paper, we propose a novel asymptotic evolution algorithm based on the Logistic Model to allocate limited bandwidth resource. The algorithm introduces an explicit bandwidth pre-allocation factor. The factor is carried by the packet and is computed in routers based on the information of the router capacity, the aggregate load, and the instantaneous queue length; therefore the algorithm does not require the routers to keep the per-flow state. According to this pre-allocation bandwidth factor, the senders asymptotically adjust their sending rate and the bandwidth factor changes asymptotically along with the variation of the aggregate load and the queue length in the routers; therefore the sending rate and the pre-allocation bandwidth factor form alternating evolution and eventually reach a steady state.     

调度和拥塞控制相结合的无线网络资源分配模型

研究了基于WLAN访问Internet的网络基站处流,提出了一种基于队列长度的调度方法和基于信道容量的拥塞控制模式,以达到网络资源的公平分配,并解决由于不恰当处理基站处堆积数据包而引起的弊端。在提出的资源分配模型中,调度算法根据各条流堆积的队列长度来随机地选择将要发送的数据分组;而拥塞控制模式中,将链路使用率作为拥塞指示,通过计算,平等地反馈给每一条流的发送端。发送端根据反馈到的拥塞信息来调整发送速率,以达到资源分配的公平性。仿真的结果表明：各条流能公平地共享无线网络的带宽。此算法的最大的优点在于基站不需要按照某种特定的公平性定义来选择数据包却能达到很高的公平性。     

一种新的拥塞避免算法——SECN

RED算法与DECbit机制是具有代表性的两种拥塞控制算法,其共同的问题是在计算平均队列长度困难。提出一种新的基于中间节点的拥塞避免机制SECN,它通过输入队列长度和吞吐量在早期检测到拥塞,不需要计算平均队列长度。之后,选择占用资源最多的连接进行通告,让发送端缩小发送窗口。SECN算法容易实现,具有较好的公平性,不会发生许多连接同时缩小发送窗口导致吞吐量下降的全局同步现象。仿真结果也证明具有较高的吞吐量与小的响应时间。     

Improving the efficiency and fairness of eXplicit Control Protocol in multi-bottleneck networks

The Transmission Control Protocol (TCP) has been extensively credited for the stability of the Internet. However, as the product of bandwidth and latency increases, TCP becomes inefficient and prone to instability. The eXplicit Control Protocol (XCP) is a novel and promising congestion control protocol that outperforms TCP in terms of efficiency, fairness, convergence speed, persistent queue length and packet loss rate. However, the XCP equilibrium solves a constrained max–min fairness problem instead of a standard max–min fairness problem. The additional constraint under XCP leads to inefficiency and unfairness for the topologies that have multiple bottleneck links.In this paper, according to classical control theory, we propose an XCP bandwidth compensation algorithm on basis of the proportional integral controller (PI-XCP), which reconfigures the available bandwidth variable from the fixed hardware determined physical link capacity value to a configuration value that can be dynamically changed. Through a reasonable online compensation, PI-XCP gets efficient and fair bandwidth allocation in a multi-bottleneck network. Extensive simulations have shown that PI-XCP indeed achieves this goal. Simulations also have shown that PI-XCP preserves good properties of XCP, including fast convergence, negligible queue length and zero packet loss rate. Compared with iXCP, an enhancement to address the XCP equilibrium problem, PI-XCP decreases the computational complexity significantly, and achieves more effective control in highly dynamic situations, especially in the presence of short-lived flows.     

一种ATM网络拥塞控制算法的仿真研究

该文讨论了一种基于随机控制理论的ATM网络拥塞控制算法,将该算法应用于带宽变化状态下ABR的拥塞控制问题研究。仿真结果表明：对于带宽变化的情况,该算法对交换机处排队长度有很好的控制效果,并且有很高的带宽资源利用率,同时能在各VCS间实现速率的公平分享。同时将该算法和ATM论坛的ERICA 算法进行了仿真和比较,仿真结果证明：采用该算法使得交换机队列长度、源速率、交换机输出能力波动平缓。该算法在控制队列长度及震荡、提高带宽的利用率以及实现速率公平性原则方面优于ERICA 算法。