无线移动自组网络中的动态带宽分配

在已有的带宽分配算法的基础上,引入加权准则对竞争的数据流进行带宽分配,该算法工作紧密结合无限局域网的MAC层协议DCF,由此保证带宽分配的公平性和每条流的最低带宽需求。使用NS仿真进行性能评价,实验表明,该算法在满足数据流的最低带宽需求的同时,提高了系统吞吐量。该文提出的算法尤其适合单跳Ad hoc多媒体传输。     

一种适用于宽带无线多媒体网络的上行带宽分配方案

提出了一种适用于宽带无线多媒体网络的上行无线带宽分配方案。该方案将业务数据分为3种类型，即实时恒定速率业务、恒定变速率业务、非实时业务，针对不同业务对时延和带宽的不同需求，采取不同的方法获取上行带宽，较好地解决了多业务并发时的上行带宽分配问题，较传统技术提高了带宽利用率，减少了协议开销和传输时延。在详细描述算法的基础上，建立了对应的仿真系统对算法进行了验证。     

弹性光数据中心网络中收益最大化的带宽分配算法

弹性光数据中心网络中的带宽分配需要兼顾云服务提供商收益和用户连接请求性能,对此提出收益最大化的带宽分配算法,其以子载波为基本单位将光纤带宽有效地分配给多个用户连接请求。首先,基于收益模型和虚拟子载波的概念建立带宽分配问题的整数线性规划模型;接着提出一种基于动态规划的带宽分配算法以及一种启发式的带宽分配算法,前者致力于获得最大的分配收益,后者则力求获得更好的时间效率;最后,通过仿真实验对所设计的带宽算法的性能进行验证。实验结果表明,相较于已有的弹性光数据中心网络中的带宽分配算法,设计的两种算法均能在带宽分配中获得更高的系统收益。     

基于用户带宽的网络流量仿真的研究

ON/OFF模型虽然可以生成具有自相似和长相关特性的网络流量,但是不能够模拟用户带宽变化对网络流量的影响。因此,以ON/OFF模型为理论依据,提出一个新的网络流量仿真模型。该仿真模型以用户数据传输请求作为数据源,以用户网络带宽决定用户传输速度,并且可以根据网络流量动态的调整用户带宽。实验结果表明,该网络流量仿真模型能够较好地反映真实的网络流量,并且通过调整用户的数据传输请求和动态地分配用户的网络带宽,有助于模拟用户带宽变化对网络流量的影响,能够为用户的网络带宽服务提供预测手段和管理依据。     

基于自相似流量预测的TCP拥塞控制算法

针对高带宽网络环境下传统TCP Reno的拥塞控制效率低的问题,提出了一种适用于随机丢失网络的TCP拥塞控制改进算法.介绍并分析了网络流量自相似特性和预测的时间尺度,并进行了TCP链路流量预测及可用带宽估计,当网络出现丢包时根据估计的带宽动态设置慢启动阈值.OPNET仿真结果表明,该算法在高随机丢包的情况下吞吐量得到了明显改善.     

IEEE 802.16中支持QoS的有效带宽分配机制

基于IEEE 802.16协议,研究宽带无线接入网中保障QoS的有效带宽资源分配和调度问题。首先,在PMP模式下设计一个有效率的QoS调度算法,利用参数的调整提供更具有弹性的服务质量,以利于rtPS服务支持多媒体传输;然后利用标准中所提供的QoS参数调度各种不同类型的服务业务,分配上传带宽,进而达到有效地使用网络资源。仿真实验结果表明,本方案能够在保证QoS需求的同时,有效地分配带宽资源。     

主动网络中基于多代理系统的流量均衡*

主动网络流量均衡控制ATEC是一种在主动网络环境中,基于多代理MA系统的网络性能控制机制。该方法将多路径路由和资源分配相结合,利用非线性规划启发式算法——多路径等性能策略,实现网络流量和带宽资源的均衡配置,从而避免或减少网络拥塞的发生,达到提高网络性能的目的。着重介绍了ATEC的多代理MA系统实现,包括基本算法、一般模型、代理设计和合作模型的设计,并给出了仿真结果。     

基于IPv6分段路由的高校网络流量调度算法

高校网络流量调度算法的数据包转发吞吐率较低,研究基于互联网协议第6版(Internet Protocol version 6,IPv6)分段路由的高校网络流量调度算法。采集高校网络数据,通过网关将数据封装成IPv6数据报文,再转发至交换机与控制器建立通信,制定数据包转发规则;设定添加传输控制协议(Transmission Control Protocol,TCP)的和式增加积式减少(Additive Increase Multiplicative Decrease,AIMD)机制,收敛网络流量,均匀分配带宽的平衡状态,调整网卡分配宽带,进行流量预估;判断链路的网络流量,求解最优路径,实现网络流量调度。实验结果表明,运用设计方法处理转发的吞吐率较高,有效提高高校网络的服务质量。     

采用分级策略和控制消息的一种动态带宽分配

通过对以太无源光网络接入技术和现有各种带宽分配算法存在不足的分析,基于数据服务优先级划分和ONU队列管理机制,提出了一种新的动态带宽分配算法。它基于服务分级策略和控制消息格式来处理一个EPONs多点控制协议中的不同优先级带宽。仿真表明,提出的动态带宽分配算法不仅有较高的链接效率和带宽利用率,而且在资源分配方面效率更高。     

多媒体服务中间一公里资源优化

重点关注如何实现中间一公里处的多媒体有效分发.为此,文章首先利用博弈论分析了多媒体分发网络的内容分发与底层基础网络流量间的相互影响关系,提出一种中间一公里资源优化分配策略.在此基础上,文章提出一种新的动态资源分配算法并利用Matlab实验验证该算法的有效性.实验结果表明,与传统的冗余路由策略相比,动态资源分配算法能够将资源均匀有效的分配到整个网络中去,不仅能够优化多媒体分发网络中间一公里传输效率,还能优化底层基础网络资源分配.     

ATM congestion control using Minimal Resource Allocation Networks (MRAN)

This paper presents a congestion control scheme for ATM traffic using a minimal radial basis function neural network referred to as Minimal Resource Allocation Network (MRAN). Earlier studies have shown that MRAN is well suited for online adaptive control of nonlinear time varying systems as it can adjust its size by adding and pruning the hidden neurons based on the input data. Since ATM traffic is nonlinear and time varying performance of MRAN as a congestion controller is investigated here. These studies are carried out using OPNET to model the ATM traffic. The ATM traffic model consists of bursty, Variable Bit-Rate (VBR) and custom traffic in a multiplexed form so as to generate a heavily congested traffic situation. For this scenario, the controller has to minimize the congestion episodes and maintain the Quality of Service (QoS) requirements. This paper compares the performance of the MRAN congestion controller with that of a modified Explicit Rate Indication with Congestion Avoidance (ERICA) scheme and a Back-Propagation (BP) neural controller. Simulation results indicate that MRAN controller performs better than the modified ERICA and BP controller in reducing the congestion episodes and maintaining the desirable QoS.     

Congestion control based dynamic routing in ATM networks

In this paper we describe briefly a dynamic multi-path algorithm that has been considered for connection oriented asynchronous transfer mode (ATM) networks. Our scheme takes advantage of a cell multiplexing capability that has particular advantage in networks supporting variable bit rate (VBR) traffic. The fundamental objective of the scheme is to propose a congestion control based scheme that bridges the gap between routing and congestion control as the network becomes congested. The proposed routing scheme works as a shortest path first algorithm under light traffic conditions. However, as the shortest path becomes congested under unbalanced heavy traffic, the source uses multiple paths when and if available to distribute the calls and reduce cell loss. This mechanism will provide good Quality of Service for clients within the given constraints. We compare the performance of the proposed scheme with other competitive schemes. The throughput and cell loss performance are compared via simulations. These have been carried out concentrating on a five node network, each with varying traffic patterns, with the intention of gaining insight into the strengths and weaknesses of the various schemes.     

VBR MPEG视频源流量的智能集成预测模型

由于VBR视频流量的预测能力是直接关系缓冲区设计、动态带宽分配及拥塞控制等提高网络服务质量的关键因素,因此,以多媒体主要应用形式VBRMPEG视频源为研究对象,提出了一种基于模糊神经网络的视频流量智能预测模型。通过设计模糊预测器减少输出比特流的预测误差,采用神经网络减少多步预测的计算量。仿真试验表明,与标准AR模型预测结果相比,该模型显著提高了预测的准确度和可靠性,且易于推广使用。     

Packet video transport in ATM networks with single-bit feedback

The promise of a broadband integrated service digital network has led to the design of mechanisms for efficient transport of real-time compressed video in packet switching networks. We examine feedback control for video transport in ATM networks where the available feedback is a single bit of information carried in the cell header. We investigate the performance of three single-bit schemes for source rate adaptation. Two were originally for congestion control of bursty data traffic and are modified to control video traffic. The third scheme conveys more information about the state of queue(s) at the bottleneck. The simulation results show that all three schemes for feedback control of VBR video streams work remarkably well. During severe network congestion, the signal quality degrades gracefully, but not uniformly across all connections. Based on insights from the initial simulations, we propose a scheme to improve the fairness of service and demonstrate its effectiveness.     

Urban traffic congestion propagation and bottleneck identification

Bottlenecks in urban traffic network are sticking points in restricting network collectivity traffic efficiency. To identify network bottlenecks effectively is a foundational work for improving network traffic condition and preventing traffic congestion. In this paper, a congestion propagation model of urban network traffic is proposed based on the cell transmission model （CTM）. The proposed model includes a link model, which describes flow propagation on links, and a node model, which represents link-to-link flow propagation. A new method of estimating average journey velocity （AJV） of both link and network is developed to identify network congestion bottlenecks. A numerical example is studied in Sioux Falls urban traffic network. The proposed model is employed in simulating network traffic propagation and congestion bottleneck identification under different traffic demands. The simulation results show that continual increase of traffic demand is an immediate factor in network congestion bottleneck emergence and increase as well as reducing network collectivity capability. Whether a particular link will become a bottleneck is mainly determined by its position in network, its traffic flow （attributed to different OD pairs） component, and network traffic demand.     

基于Additive2multipl icative 模糊 神经网的ATM 网络拥塞控制

考虑了模糊神经网络的学习功能，提出利用Additive-multiplicative模糊神经网络(AMFNN)对ATM网络进行拥塞控制的方案．在拥塞控制过程中，利用AMFNN模糊神经网络预测下一个将要到达流的特征，结合当前缓冲区的队列信息预测网络是否发生拥塞．一旦预测出将有拥塞发生，控制器则向源端反馈拥塞控制信息，信源根据拥塞信息适当降低传输速率，从而避免了拥塞的发生．仿真结果表明，该方法可改善网络对拥塞的实时处理能力，提高网络资源的利用率．     

Connection admission control of ATM network using integrated MLP and fuzzy controllers

This paper presents a new approach to the problem of call admission control (CAC) of variable bit rate (VBR) traffic in an asynchronous transfer mode (ATM) network. Our approach employs an integrated neural network and fuzzy controller to implement the CAC controller. This scheme capitalizes on the learning ability of a neural network and the robustness of a fuzzy controller. Experiments show that this scheme is able to achieve high throughput and low cell loss while achieving fairness among different classes of VBR traffic. For comparison, we have also implemented four other CAC schemes: (1) peak bandwidth method, (2) equivalent bandwidth method, (3) average bandwidth method and (4) neural network quality of service (QoS) predictor. Results of these experiments are presented in this paper.     

Real-time applications in a CRMA network: a performance analysis

This paper analyses bandwidth allocation schemes for managing real-time applications (Variable Bit Rate video and voice) in a CRMA network. A methodology to compute the Quality of Service (QoS) experienced by variable bit rate (VBR) video and voice sources is proposed. As VBR video applications only tolerate extremely low packet loss rates (< 10⁻⁸), we need a computational approach to estimate very low tail probabilities. Studying the QoS with a simulation technique is not feasible, because computational costs make it almost impossible to estimate tail distribution probabilities lower than 10⁻²−10⁻³. Therefore, to achieve this target, we propose a model which represents a CRMA network's worst case behaviour (i.e. a scenario with maximum network congestion), and which can be solved analytically. By solving this model for different bandwidth allocation schemes, we can obtain the corresponding bounds on the QoS experienced by VBR video users. Finally, for those bandwidth allocation schemes which provide an acceptable QoS for VBR video traffic, we also estimate (via a trace-driven simulation) the QoS achieved by voice users.     

一种基于IEEE 802.11e的多跳无线网络拥塞控制协议

多跳无线网络中网络拥塞的出现将严重降低网络的性能。基于802.11e提供的区分业务类型的信道接入优先级机制,提出了一种对尽力而为(best-effort)类型业务动态调整其优先级进行网络拥塞控制的协议。该算法的主要思想是对发生网络拥塞的节点提升其业务流传输的优先级使其获得更多的传输机会以缓解拥塞状况,并对严重的网络拥塞状况采取反向施压的策略降低上游节点业务流的转发速率。仿真结果表明,该算法有效地提高了网络重负载情况下的吞吐量。