光突发交换网中流量特性分析与汇聚机制研究

文章对光突发交换(OBS)网络中的IP流量特性以及汇聚机制进行了深入的研究,通过引入ON／OFF源模型来模拟OBS网络中数据业务的自相似特性,通过对仿真进行分析,验证了ON／OFF理论模型的正确性,最后,利用合成的可控Hurst参数流量源,对几种典型的OBS汇聚算法进行了仿真分析,结果表明,这些汇聚算法对严格自相似性流量的长相关性并没有抑制效果,只是在短时间内对流量具有平滑作用．     

重尾ON/OFF源模型生成自相似业务流研究

因为传统模型没有考虑网络业务流量各种时间尺度都具有突发性,因此是不完善的,一系列的测量结果表明,网络业务流量显示自相似性,重尾分布ON／OFF模型能比较好地解释自相似业务流的产生原因,可以把LAN上的业务分解为多个活动（active)主机对之间的业务流,本文通过系统的仿真实验研究了重尾ON／OFF源模型生成自相似流的机理,并与理论结果进行了对比,而且补充了理论结果。     

面向大规模网络的聚集TCP流量模拟方法研究

为平衡大规模网络骨干网上TCP流量模拟的准确性和复杂度,提出模拟接入网出口处的TCP聚集流量,而不从单台主机或会话的层面进行流量模拟。从网络流量的自相似性出发,提出基于应用层和网络传输层自相似的TCP聚集流量模型:在应用层通过聚集多个服从Pareto分布的ON/OFF源模拟生成自相似流量,在网络传输层根据TCP机制实现对应用层流量的聚集传输控制。模拟结果显示,在流量负载比例、流量自相似性以及骨干节点丢包率等方面,模拟结果与采集自某互联网交换中心的实际数据吻合良好,表明了该模型的有效性。     

分析重尾ON/OFF源功率谱密度的TAM近似法

经过十年的研究，发现电信网络业务流量显示自相似和长相关性。传统模型不能很好的仿真网络特性，而重尾分布的ON／OFF模型能够很好地解释计算机网络业务流量的自相似性的形成机理，它的功率谱密度(PSD)成为判断其突发性的有效手段。本文在Laevens K的基础上，结合Harris CM提出的TAM方法，提出一种计算重尾ON／OFF源的PSD的TAM近似法，并通过MATLAB仿真得到PSD曲线，符合其长相关特性，证明了该方法的有效性。     

自相似网络通信量模型研究综述

越来越多的研究表明网络通信量不是Markov过程,而是在任意时间尺度上都具有突发特性,即自相似特性。描述网络通信量的数学模型主要有自相似和长相关结构。网络的某些参数服从重尾分布,从而导致网络通信量时间尺度上的突发特性。该文分析了传统网络通信量模型和性能分析的弊端,描述了新型网络通信量模型应该具有的基本特征。本文重点研究了网络自相似通信量相关的ON/OFF模型、用户访问概率模型和网络流量闭环模型,讨论了相关的研究方向,并总结了在研究网络通信量模型的过程中应该注意的原则和问题。     

异步光分组边缘节点组装机制的性能研究

针对光异步分组交换网络边缘节点的流量汇聚过程提出一种新型的流量汇聚整形算法,概算法突破基于组装门限的传统算法无法平滑自相似业务流量的局限性,引入延迟因子D来有效平滑自相似流量,取得了较好的效果.     

业务自相似性对光突发交换调度算法影响分析

使用泊松业务流模型对光突发交换网络进行性能分析不能准确地反映网络状态。该文从理论上对突发包长度进行了推导,对基于时间门限汇聚机制下突发包数据流自相似程度进行了计算机仿真测量,并利用自相似业务流模型对光突发交换网络中比较常用的LAUC和LAUC-VF调度算法进行了性能仿真。仿真结果表明:基于时间门限的汇聚机制能够有效地降低数据流自相似程度,数据流的自相似特性对LAUC算法的影响并不非常明显,但对LAUC-VF算法的性能则产生了比较严重的影响,其突发包丢失率较泊松流平均增加了近3个百分点。     

输入排队Crossbar架构下的流量模型

 本文基于IP包在路由器各端口到达流量的统计特性,建立了输入排队Crossbar架构下的流量模型,对IP包流量的平均到达速率、突发性和均衡性等流量特征进行了分类定义,给出了各自的充要条件.文中所讨论的突发度B和不均衡度U为到达流量提供了精细的计算粒度,从而为基于IQ-VOQ的调度算法性能评估提供了理论依据.与LAN的自相似模型、WAN的Poisson模型以及数据业务的ON/OFF模型相比,本文讨论的流量模型更适用于基于IQ-VOQ调度算法性能的精确评估,为路由器交换架构的工程设计提供了理论依据.     

自相似网络几种不同模型的比较和分析

随着网络业务的多样化,多媒体数据流已成为网络数据流的主体,网络业务与早期相比有了很大变化,传统的网络理论已不适应当前的网络分析,因而提出了自相似网络建模的理论。目前已有多种方法应用于自相似网络建模中。文中着重介绍了2种类型4种建模方法,即开/关(ON/OFF)模型、分形布朗运动(FBM)模型、分形自回归滑动平均过程(FARIMA)模型和α稳定模型,并比较了它们的优缺点及其应用范围。     

基于大偏差技术的自相似流CAC算法

文章采用大偏差方法，对渐近自相似流进行了分析，提出了具有重尾分布间隔的ON—OFF流的呼叫准入控制(CAC)算法，并进行了仿真分析。     

ATM网络中的ABR业务在不同ONOFF业务背景下的性能研究

本文比较研究了ＡＴＭ网络中的三种不同分布的ＯＮＯＦＦ源对ＡＢＲ业务性能的影响;周期性的ＯＮＯＦＦ源,长度为指数分布的ＯＮＯＦＦ源以及长度为Ｐａｒｅｔｏ分布的ＯＮＯＦＦ源．发现Ｐａｒｅｔｏ分布的ＯＮＯＦＦ源对ＡＢＲ业务的性能影响最大,此时需要更大的缓存器存放在ＶＢＲ业务的ＯＮ期间累积的ＡＢＲ信元．为了改善性能,我们对ＰａｒｅｔｏＯＮＯＦＦ源进行了平滑处理,还在理论上对所得实验结果作了解释．     

Traffic Capacity of UMTS System in Reverse Link

UMTS can be connected to data networks. So Internet traffic services such as WWW browsing, email, ftp, SMTP, etc should be handled by UMTS. Each of the traffic services has some specific properties but all of them obey a basic ON/OFF model. For a traffic service there is some unused (OFF) times between their transmitted packets which we may use them for other services to increase the traffic capacity of the network. In this paper we propose a new method on the Internet traffic evaluation in an interference limited UMTS-WCDMA system. In this method first we calculate ON and OFF time durations of the above traffic services based on the model presented in 3GPP then their activity factors. Secondly we introduce new capacity curves such as The Number of Web browsing users/Email users/ftp users/Telnet users and Fax users versus voice users. These are applicable in traffic planning for wireless systems.     

Self-similarity through high-variability: statistical analysis ofEthernet LAN traffic at the source level

A number of empirical studies of traffic measurements from a variety of working packet networks have demonstrated that actual network traffic is self-similar or long-range dependent in nature-in sharp contrast to commonly made traffic modeling assumptions. We provide a plausible physical explanation for the occurrence of self-similarity in local-area network (LAN) traffic. Our explanation is based on convergence results for processes that exhibit high variability and is supported by detailed statistical analyzes of real-time traffic measurements from Ethernet LANs at the level of individual sources. This paper is an extended version of Willinger et al. (1995). We develop here the mathematical results concerning the superposition of strictly alternating ON/OFF sources. Our key mathematical result states that the superposition of many ON/OFF sources (also known as packet-trains) with strictly alternating ON- and OFF-periods and whose ON-periods or OFF-periods exhibit the Noah effect produces aggregate network traffic that exhibits the Joseph effect. There is, moreover, a simple relation between the parameters describing the intensities of the Noah effect (high variability) and the Joseph effect (self-similarity). An extensive statistical analysis of high time-resolution Ethernet LAN traffic traces confirms that the data at the level of individual sources or source-destination pairs are consistent with the Noah effect. We also discuss implications of this simple physical explanation for the presence of self-similar traffic patterns in modern high-speed network traffic     

Simulation‐based results of weighted fair queuing algorithms for ATM networks

The behavior of the ideal General Processor Sharing (GPS) discipline and different per‐VC queuing algorithms approximating this ideal scheme, namely the Self Clocked Fair Queuing, the Packet by Packet Generalized Processor Sharing, and the Virtual Starting Time disciplines, are studied in this paper via simulation. We specifically consider a simple simulation configuration involving two Constant Bit rate (CBR) connections and several ON/OFF connections (bursty traffic). This simple simulation experiment allows us to point out three important features of the GPS and approximating disciplines. First, by adequately choosing the weight coefficients, these scheduling schemes can offer to CBR traffic almost Head of Line (HOL) priority over ON/OFF connections, to each of which, nevertheless, a minimum bandwidth is guaranteed. Second, GPS and per‐VC queuing disciplines, like the simple FIFO scheme, is very sensitive to burst scale congestion phenomena. Finally, simulation results seem to indicate that the scheduling disciplines considered perform traffic shaping on ON/OFF connections, which drastically reduces the burstiness of output traffic. This revised version was published online in June 2006 with corrections to the Cover Date.     

一种以太网流量的仿真方法

分析了以太网流量具有的自相似性和长相关性,并提出了详细的仿真方法用于产生具有这些特性的以太网流量.该软件方法基于ON/OFF模型和Pareto分布,提供了一种广泛适用的流量生成模型,其接口简单且易于定制.试验证明了该方法具有预期性能.     

Queue system analytical study with self-similar chaos-based traffic

Recent measures on LANs have highlighted the self-similar nature of the traffic. A systematic procedure to design a 1D chaotic map, which generates a self-similar process characterised by a polynomial OFF time distribution, is considered and reviewed. This polynomial law allows the performance of a queue system to be investigated by extending the G/M/l theory to the case of discrete arrival and service processes. Analytical results are reported highlighting the impact of the traffic self-similar degree and simulations show the validity of the developed theory     

DM-CSAT: a LTE-U/Wi-Fi coexistence solution based on reinforcement learning

Recent literature demonstrated promising results of Long-Term Evolution (LTE) deployments over unlicensed bands when coexisting with Wi-Fi networks via the Duty-Cycle (DC) approach. However, it is known that performance in coexistence is strongly dependent on traffic patterns and on the duty-cycle ON–OFF rate of LTE. Most DC solutions rely on static coexistence parameters configuration, hence real-life performance in dynamically varying scenarios might be affected. Advanced reinforcement learning techniques may be used to adjust DC parameters towards efficient coexistence, and we propose a Q-learning Carrier-Sensing Adaptive Transmission mechanism which adapts LTE duty-cycle ON–OFF time ratio to the transmitted data rate, aiming at maximizing the Wi-Fi and LTE-Unlicensed (LTE-U) aggregated throughput. The problem is formulated as a Markov decision process, and the Q-learning solution for finding the best LTE-U ON–OFF time ratio is based on the Bellman’s equation. We evaluate the performance of the proposed solution for different traffic load scenarios using the ns-3 simulator. Results demonstrate the benefits from the adaptability to changing circumstances of the proposed method in terms of Wi-Fi/LTE aggregated throughput, as well as achieving a fair coexistence.

     

Cell arrival modeling and related statistical multiplexer performance in ATM networks

A source is assumed to go through independently distributed ON and OFF periods. During an ON period, cells arrive spaced apart in time by a fixed interval. No cells arrive during an OFF period. The probability distribution of the ON and OFF periods are arbitrary. Traffic from a number of such sources is statistically multiplexed. The related statistical multiplexer performance is studied analytically as follows. A statistical multiplexer is modeled as a discrete-time single-server queueing system where the traffic from a new source (conforming to the cell arrival process described above) joins traffic that is already being statistically multiplexed. The aggregated arrival of cells from existing traffic is assumed to follow a two-state Markov modulated cell arrival process. Numerical examples that relate the performance at the statistical multiplexer to the parameters describing the traffic from the new source and the aggregated traffic are presented.This research was supported in part by the National Science Foundation under Grant No. NCR-9016348, and by the Pacific Bell External Technology Program.