Controlling mean queuing delay under multi-class bursty and correlated traffic

This paper presents an adaptive queue management scheme to maintain queuing delay in a router at a required level based on a comprehensive analytical model under aggregated Internet traffic flows from various traffic classes. The proposed scheme uses a closed-loop feedback control mechanism to constrain the average queuing delay by regulating traffic arrival rate implicitly through a movable queuing threshold. A discrete-time queuing model is developed to derive the relationship between average queuing delays and queuing thresholds based on a traffic model that models aggregated Internet traffic through superposition of N MMBP-2 arrival processes. The queuing threshold is adjusted dynamically with reference to the relationship derived in the analytical model and also feedback of average queuing delay measurement. Packets are dropped dynamically with respect to the changes of queuing threshold and the packet loss events serve as implicit congestion indicators. Matlab is used to perform queuing analysis and simulation. Statistical evaluation is performed to show the efficiency and accuracy of the analytical and simulation results.     

Generation of synthetic video traffic using time series

Generating traffic has always been an important part of network simulations but has turned to an even more challenging task with modern networks. The statistical properties of the input stochastic processes traced in the networks used all along Information Era turned out to be complicated and difficult to reproduce. Taking into account successful efforts in modeling Internet traffic with FARIMA time series models, this paper attempts to extend their applicability and employ them to generate synthetic video traffic. It is known that FARIMA can model both the Short Range (SRD) and Long Range Dependence (LRD) existing in video traffic; however the traces it produces fail to describe correctly the moments (mean, standard deviation, skewness, kurtosis) of the distribution behind the data. Since an efficient traffic generator should capture both the statistical properties and queuing behavior of video traffic we experiment with models such as FARIMA with Student's t errors and FARIMA-GARCH with Normal and Student's t errors, improving somewhat the accuracy of the generated traffic. Furthermore, the paper suggests the projection of the traces generated by a FARIMA model to values of a Lognormal distribution. It is shown that such a methodology produces synthetic traces that can emulate very closely the behavior of real traces. In order to quantify closeness the generated traces are fed into a simple FIFO queuing system with finite buffers, where loss probability is calculated and compared to that experienced by the corresponding real traces. Using five different real traces, MPEG-4 or H.263, it is shown that the proposed methodology produces traffic generators that can capture satisfactorily several statistical properties of the real traffic and also its queuing behavior for a wide range of buffer sizes and service rates.     

Per-stream loss behavior of ∑MAP/M/1/K queuing system with a random early detection mechanism

In this paper, the matrix-analytic approach is applied to explore the per-stream loss behavior of the multimedia traffic under RED scheme. We constructed a ∑MAP/M/1/K queuing model for the RED mechanism with multimedia traffic which follows a continuous-time Markovian arrival process (MAP). In addition to evaluating the long-term per-stream packet drop probabilities, we examine the bursty nature of per-stream packet drops by means of conditional statistics with respect to dropped periods and the probability that the queuing system stays in the dropped period. The dropped period corresponds to having more than a certain number of packets in router buffer; non-dropped period corresponds to the opposite. These performance measures describe the quality of service provided by the router to particular multimedia traffic streams in the presence of background multimedia traffic.     

Dimensioning shared-per-node recirculating fiber delay line buffers in an optical packet switch

Optical buffering based on fiber delay lines (FDLs) has been proposed as a means for contention resolution in an optical packet switch. In this article, we propose a queuing model for feedback-type shared-per-node recirculating FDL optical buffers in asynchronous optical switching nodes. In this model, optical packets are allowed to recirculate over FDLs as long as the total number of recirculations is less than a pre-determined limit to meet signal loss requirements. Markov Modulated Poisson Process (MMPP)-based overflow traffic models and fixed-point iterations are employed to provide an approximate analysis procedure to obtain blocking probabilities as a function of various buffer parameters in the system when the packet arrival process at the optical switch is Poisson. The proposed algorithm is numerically efficient and accurate especially in a certain regime identified with relatively long and variably-sized FDLs, making it possible to dimension optical buffers in next-generation optical packet switching systems.     

Correlation analysis of a discrete-time flexible arrival process

In this paper, a flexible discrete-time arrival process is introduced and its correlation properties are analyzed. The arrival process is the so-called batch-on/off model, an extension of the original on/off source used in the context of ATM networks. In the batch-on/off model, a group of arrivals may be generated at any given active slot. General distributions are assumed for the three input random variables characterizing the process: busy and idle periods, and batch size. The analysis focuses on two related processes: the process of counts and the sequence of interarrival times. For each process, an exact closed-form expression of its complete autocorrelation function is obtained. Explicit algorithms are provided to compute both autocorrelation functions, which are numerically evaluated for different distributions of the busy and idle periods and the batch size. The results provided in this paper reveal the analytical tractability of these models which, in addition to their flexibility, makes them very suitable for the performance evaluation of discrete-time communication systems and for general research in the area of queuing theory.     

基于车辆载带中继的路边单元突发业务分组调度最优策略

高速公路车联网场景中, 路边单元(Roadside units, RSUs)可作为多种周边监测数据的汇入网关, 其业务具有突发特性, 且可通过移动车辆以“存储?载带?转发”方式传输到与骨干网络互联的RSU. 针对RSU间业务传输问题, 源RSU可根据实时业务到达率按需匹配资源, 以应对业务突发性对分组端到端时延的影响. 本文首先针对RSU突发业务传输过程建立突发业务到达模型、车辆到达模型和离散车速状态模型; 进而利用受限马尔科夫决策过程对系统状态转移过程进行分析, 并建立非线性平均端到端时延最小化问题; 最后通过分析最优解的形式得出最优分组调度策略具有门限结构. 仿真结果验证了RSU间业务传输过程中排队时延和传播时延之间存在折中, 且该分组调度策略能降低业务传输过程的平均端到端时延.     

Numerical analysis of the power saving with a bursty traffic model in LTE-Advanced networks

We analyze the power saving operation called Discontinuous Reception (DRX) with a novel bursty packet arrival model in 3GPP Long Term Evolution (LTE)-Advanced networks. Typical analytical studies on the power saving operations in wireless networks have been carried out under the assumption that an expectation of exponentially distributed packet arrival intervals stays unchanged. However, practical packet arrival rate may change depending on time or typical Internet services may incur bursty packet arrivals. In either case, we need to evaluate the performance of the DRX operation. For this purpose, we develop a more realistic traffic arrival model considering packets may arrive in a bursty manner under the DRX operation. We, then, analyze the performance of the DRX operation in terms of power saving efficiency and average queuing delay, respectively. The analytical results are validated via comparisons with simulation results.     

自相似网络的时延抖动性能仿真分析

自相似性对网络性能产生了影响是当前的研究热点。建立了一种基于FBM的自相似网络排队时延抖动分析模型,重点讨论了自相似流量作为输入时对排队系统的时延抖动的影响。对理论分形流量和实际测量流量进行了仿真实验,验证了结果的正确性和有效性。实验结果表明：自相似流量长相关强弱的程度对排队系统时延抖动特性具有非常不同的影响,尤其是在缓存较大的情况下。同时,还发现网络流量中长相关发生作用时状态转变与排队系统本身的参数也有关,这是新的发现,对实时业务的网络性能评价具有重要的参考意义。     

Criticisms of modelling packet traffic using long-range dependence (extended version)

This paper criticises the notion that long-range dependence is an important contributor to the queuing behaviour of real Internet traffic. The idea is questioned in two different ways. Firstly, a class of models used to simulate Internet traffic is shown to have important theoretical flaws. It is shown that this behaviour is inconsistent with the behaviour of real traffic traces. Secondly, the notion that long-range correlations significantly affects the queuing performance of traffic is investigated by destroying those correlations in real traffic traces (by reordering). It is shown that the longer ranges of correlations are not important to mean queue length except in one case with an extremely high load.     

基于排队模型的包链测量方法特征分析

基于单跳路由器的排队模型,研究了受背景流量影响下的探测包链排队行为。随着背景流量影响程度的不同,分析得出无背景流量排队、短背景流量排队、长背景流量排队和多背景流量排队等四种具有不同时延变化分布特征的典型探测包链排队行为。仿真实验通过调整包链发送速率,模拟了不同的背景流量影响程度,发现探测包链的包时延变化有不同的分布特征,与分析的四种典型探测包链排队行为特征基本一致。     

基于Pareto分布的IP骨干节点输入通信量模型

输入通信量的行为特性对于IP骨干网节点的性能和设计有重要的影响.本文从IP骨干网络节点输入通信量角度出发,提出了一个基于Pareto和指数分布的混合通信量模型,其中数据包到达间隔为Pareto分布,包大小为指数分布.该模型克服了传统网络通信量模型中没有显式考虑数据包大小的缺点,从数据包级对网络通信量进行了精确的描述,从而能够更好地进行路由器结构设计和性能分析.仿真实验验证了我们模型的有效性.     

Some issues in performance modeling of data teletraffic

Data teletraffic is characterized by bursty arrival processes. Performance models are characterized by a desire to know under what circumstances is the probability that an arrival finds a full input buffer very small. In this paper I examine how four models proposed in the literature perform on two data sets of local area network traffic. Among my conclusion are (1) the protocol governing the data transmission may have a substantial effect on the statistical propoerties on the packet stream, (2) approximating the probability that a finit buffer of size b overflows may not be adequately approximated by the probability that an infinite buffer has at least b packets in it, and (3) a data-based estimate of large-deviation rate-function does the best job of estimating packet loss on these data sets. This method may overestimate the loss rate by several orders of magnitude, so there is room for further refinements.     

Heavy traffic queue with stochastic arrival and service rates

A new approach is proposed to model heavy traffic queuing behaviour by stochasticizing in various ways the arrival and service rates so as to incorporate the random effect of the environment. This approach yields for the queue size a differential equation with stochastic parameters. The corresponding Fokker-Planck equation for the probability density function of the queue size is employed to analyse the queuing system. In this framework we consider the arrival and service rates to be subject to gaussian, white-noise perturbations and obtain the probability density function of the queue size and the distribution of the busy period. The study is generalized by considering the effect of coloured-noise perturbations in these rates. The effect of the white-noise perturbations on the state-dependent service rate is also investigated.     

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).     

One-way queuing delay measurement and its application on detecting DDoS attack

This paper presents a novel approach to measure and estimate end-to-end one-way queuing delay in a network, which carries information about traffic characteristics and congestion properties. The measurement results can be used to describe the normal behavior of the network and detect distributed denial-of-service attacks (DDoS attacks). The measurement does not require any synchronization between the two measurement ends. Pairs of probe packets are sent from the source to the destination and intra-gaps between the probes are separately measured at the two ends. By performing an iterative Fourier-to-time reconstruction algorithm on the measured intra-gaps, distribution of the end-to-end one-way queuing delay is estimated. The packet loss rate and delay jitter are simultaneously measured as well. The simulations and experiments are conducted to validate the approach.     

Dynamic neural-based buffer management for queuing systems with self-similar characteristics

Buffer management in queuing systems plays an important role in addressing the tradeoff between efficiency measured in terms of overall packet loss and fairness measured in terms of individual source packet loss. Complete partitioning (CP) of a buffer with the best fairness characteristic and complete sharing (CS) of a buffer with the best efficiency characteristic are at the opposite ends of the spectrum of buffer management techniques. Dynamic partitioning buffer management techniques aim at addressing the tradeoff between efficiency and fairness. Ease of implementation is the key issue when determining the practicality of a dynamic buffer management technique. In this paper, two novel dynamic buffer management techniques for queuing systems accommodating self-similar traffic patterns are introduced. The techniques take advantage of the adaptive learning power of perceptron neural networks when applied to arriving traffic patterns of queuing systems. Relying on the water-filling approach, our proposed techniques are capable of coping with the tradeoff between packet loss and fairness issues. Computer simulations reveal that both of the proposed techniques enjoy great efficiency and fairness characteristics as well as ease of implementation.     

基于超爱尔兰分布的自相似网络排队模型研究

现有网络的业务流研究表明,多种通信业务中普遍存在自相似特性,但是如何对自相似业务流进行建模和分析一直是个难解问题。基于超爱尔兰拟合算法,建立了到达为泊松分布,服务时间为超爱尔兰分布的M/HErD/1/K自相似排队模型,推导得到呼叫损失概率、平均排队队长等排队性能的解析解。在实际业务环境下和传统的M/M/1/K排队模型进行了仿真对比,结果表明M/HErD/1/K模型不仅可有效表征业务流的快挂业务特性,而且能仿真出该网络在业务负荷较重时潜在的运营风险,对实际网络运营管理具有重要的指导作用。     

An unified VoIP model for workload generation

This paper presents a new model for VoIP workload generation. The novelty of our proposal consists in modeling the sessions by characterizing both the user behavior (session level) and the packet generation for an active call (intra-session level) with easily measured parameters and low computational complexity. This approach also facilitates systematic study of changes in user behavior and voice codec. The session level was modeled by analysis of call-holding time and time interval between successive calls. The model for call-holding time, characterizing the individual user behavior, uses the Pareto type 2 probability distribution. The time interval between calls is obtained from aggregate traffic and can be modeled by exponential probability distribution. Aggregate traffic is obtained by superposition of simultaneous sessions. The data used to characterize the session level were collected at the backbone of two Brazilian telecommunication carriers. The model for intra-session level comprises the characterization of the packet size and the packet inter-arrival time. The intra-session model was based on data generated in a laboratory environment, in order to properly characterize the codec influence on packet generation and to avoid the effects of delay, jitter and loss commonly present in an operational network. Models for constant bit rate and variable bit rate codecs were considered. A simulator was implemented and the results indicate that our model properly mimics the characteristics observed in real traffic and can be used for VoIP modeling and workload generation. Additionally, an application to automate the performance analysis was developed.     

BitTorrent packet traffic features over IPv6 and IPv4

At present, BitTorrent protocol packets constitute a large part of peer-to-peer application traffic on the Internet. Due to the increasing amount of BitTorrent traffic, it has become inevitable to take into account its effects on network management. Generally, studies on BitTorrent traffic measurement have involved analysis with packets transmitted via IPv4 protocol. However, with several facilities provided by IPv6 protocol, its traffic volume in operational networks is increasing day by day. New features of IPv6 enhance packet processing speeds over routers, switches and end systems. We consider that traffic features and packet traffic characteristics are likely to be affected with increasing amount of IPv6 protocol traffic. Therefore, it becomes significant to explore IPv6 packet traffic characteristics and application traffic features over IPv6. In this study, we investigate the IPv6 BitTorrent packet traffic characteristics in terms of autocorrelation, power spectral density and self similarity of packet size and packet interarrival time. We also perform distribution modeling for IPv4 and IPv6 BitTorrent packet traffic. With these models, efficient packet traffic traces are generated for network simulation studies. A detailed comparison is performed to determine differences between IPv4 and IPv6 BitTorrent packet traffic.     

JitterPath: Probing Noise Resilient One-Way Delay Jitter-Based Available Bandwidth Estimation

Measurement of end-to-end available bandwidth has received considerable attention due to its potential use in improving QoS. Available bandwidth enables the sending rate to adapt to network conditions, so that packet loss, caused by congestion, can be significantly reduced before error control mechanisms are finally employed. To this end, we propose a probing noise resilient available bandwidth estimation scheme, called JitterPath, which is adaptive to both the fluid and bursty traffic models. Two key factors, one-way delay jitter and accumulated queuing delay, are both exploited to predict the type of queuing region for each packet pair. Then, the bottleneck utilization information included in the joint queuing regions is estimated and used to quantify the captured traffic ratio, which indicates the relationship between the probing rate and available bandwidth. The contributions of our method are as follows: 1) JitterPath can work without being restricted to fluid traffic models; 2) since JitterPath does not directly use the bottleneck link capacity to calculate the available bandwidth, it is feasible for use in a multihop environment with a single bottleneck; and 3) JitterPath inherently reduces the impact of probing noises under the bursty cross traffic model. Extensive simulations, Internet experiments, and comparisons with other methods were conducted to verify the effectiveness of our method under both single-hop and multihop environments