Scene oriented model for VBR video

A new model for variable bit rate (VBR) video traffic is presented. The model, which could be used as a traffic generator, considers two time scales: scenes, for periods of several minutes, and groups of pictures (GOP), for periods of half a second. To model the scene changes, a Markov chain is used. For the GOP level. A modification for the projected autoregressive (PAR) model is proposed so that the fitting of the autocorrelation function is improved. The model is used to imitate two real MPEG video signals, showing that it is able to accurately capture the behaviour of the real traffic in a queue     

An adaptive cross-layer mapping algorithm for MPEG-4 video transmission over IEEE 802.11e WLAN

This paper proposes an adaptive cross-layer mapping algorithm to improve the transmission quality of MPEG-4 video stream over an IEEE 802.11e wireless network. Instead of classifying video data to a specific access category in an 802.11e network, we propose an algorithm that dynamically maps MPEG-4 video packets to appropriate access categories according to both the significance of the video data and the network traffic load. Our proposed cross-layer architecture passes information about the significance of video packets from the application layer to the media access control layer. The queue length of a specific access category is used to deduce the network traffic load. We conducted a performance evaluation of our proposed cross-layer approach under both light and heavily loaded network conditions. Our simulation results demonstrate: (a) superior performance of our proposed approach (under both light and heavy loads) over 802.11e (Enhanced Distributed Channel Access (EDCA) and static mapping schemes, (b) not only guarantees prioritized transmission of essential video data but also provides efficient queue length utilization.     

多信道无线通信网混合业务接入控制的离散排队分析

基于无线通信网的运行机制、实时性和非实时性混合业务对无线通信网络不同服务质量(QoS)要求,设计了实时性业务优先接入控制策略,建立了无线通信网络的混合业务带有优先接入控制的多服务台离散时间排队模型Geo1 Geo2/Geo1,Geo2/s,s(PP)。并且应用矩阵几何解方法,对该排队模型进行精确分析,得到了系统的主要性能指标:实时性业务和非实时性业务的平均队长、实时性业务的阻塞概率、系统信道利用率等结果。     

DYNAMIC BANDWIDTH ALLOCATION IN AN ATM MULTIPLEXER WITH MULTICLASS TRAFFIC AND ITS PERFORMANCE ANALYSIS

This paper introduces two source models: MAP(Markovian arrival process) model for the traffic with correlation and burst, e.g., voice, video, etc. and PAP(Poisson arrival process) model for the traffic with non-correlation, such as data, etc. Then a movable boundary bandwidth access policy is chosen.Basing on above model, the performance measures, e.g., mean waiting time and loss probability,especially the queue length time distribution are obtained. Finally, a number of numerical results are provided and shown through simulation.     

Real-time image processing approach to measure traffic queueparameters

The real-time measurement of various traffic parameters including queue parameters is required in many traffic situations such as accident and congestion monitoring and adjusting the timings of the traffic lights. In case of the queue detection, at least two algorithms have been proposed by previous researchers. Those algorithms are used for queue detection and are unable to measure queue parameters. The authors propose a method based on applying the combination of noise insensitive and simple algorithms on a number of sub-profiles (a one-pixel-wide key-region) along the road. The proposed queue detection algorithm consists of motion detection and vehicle detection operations, both based on extracting edges of the scene, to reduce the effects of variation of lighting conditions. To reduce the computation time, the motion detection operation continuously operates on all the sub-profiles, but the vehicle detection is only applied to the tail of the queue. The proposed algorithms have been implemented on an 80386-based microcomputer system and the whole system works in real-time     

Parameter estimation and optimization techniques for discrete-time semi-Markov models of H.264/AVC video traffic

We investigate a variety of known and new approaches for the estimation of the parameters of discrete-time semi-Markovian traffic models. We focus on modeling video traffic, since the accurate representation of its long-term autocorrelation is a challenge to the parameter estimation methods. The modeling techniques are applied to sample H.264/AVC-encoded video traces. We study their ability to reflect the autocorrelation and variability of the original traffic and also the delay probabilities of a resulting SMP/GI/1 queueing system. The delay probabilities are determined both by simulation and verified analysis of the queue.     

The effect of multiple time scales and subexponentiality in MPEGvideo streams on queueing behavior

Guided by the empirical observation that real-time MPEG video streams exhibit both multiple time scale and subexponential characteristics, we construct a video model that captures both of these characteristics and is amenable to queueing analysis. We investigate two fundamental approaches for extracting the model parameters: using sample path and second-order statistics-based methods. The model exhibits the following two canonical queueing behaviors. When strict stability conditions are satisfied, i.e., the conditional mean of each scene is smaller than the capacity of the server, precise modeling of the interscene dynamics (long-term dependency) is not essential for the accurate prediction of small to moderately large queue sizes. In this case, the queue length distribution is determined using quasistationary (perturbation theory) analysis. When weak stability conditions are satisfied, i.e., the conditional mean of at least one scene type is greater than the capacity of the server, the dominant effect for building a large queue size is the subexponential (long-tailed) scene length distribution. In this case, precise modeling of intrascene statistics is of secondary importance for predicting the large queueing behavior. A fluid model, whose arrival process is obtained from the video data by replacing scene statistics with their means, is shown to asymptotically converge to the exact queue distribution. Using the transition scenario of moving from one stability region to the other by a change in the value of the server capacity, we synthesize recent queueing theoretic advances and ad hoc results in video modeling, and unify a broad range of seemingly contradictory experimental observations found in the literature. As a word of caution for the widespread usage of second-order statistics modeling methods, we construct two processes with the same second-order statistics that produce distinctly different queueing behaviors     

Evaluating the limit behavior of the ATM traffic within a network

This paper is concerned with the ATM traffic characterization within the network. Most of the work performed up to now has studied the effects of traffic on the access multiplexer and the first switch of an ATM network. Various source models were assumed to generate the ATM traffic. So, while the performance of a single switch node has been exhaustively examined, the statistical behavior of the traffic modified as it crosses the network has not been thoroughly analyzed yet. This paper, through an analysis of a network of cascaded queues, indicates that limit distributions exist in the statistical behavior of the traffic streams and in the queue performance, although a formal proof is believed to be very hard to obtain. The first modelling step consists of deriving the exact interdeparture time distribution for the cells of a reference-connection arriving to the output queue of a switch node with a general interarrival time distribution and multiplexed with a background traffic stream. The analysis is iterated through a long sequence of cascaded output queues, until the interdeparture time distribution converges. Simulations show that the analytical results are accurate at each stage of the network under the hypothesis of independent queues, and are also good approximations in the case of correlated queues. This study shows that the queue performance at the limit point is always better than the M/D/1 case. The distributions found in this way depend only on the connection bandwidth and on the background traffic behavior. The initial characteristics of a connection (burst length distributions and burst interarrival time distributions) only influence the convergence speed, not the limit distribution     

An approximation for the loss probability in a multiserver queue fed by a shifting level process

A shifting level (SL) process is useful to traffic modeling because it is very easy to match the stationary distribution and autocorrelation function of the SL process with those of measured real traffics. Especially, SL processes have been used to traffic modeling for VBR video traffics reflecting the long range dependence and the scene structure. We give an approximation for the loss probability in a multiserver queue fed by a SL process. Numerical examples show that our approximation is very accurate.     

Improved multi-fractal network traffic model and its performance analysis

This paper demonstrates the limitation of the traditional multi-fractal wavelet model(MWM).Through analyzing the multi-resolution behaviors of the real video traffic,we propose an improved MWM model.It synthesizes the traffic traces using another wavelet basis,and can adjust wavelet coefficients and multiplicative coefficients at each time scale,based on the network measurement.Subsequently,multifractal spectra and queue performances of the new model have been analyzed.The simulation proves it can capture the multifractal behaviors of network traces.     

Quasi-pushout cell discarding

In asynchronous transfer mode (ATM) switching networks, buffers are required to accommodate traffic fluctuations due to statistical multiplexing. However, cell discarding takes place when the buffer space of a network node is used up during a traffic surge. Though pushout cell discarding was found to achieve fair buffer utilization and good cell loss performance, it is difficult to implement because of the large number of queue length comparisons. We propose quasi-pushout cell discarding which reduces the number of queue length comparisons by employing the concept of quasi-longest queue. Simulation results under bursty and imbalanced traffic conditions show that quasi-pushout can achieve comparable cell loss performance as pushout at a much lower complexity     

一种基于预测PI控制器的自相似网络主动队列管理算法

近年研究发现网络中的业务量呈自相似特征,这种自相似特征显著影响网络的流量控制与排队性能,本文在自相似网络流量可预测的基础上,利用线性回归分析理论进行流量预测,并应用控制理论中的预测PI控制器原理设计了动态矩阵PI控制主动队列管理(Dynamic Matrix PI Control-Active Queue Management,简称DMPIC-AQM)算法,以克服队列的剧烈振荡,保持队列稳定在期望的长度.仿真实验结果表明,DMPIC-AQM算法在网络流量剧烈变化和小期望队列长度的情形下,DMPIC-AQM算法明显优于RED与PI算法.     

SMAQ: a measurement-based tool for traffic modeling and queuinganalysis. I. Design methodologies and software architecture

SMAQ is a measurement-based tool for integration of traffic modeling and queuing analysis. There are three basic components in SMAQ. In the design of the first component, statistic measurement, the most critical issues are to identify the important traffic statistics for queuing analysis in a finite buffer system and then to build a measurement structure to collect them. Our study indicates that both first- and second-order traffic statistics, measured within a given frequency-window, have a very significant impact on the queue length and loss rate performance. In the design of the second component, matched modeling, the focal point is to construct a stochastic model that can match a wide range of important statistics collected in various applications. New methodologies and fast algorithms are developed for such construction on the basis of a circulant modulated Poisson process (CMPP). For the third component, queuing solutions, the basic requirement is to provide numerical solutions of the queue length and loss rate for transport of given traffic in a finite buffer system. A fast and stable computation method, called a Folding algorithm, is applied to provide both steady-state and transient solutions of various kinds, including congestion control performance where arriving traffic are selectively discarded based on queue thresholds. We provide both design methodologies and software architectures of these three components, with discussion of practical engineering issues for the use of the SMAQ tool     

Accurate Prediction of Real‐Time MPEG‐4 Variable Bit Rate Video Traffic

In this letter, we propose a novel algorithm to predict MPEG‐coded real‐time variable bit rate (VBR) video traffic. From the frame size measurement, the algorithm extracts the statistical property of video traffic and utilizes it for the prediction of the next frame for I‐, P‐, and B‐ frames. The simulation results conducted with real‐world MPEG‐4 VBR video traces show that the proposed algorithm is capable of providing more accurate prediction than those in the research literature.     

Queue length‐based load balancing in data center networks

Traffic load balancing in data centers is an important requirement. Traffic dynamics and possibilities of changes in the topology (e.g., failures and asymmetries) make load balancing a challenging task. Existing end‐host–based schemes either employ the predominantly used ECN or combine it with RTT to get congestion information of paths. Both congestion signals, ECN and RTT, have limitations; ECN only tells whether the queue length is above or below a threshold value but does not inform about the extent of congestion; similarly, RTT in data center networks is on the scale of up to few hundreds of microseconds, and current data center operating systems lack fine‐grained microsecond‐level timers. Therefore, there is a need of a new congestion signal which should give accurate information of congestion along the path. Furthermore, in end‐host–based schemes, detecting asymmetries in the topology is challenging due to the inability to accurately measure RTT on the scale of microseconds. This paper presents QLLB, an end‐host–based, queue length–based load balancing scheme. QLLB employs a new queue length–based congestion signal that gives an exact measure of congestion along the paths. Furthermore, QLLB uses relative‐RTT to detect asymmetries in the topology. QLLB is implemented in ns‐3 and compared with ECMP, CONGA, and Hermes. The results show that QLLB significantly improves performance of short flows over the other schemes and performs within acceptable level, of CONGA and Hermes, for long flows. In addition, QLLB effectively detects asymmetric paths and performs better than Hermes under high loads.     

基于多终端协同的高清视频多流并发自适应传输控制方法

摘要：针对高清视频在异构无线网络中以多流并发的方式进行传输,以提高传输速率,从而增强用户体验的问题,以最小化系统传输时延以及各路径间时延差为优化目标,联合考虑了视频发送端和接收端,自适应调整视频发送速率和接收端缓存大小以提高用户体验,建立了异构无线网络中视频多流并发传输的控制模型,并基于Pareto分布和P/P/1排队理论对具有自相似性和长相关性的视频流进行了研究,推导了并发传输系统的时延统计特性,并在此基础上提出了一种异构无线网络视频流自适应分流决策方法。仿真结果表明,与一般的负载均衡分流决策方法相比,提出的异构网络多流并发自适应传输控制方法在时延和分组丢失率方面都有一定的优越性。     

Traffic-based queue-aware scheduling for 3GPP LTE system

Although the medium access control （MAC） signaling has been well-defined in the 3rd generation partnership project （3GPP） long term evolution （LTE） specifications, the scheduling algorithm crucial to guarantee QoS performance, still remains as open issues. In this article, a traffic-based queue-aware scheduling （TQS） algorithm is proposed for evolved nodeB＇s （eNB＇s） MAC scheduler in 3GPP LTE broadband wireless networks. The proposed TQS is divided into three sub-algorithms： firstly, the authors propose a traffic model construction （TMC） algorithm which can construct a discrete-time Markov-modulated Poisson process （dMMPP） to represent each flow. Secondly, a newly traffic state estimation （TSE） algorithm is designed to obtain the queue＇s analytical statistics. Thirdly, based on the derived results of TSE and the channel states, a scheduling action decision （SAD） algorithm is presented that can adaptively allocate bandwidth to flows by considering both queue states and spectrum efficiency. Simulation shows that the TMC and TSE algorithm can capture the fluctuation of traffic and queue accurately. Moreover, compared with a widely accepted traffic-based scheduling algorithm, the proposed TQS has better average queue length and overflow probability performance.     

基于强化学习的交叉口交通低排放信号控制研究

交叉口车辆排放较为复杂,尤其是在考虑初始排队长度的情况下,更是难以建立明确的数学模型。Q学习是一种无模型的强化学习算法,通过与环境的试错交互学习最优控制策略。本文提出了一种基于Q学习的交通排放信号控制方案。利用仿真平台USTCMTS2.0,通过不断地试错学习找到在不同相位排队长度下最优配时。在Q学习中添加了模糊初始化Q函数的方法以改进Q学习的收敛速度,加速了学习过程。仿真实验结果表明:强化学习算法取得较好的效果。相比较Hideki的方法,在车流量较高时,车辆平均排放量减少了13.9%,并且对Q函数值的模糊初始化大大加速了Q函数收敛的过程。     

多重分形网络流量的单队列输入排队性能研究

多重分形已被证明能够较好地用于网络流量多尺度突发行为特性的研究.本文以队列处于满负荷状态的概率为指标研究了多重分形流量输入下单队列的排队性能问题,提出了以尺度函数与矩因子表示的队列满负荷运行概率的解析性框架.用FBM过程作为输入,从理论上验证了该概率框架的正确性,进一步用实测的网络流量数据对多重分形流量输入下单队列满负荷运行的概率进行了分析与比较,结果表明该框架能同时满足单、多重分形流量输入时排队性能的计算.结合文献[1]给出的联合多重分形(JMF)流量模型,为排队系统中队列深度的设计提供了有效的定量计算方法.     

Video transmission strategy in multi-rate and multi-node IEEE 802.11 networks

The video transmission strategy VQCW (video queue contention window) was proposed for video transmission fair problem in multi-rate and multi-node IEEE 802.11 networks.The strategy was based on node queue selective packet drop and contention window dynamic adjustment.It deduced a maximum throughput model according to initial contention window size because of the relation between throughput and initial contention window size.This model can provide theoretical upper limit for improving throughput.The theoretical modeling and NS simulation show that the proposed strategy can maintain both video transmission quality and high network overall throughput.