Online traffic smoothing for delivery of variable bit rate media streams

Traffic smoothing for delivery of online variable bit rate (VBR) media streams is one of the most important problems in designingmultimedia systems. Given an available client buffer, a window size, and a window-sliding size, previous window-based online smoothing methods have tried to reduce the peak bandwidth allocated in each window. However, as bandwidths allocated in different windows are minimized independently, these methods require a large peak bandwidth for transmitting an entire stream. In this paper, a new window-based method is proposed. It introduces two new ideas, the dynamic windowsliding size and the aggressive workahead, for delivery of online VBR media streams. Our aggressive and dynamic window sliding (ADWS) method can automatically decide on the suitable window-sliding sizes for different windows. Thus, the allocated peak bandwidth can be further reduced. By examining various media streams, ADWS is shown to be effective and efficient. Considering the online transmission of the movieStar Wars with a 90-kB client buffer, ADWS yields 13% less in peak bandwidth, compared with the bestknown window-based online smoothing algorthm SLWIN(1). Its computation cost (the window-sliding number) is 75% of that required by SLWIN(1).This work was partially supported by NSC, Taiwan, under grants. NSC88-2213-E-001-011, NSC88-2213-E-001-012, and NSC88-2213-E-001-025. A primitive version of this work appeared in IEEE INFOCOM'99 [7].     

Multi-scaling chaotic map suitable for modelling aggregate TCP/IP and MPEG4 traffic streams

Both TCP/IP traffic and MPEG4 scalable video are known to exhibit multi-fractal behaviour. By subdividing the intermittency portion of a chaotic map, packet traffic with multi-fractal scaling can be modelled. This novel chaotic map structure accurately reproduces the scaling behaviour, and is straightforward to parameterise from scaling measurements and finite timescale ranges. Unlike cascade models, the multi-scaling chaotic map can be employed in continuous online generation, offering the real possibility of an aggregate model capable of reacting to network conditions.     

Experience with pipelined multiple instruction streams

Pipelining has been used to implement efficient, high-speed vector computers. It is also an effective method for implementing multiprocessors. The Heterogeneous Element Processor (HEP) built by Denelcor Incorporated is the first commercially available computer system to use pipelining to implement multiple processes. This paper introduces the architecture and programming environment of the HEP and surveys a range of scientific applications programs for which parallel versions have been produced, tested, and analyzed on this computer. In all cases, the ideal of one instruction completion every pipeline step time is closely approached. Speed limitations in the parallel programs are more often a result of the extra code necessary to ensure synchronization than of actual synchronization lockout at execution time. The pipelined multiple instruction stream architecture is shown to cover a wide range of applications with good utilization of the parallel hardware.     

Wide-area IP multicast traffic characterization

IP multicast is gaining acceptance among service providers as the protocols and infrastructure mature. However, characteristics of multicast traffic remain poorly understood. Using passive OC-12 monitors, we observed multicast traffic on links connecting aggregated customers and peer networks to our native multicast backbone network. We first refined existing traffic flow profiling methodologies via an exploration of temporal differences in multicast packet trains. Based on this framework, we collected multicast flow traces from four geographically dispersed nodes in the Worldcom vBNS network over a one-month period. We present multicast-specific traffic characteristics including packet and flow sizes, fragmentation, sources per group, and address space distribution. Analysis reveals results contrary to prevailing wisdom, including a preponderance of single-packet flows; a highly variable packet size distribution, with many large packets and strong modes; the existence of fragmented multicast traffic; and an insignificant number of simultaneous multiple-source groups. Based on our analysis, we recommend policies for deployment and improvements to protocol implementations.     

Shaping of traffic streams through data spacing

A traffic shaping algorithm, based on suitable spacing of data units, is proposed and validated both theoretically and by simulation. It ensures a “tight” upper bound to the queue-length distribution at subsequent multiplexing stages, being essentially an effective-rate-enforcement mechanism in the asymptotic regime. It does not presume any stationarity, homogeneity or Markovian property of the input streams     

MPEG-4码流在IP网络上的传输

MPEG-4终端结构最近在视听对象编码以及场景编码方面的进展很快，已经出现了很多的标准，使得场景编码能够和视听对象编码联系在一起。MPEG-4标准在多媒体技术方面有了突破，这个标准明确了视听对象和场景的编码方法、如何将对象展现存储以及如何通过各种传输技术来访问它。MPEG-4终端如图1所示，主要包含三层：压缩层、同步层和传输层。分层结构有利于模块化设计，确保每一层只需知道对自己有用的信息。在压缩层，媒体（如声音、背景等）是按照不同的对象编码的，编码后的比特流以访问单元的形式送到同步层，访问单元是同步层中最小的…     

Modeling of systems with overflow multi-rate traffic

The article proposes an analytical method for determining occupancy distribution and blocking probability in systems which are offered overflow traffic composed of multi-service traffic streams. The described analytical model enables determination of parameters of traffic overflowed from primary groups in hierarchically constructed telecommunication networks. The proposed method is based on an appropriate modification of the Kaufman-Roberts recursion for the full-availability group with multi-rate traffic and uses the modified Fredericks & Hayward’s approximation. Additionally, an approximate method for dimensioning systems with multi-service overflow traffic is also presented. The analytical results of the blocking probability and the results obtained in the dimensioning processes calculated using the presented methodology are compared with the data obtained from the system simulation process.     

跨越不同容量设置DWDM网络的动态IP/DWDM综合路由算法研究

IP/DWDM网络的综合路由中的一个重要的研究问题就是如何对跨越不同DWDM网络的IP路由进行综合路由,特别是当两个DWDM网络的容量设置不同时。本文着重解决的就是如何对从单波长带宽大的网络进入单波长带宽小的网络传输的IP业务的综合路由问题。根据尽量鼓励对波长链路的带宽进行完全使用,以减小波长链路带宽碎片的原则,我们提出了两种解决算法:1 n 算法和 m n算法。仿真结果对两种算法的效率和性能进行了测试。     

Understanding Internet traffic streams: dragonflies and tortoises

We present the concept of network traffic streams and the ways they aggregate into flows through Internet links. We describe a method of measuring the size and lifetime of Internet streams, and use this method to characterize traffic distributions at two different sites. We find that although most streams (about 45 percent of them) are dragonflies, lasting less than 2 seconds, a significant number of streams have lifetimes of hours to days, and can carry a high proportion (50-60 percent) of the total bytes on a given link. We define tortoises as streams that last longer than 15 minutes. We point out that streams can be classified not only by lifetime (dragonflies and tortoises) but also by size (mice and elephants), and note that stream size and lifetime are independent dimensions. We submit that ISPs need to be aware of the distribution of Internet stream sizes, and the impact of the difference in behavior between short and long streams. In particular, any forwarding cache mechanisms in Internet routers must be able to cope with a high volume of short streams. In addition ISPs should realize that long-running streams can contribute a significant fraction of their packet and byte volumes-something they may not have allowed for when using traditional "flat rate user bandwidth consumption" approaches to provisioning and engineering.     

GARCH model-based large-scale IP traffic matrix estimation

This letter proposes a novel method to estimate large-scale IP traffic matrix (TM). By using the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) to model the Origin-Destination (OD) flows, we can easily get rid of the ill-posed problem of large-scale IP TM. Compared with previous methods, our method does not only hold the lower estimation errors but also is more robust to the noise.     

IP network configuration for intradomain traffic engineering

The smooth operation of the Internet depends on the careful configuration of routers in thousands of autonomous systems throughout the world. Configuring routers is extremely complicated because of the diversity of network equipment, the large number of configuration options, and the interaction of configuration parameters across multiple routers. Network operators have limited tools to aid in configuring large backbone networks. Manual configuration of individual routers can introduce errors and inconsistencies with unforeseen consequences for the operational network. In this article we describe how to identify configuration mistakes by parsing and analyzing configuration data extracted from the various routers. We first present an overview of IP networking from the viewpoint of an Internet service provider and describe the kinds of errors that can appear within and across router configuration files. To narrow the scope of the problem, we then focus our attention on the configuration commands that relate to traffic engineering-tuning the intradomain routing protocol to control the flow of traffic through the ISP network. We present a case study of a prototype tool, developed in collaboration with AT&T IP Services, for checking the configuration of the AT&T IP Backbone and providing input to other systems visualization and traffic engineering     

NetScope: traffic engineering for IP networks

Managing large IP networks requires an understanding of the current traffic flows, routing policies, and network configuration. However, the state of the art for managing IP networks involves manual configuration of each IP router, and traffic engineering based on limited measurements. The networking industry is sorely lacking in software systems that a large Internet service provider can use to support traffic measurement and network modeling, the underpinnings of effective traffic engineering. This article describes the AT&T Labs NetScope, a unified set of software tools for managing the performance of IP backbone networks. The key idea behind NetScope is to generate global views of the network on the basis of configuration and usage data associated with the individual network elements. Having created an appropriate global view, we are able to infer and visualize the networkwide implications of local changes in traffic, configuration, and control. Using NetScope, a network provider can experiment with changes in network configuration in a simulated environment rather than the operational network. In addition, the tool provides a sound framework for additional modules for network optimization and performance debugging. We demonstrate the capabilities of the tool through an example traffic engineering exercise of locating a heavily loaded link, identifying which traffic demands flow on the link, and changing the configuration of intradomain routing to reduce the congestion     

Dimensioning IP access links carrying data traffic

This paper proposes simple dimensioning rules for high speedip access links carrying data traffic. Assuming a finite source population and fair bandwidth sharing among user flows, we derive formulas relating capacity, demand and performance. These formulas allow link dimensioning for a target quality of service expressed in terms of useful per-flow throughput. They constitute a data traffic model equivalent of the Engset model for telephone access networks. Performance is shown to be largely independent of detailed traffic characteristics such as the statistical distributions of flow size and think time. Simple approximations are derived for two distinct performance regimes corresponding to transparency and saturation, respectively. Extensions to the basic model account for a heterogeneous user demand, unfair bandwidth sharing or different access rate classes. In any case, the key parameter for dimensioning is the offered traffic, defined as the average data rate a user would generate in the absence of congestion.     

MPLS and traffic engineering in IP networks

Rapid growth and increasing requirements for service quality, reliability, and efficiency have made traffic engineering an essential consideration in the design and operation of large public Internet backbone networks. Internet traffic engineering addresses the issue of performance optimization of operational networks. A paramount objective of Internet traffic engineering is to facilitate the transport of IP traffic through a given network in the most efficient, reliable, and expeditious manner possible. Historically, traffic engineering in the Internet has been hampered by the limited functional capabilities of conventional IP technologies. Recent developments in multiprotocol label switching (MPLS) and differentiated services have opened up new possibilities to address some of the limitations of the conventional technologies. This article discusses the applications of MPLS to traffic engineering in IP networks     

IP骨干网流量的自动化预测

高效、可靠的网络流量预测是网络规划、扩容建设的基础。互联网流量目前缺乏完备的理论模型,行业内大多根据工程实践特点,设计简化可操作的预测模型以满足IP网络规划需求。首先根据中国电信自身IP骨干网流量预测工作的需求及特点,使用时间序列分析的多因子回归模型和函数自适应模型对IP骨干网流量进行分析和预测,基于大量现网实际数据的仿真运算,对比两种模型的特点、优劣和适用场景,提出了一种预测模型选择和参数优化的原则和方法。在此基础上,构建了可以满足百千量级时间序列要求的自动化流量预测系统,极大简化并提升了流量预测工作的效率。最后,展望了未来IP流量预测工作的延展方向和关注重点。     

Modeling of HTTP traffic

In this letter, the authors show that the behavior of Web users strongly affects the dynamics of TCP connections in the Internet. Analyzing actual and systematically generated HTTP traces, it is proved that the time between the downloads of two pages is critical to determine the re-utilization of connections. On the other hand, the use of the 1.1 version of the HTTP standard does not significantly affect the traffic generated by HTTP 1.0 browsers. In this sense, the heavy-tailed nature of the size of HTTP connections can be considered an invariant property     

TELNET的客户端流量模型

本文针对英特网上的一个常用协议－远程登录（ＴＥＬＮＥＴ）协议分析了它的客户端数据包产生的时间间隔分布,发现泊松模型的指数分布不能很好地刻画它的特性。本文依据Ｔｃｐｌｉｂ提供的经验分布曲线,认为Ｐａｒｅｔｏ分布在很大时间范围内能较好地描述ＴＥＬＮＥＴ的客户端流量特性,并对其突发序列的特性进行了分析。本文最后指出在描述网络流量时自相似模型要比泊松模型有效和精确得多,并给出了Ｐａｒｅｔｏ分布在建立自相似     

Online rate control for video streams

A mechanism for varying the frame rate of pre-encoded video clips online is described. The mechanism relies on two different encoders. An offline encoder creates a high-quality bit stream encoded at 30 fps, as well as separate files containing motion vectors for the same clip at lower frame rates. An online encoder decodes the bit stream (if necessary) and re-encodes it at lower frame rates in real time using the precomputed, stored motion information. Online frame rate control, used in conjunction with dynamic bit rate control, allows clients to solve the rate mismatch between the bandwidth available to them and the bit rate of the pre-encoded bit stream. Clients can therefore choose the amount of trade-off between temporal and spatial quality while resolving the rate mismatch problem. Moreover, online frame rate control provides a natural means for implementing a VCR-like fast forward control for video streaming applications, without increasing bandwidth consumption.An earlier version of this paper appeared in Proceedings of ACM Multimedia, 1999, pp. 141–144.     

Combinatorial considerations for switching systems carrying multi-channel traffic streams

This paper presents a combinatorial analysis of limited-availability groups to which the mixture of different multi-channel traffic streams is offered. The availability distributions of an exactly determined number of subgroups has been derived for traffic streams of various classes. The determined distributions enable calculation of blocking probabilities in multi-stage switching networks carrying different multi-channel traffic streams by the effective availability method. The paper defines the components of effective availability and gives procedures for their determination in the case of multi-channel traffic. In this paper, two calculation methods are derived, one used for point-to-point selection, and the other for point-to-group selection. The results of analytical calculations are compared with the results of digital simulation of three-stage switching networks. The proposed formulae can be used in the analysis of isdn and ?-isdn systems.