Performance models of statistical multiplexing in packet video communications

Maglaris, Vasilis; Anastassiou, Dimitris; Sen, P. K.; Karlsson, Gunnar; Robbins, J. D.

doi:10.1109/26.2812

Cited by 888 publications

(294 citation statements)

References 11 publications

Supporting

Mentioning

280

Contrasting

Unclassified

Order By: Relevance

“…We also observe that with the increasing of p parameter the overall structure of generated data has a strong "smoothing" trend. This trend results from strong positive correlation of GBAR process and may offer several potential applications in traffic modeling of multiplexed streams [9]. Further, the autocorrelation function is a subject of our attention.…”

Section: Modeling Resultsmentioning

confidence: 86%

“…A huge amount of videotraffic models were based on Markov chains which are parameterized by a limited set of parameters [7,9,10]. These models try to capture the empirical distribution of frame sizes and autocorrelation function up to several lags.…”

Section: Introductionmentioning

confidence: 99%

“…Basically, these studies are dedicated to analyze and to model the frame streams of H.261, DPCM, CR compression algorithms, and MPEG traffic at the GoP (Group of Pictures) level [1,8,9,10]. MPEG frames sequences may have sophisticated GoP structure at the output of the codec.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Two-Step MPEG Traffic Modeling Algorithm Based on a GBAR Process

Koucheryavy

Moltchanov

Harju

2003

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract:In this paper we propose a two-step MPEG video sources modeling algorithm based on three auto-and cross-correlated gamma-beta autoregressive processes of order one GBAR(1). This algorithm is an extension of models originally proposed by Heyman [1] and Lombardo et al. [2]. We extend the model proposed by Heyman to the case of periodic frame sequence at the output of the codec. In order to do that we use information about the correlation between frame sizes within the group of pictures. Based on this information we introduce three cross-correlated GBAR(1) processes each of which models a particular type of the frame. The proposed algorithm captures the basic statistical characteristics of the empirical data well: the distribution of frame sizes and the autocorrelation function. Our algorithm is fairly simple computationally efficient and therefore, can be used in simulation studies.

show abstract

Section: Modeling Resultsmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Two-Step MPEG Traffic Modeling Algorithm Based on a GBAR Process

Koucheryavy

Moltchanov

Harju

2003

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…We consider three scenarios for the N traffic sources: a) all sources are VoIP sources with peak rate 64kbps and exponentially distributed ON and OFF periods with average durations 1.004sec and 1.587sec respectively (mean rate 24.8kbps, standard deviation of rate 31.18kbps) [15], b) all sources are Videoconference sources with mean rate 3.89Mbps, peak rate 10.585Mbps and standard deviation of rate 1.725Mbps [16], and c) that we have a mixture of both VoIP and Videoconference sources. We fix the packet size to 100bytes (constant packet size seems to be a reasonable assumption for Voice and Video communications [17]) and since the realtime traffic class is assumed to be isolated from other classes, we do not consider any best-effort or any other traffic classes and we simulate the real-time traffic class as being serviced by queues running at the speed of their bandwidth limit.…”

Section: Fig 1 Topology For Assessing the Effects Of Topological Plmentioning

confidence: 99%

On the Location-Awareness of Bandwidth Allocation and Admission Control for the Support of Real-Time Traffic in Class-Based IP Networks

Georgoulas

Trimintzios

Pavlou

et al. 2006

Autonomic Management of Mobile Multimedia Services

View full text Add to dashboard Cite

Abstract. The support of real-time traffic in class-based IP networks requires reservation of resources, accompanied by admission control in order to guarantee that newly admitted real-time traffic flows do not cause any violation to the Quality of Service (QoS) perceived by the already established ones. In this paper we highlight certain issues with respect to bandwidth allocation and admission control for supporting real-time traffic in class-based IP networks. We investigate the implications of topological placement of both bandwidth allocation and admission control schemes. We show that their performance depends highly on the location of the employed procedures with respect to the end-users and the various network boundaries. We conclude that the strategies for applying these schemes should be location-aware, because their performance at different points in a class-based IP network can be different and can deviate from the expected performance. Through simulations we also provide a quantitative view of these deviations.

show abstract

“…On the other hand, multiple thresholds are implemented in each queue, respectively, for packet loss priority control [7]. The performance analysis is done using¯uid¯ow technique [10,11]. The evaluation focuses on the performance tradeoff between the delay sensitive traf®c and delay insensitive traf®c in terms of traf®c throughput, packet loss probability and end-to-end delay in VPN networks are also presented.…”

Section: Introductionmentioning

confidence: 99%

Modeling and performance analysis for IPv6 traffic with multiple QoS classes

Zhang

Zheng

2001

Computer Communications

View full text Add to dashboard Cite

This paper focuses on the modeling and performance analysis for IPv6 traf®c with multi-class QoS in virtual private networks (VPN). The multi-class QoS is implemented on differentiated service basis using priority scheme of 4 bits de®ned in the packet header of IPv6. A VPNenabled IP router is modeled as a tandem queuing system in which each output link consists of two parallel priority output queues. The highpriority queue is used to carry the delay sensitive traf®c while the low-priority queue is used to carry the delay insensitive traf®c. On the other hand, multiple thresholds are implemented in each queue, respectively, for packet loss priority control. The performance analysis is done using¯uid¯ow techniques. The numerical results obtained from the analysis show that the differentiated service based on the priority schemes de®ned in IPv6 is able to effectively satisfy the multi-class QoS requirement for supporting multimedia services in VPN. The performance trade-off between the delay sensitive traf®c and delay insensitive traf®c in terms of traf®c throughput, packet loss probability and end-to-end delay in VPN networks is presented. q

show abstract

Performance models of statistical multiplexing in packet video communications

Cited by 888 publications

References 11 publications

A Novel Two-Step MPEG Traffic Modeling Algorithm Based on a GBAR Process

A Novel Two-Step MPEG Traffic Modeling Algorithm Based on a GBAR Process

On the Location-Awareness of Bandwidth Allocation and Admission Control for the Support of Real-Time Traffic in Class-Based IP Networks

Modeling and performance analysis for IPv6 traffic with multiple QoS classes

Contact Info

Product

Resources

About