Online variable-bit-rate video traffic smoothing

Guohong Cao, Wu Chi Feng, Mukesh Singhal

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The efficient transmission of variable-bit-rate (VBR) video streams is complicated by the burstiness that video compression standards such as MPEG introduce. Most of the existing techniques concentrate on stored video traffic smoothing or real-time video traffic smoothing. However, there is a growing number of live video applications, such as video-casts of courses or television news, where many clients may be willing to tolerate a playback delay of several seconds or minutes in exchange for a smaller throughput requirement. Bandwidth smoothing for these live video applications is referred to as online smoothing. In this paper, in order to measure the effectiveness of online video smoothing methods, we propose a benchmark algorithm, which provides an upper bound on some of the performance metrics in the smoothing results. Based on this algorithm, we found that significant discrepancy exists between the results produced by the existing online smoothing methods and the upper bound. With this observation, we focus on designing algorithms that can improve the smoothing results. Experimental results show that the proposed algorithms make considerable improvements compared to existing smoothing methods.

Original languageEnglish (US)
Pages (from-to)639-651
Number of pages13
JournalComputer Communications
Volume26
Issue number7
DOIs
StatePublished - May 1 2003

Fingerprint

Image compression
Television
Throughput
Bandwidth

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Cao, Guohong ; Feng, Wu Chi ; Singhal, Mukesh. / Online variable-bit-rate video traffic smoothing. In: Computer Communications. 2003 ; Vol. 26, No. 7. pp. 639-651.
@article{5b498f76b6a744feb1fc56ab8fb5baa3,
title = "Online variable-bit-rate video traffic smoothing",
abstract = "The efficient transmission of variable-bit-rate (VBR) video streams is complicated by the burstiness that video compression standards such as MPEG introduce. Most of the existing techniques concentrate on stored video traffic smoothing or real-time video traffic smoothing. However, there is a growing number of live video applications, such as video-casts of courses or television news, where many clients may be willing to tolerate a playback delay of several seconds or minutes in exchange for a smaller throughput requirement. Bandwidth smoothing for these live video applications is referred to as online smoothing. In this paper, in order to measure the effectiveness of online video smoothing methods, we propose a benchmark algorithm, which provides an upper bound on some of the performance metrics in the smoothing results. Based on this algorithm, we found that significant discrepancy exists between the results produced by the existing online smoothing methods and the upper bound. With this observation, we focus on designing algorithms that can improve the smoothing results. Experimental results show that the proposed algorithms make considerable improvements compared to existing smoothing methods.",
author = "Guohong Cao and Feng, {Wu Chi} and Mukesh Singhal",
year = "2003",
month = "5",
day = "1",
doi = "10.1016/S0140-3664(02)00197-4",
language = "English (US)",
volume = "26",
pages = "639--651",
journal = "Computer Communications",
issn = "0140-3664",
publisher = "Elsevier",
number = "7",

}

Online variable-bit-rate video traffic smoothing. / Cao, Guohong; Feng, Wu Chi; Singhal, Mukesh.

In: Computer Communications, Vol. 26, No. 7, 01.05.2003, p. 639-651.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online variable-bit-rate video traffic smoothing

AU - Cao, Guohong

AU - Feng, Wu Chi

AU - Singhal, Mukesh

PY - 2003/5/1

Y1 - 2003/5/1

N2 - The efficient transmission of variable-bit-rate (VBR) video streams is complicated by the burstiness that video compression standards such as MPEG introduce. Most of the existing techniques concentrate on stored video traffic smoothing or real-time video traffic smoothing. However, there is a growing number of live video applications, such as video-casts of courses or television news, where many clients may be willing to tolerate a playback delay of several seconds or minutes in exchange for a smaller throughput requirement. Bandwidth smoothing for these live video applications is referred to as online smoothing. In this paper, in order to measure the effectiveness of online video smoothing methods, we propose a benchmark algorithm, which provides an upper bound on some of the performance metrics in the smoothing results. Based on this algorithm, we found that significant discrepancy exists between the results produced by the existing online smoothing methods and the upper bound. With this observation, we focus on designing algorithms that can improve the smoothing results. Experimental results show that the proposed algorithms make considerable improvements compared to existing smoothing methods.

AB - The efficient transmission of variable-bit-rate (VBR) video streams is complicated by the burstiness that video compression standards such as MPEG introduce. Most of the existing techniques concentrate on stored video traffic smoothing or real-time video traffic smoothing. However, there is a growing number of live video applications, such as video-casts of courses or television news, where many clients may be willing to tolerate a playback delay of several seconds or minutes in exchange for a smaller throughput requirement. Bandwidth smoothing for these live video applications is referred to as online smoothing. In this paper, in order to measure the effectiveness of online video smoothing methods, we propose a benchmark algorithm, which provides an upper bound on some of the performance metrics in the smoothing results. Based on this algorithm, we found that significant discrepancy exists between the results produced by the existing online smoothing methods and the upper bound. With this observation, we focus on designing algorithms that can improve the smoothing results. Experimental results show that the proposed algorithms make considerable improvements compared to existing smoothing methods.

UR - http://www.scopus.com/inward/record.url?scp=0037400857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037400857&partnerID=8YFLogxK

U2 - 10.1016/S0140-3664(02)00197-4

DO - 10.1016/S0140-3664(02)00197-4

M3 - Article

AN - SCOPUS:0037400857

VL - 26

SP - 639

EP - 651

JO - Computer Communications

JF - Computer Communications

SN - 0140-3664

IS - 7

ER -