Parallel video streaming optimizing network throughput

Noriaki Kamiyama, Ryoichi Kawahara, Tatsuya Mori, Shigeaki Harada, Haruhisa Hasegawa

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In the Internet, video streaming services, in which users can enjoy videos at home, are becoming popular. Video streaming with high definition TV (HDTV) or ultra high definition video (UHDV) quality will be also provided and widely demanded in the future. However, the transmission bit-rate of high-quality video streaming is quite large, so generated traffic flows will cause link congestion. In the Internet, routes that packets take are determined using static link weights, so the network productivity, i.e., the maximum achievable throughout by the network, is determined by the capacity of a bottleneck link with the maximum utilization, although utilizations of many links remain low level. Therefore, when providing streaming services of rich content, i.e., videos with HDTV or UHDV quality, it is important to flatten the link utilization, i.e., reduce the maximum link utilization. We propose that ISPs use multiple servers to deliver rich content to balance the link utilization and propose server allocation and server selection methods for parallel delivery. We evaluate the effect of parallel delivery using 23 actual commercial ISP networks.

Original languageEnglish
Pages (from-to)1182-1194
Number of pages13
JournalComputer Communications
Volume34
Issue number10
DOIs
Publication statusPublished - 2011 Jul 1
Externally publishedYes

Fingerprint

Video streaming
Servers
Throughput
Internet
Telecommunication traffic
Telecommunication links
Productivity

Keywords

  • Link utilization
  • Network topology
  • Parallel delivery
  • Video streaming

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Parallel video streaming optimizing network throughput. / Kamiyama, Noriaki; Kawahara, Ryoichi; Mori, Tatsuya; Harada, Shigeaki; Hasegawa, Haruhisa.

In: Computer Communications, Vol. 34, No. 10, 01.07.2011, p. 1182-1194.

Research output: Contribution to journalArticle

Kamiyama, N, Kawahara, R, Mori, T, Harada, S & Hasegawa, H 2011, 'Parallel video streaming optimizing network throughput', Computer Communications, vol. 34, no. 10, pp. 1182-1194. https://doi.org/10.1016/j.comcom.2010.12.003
Kamiyama, Noriaki ; Kawahara, Ryoichi ; Mori, Tatsuya ; Harada, Shigeaki ; Hasegawa, Haruhisa. / Parallel video streaming optimizing network throughput. In: Computer Communications. 2011 ; Vol. 34, No. 10. pp. 1182-1194.
@article{4be44d301eb1454eb814a4277396b497,
title = "Parallel video streaming optimizing network throughput",
abstract = "In the Internet, video streaming services, in which users can enjoy videos at home, are becoming popular. Video streaming with high definition TV (HDTV) or ultra high definition video (UHDV) quality will be also provided and widely demanded in the future. However, the transmission bit-rate of high-quality video streaming is quite large, so generated traffic flows will cause link congestion. In the Internet, routes that packets take are determined using static link weights, so the network productivity, i.e., the maximum achievable throughout by the network, is determined by the capacity of a bottleneck link with the maximum utilization, although utilizations of many links remain low level. Therefore, when providing streaming services of rich content, i.e., videos with HDTV or UHDV quality, it is important to flatten the link utilization, i.e., reduce the maximum link utilization. We propose that ISPs use multiple servers to deliver rich content to balance the link utilization and propose server allocation and server selection methods for parallel delivery. We evaluate the effect of parallel delivery using 23 actual commercial ISP networks.",
keywords = "Link utilization, Network topology, Parallel delivery, Video streaming",
author = "Noriaki Kamiyama and Ryoichi Kawahara and Tatsuya Mori and Shigeaki Harada and Haruhisa Hasegawa",
year = "2011",
month = "7",
day = "1",
doi = "10.1016/j.comcom.2010.12.003",
language = "English",
volume = "34",
pages = "1182--1194",
journal = "Computer Communications",
issn = "0140-3664",
publisher = "Elsevier",
number = "10",

}

TY - JOUR

T1 - Parallel video streaming optimizing network throughput

AU - Kamiyama, Noriaki

AU - Kawahara, Ryoichi

AU - Mori, Tatsuya

AU - Harada, Shigeaki

AU - Hasegawa, Haruhisa

PY - 2011/7/1

Y1 - 2011/7/1

N2 - In the Internet, video streaming services, in which users can enjoy videos at home, are becoming popular. Video streaming with high definition TV (HDTV) or ultra high definition video (UHDV) quality will be also provided and widely demanded in the future. However, the transmission bit-rate of high-quality video streaming is quite large, so generated traffic flows will cause link congestion. In the Internet, routes that packets take are determined using static link weights, so the network productivity, i.e., the maximum achievable throughout by the network, is determined by the capacity of a bottleneck link with the maximum utilization, although utilizations of many links remain low level. Therefore, when providing streaming services of rich content, i.e., videos with HDTV or UHDV quality, it is important to flatten the link utilization, i.e., reduce the maximum link utilization. We propose that ISPs use multiple servers to deliver rich content to balance the link utilization and propose server allocation and server selection methods for parallel delivery. We evaluate the effect of parallel delivery using 23 actual commercial ISP networks.

AB - In the Internet, video streaming services, in which users can enjoy videos at home, are becoming popular. Video streaming with high definition TV (HDTV) or ultra high definition video (UHDV) quality will be also provided and widely demanded in the future. However, the transmission bit-rate of high-quality video streaming is quite large, so generated traffic flows will cause link congestion. In the Internet, routes that packets take are determined using static link weights, so the network productivity, i.e., the maximum achievable throughout by the network, is determined by the capacity of a bottleneck link with the maximum utilization, although utilizations of many links remain low level. Therefore, when providing streaming services of rich content, i.e., videos with HDTV or UHDV quality, it is important to flatten the link utilization, i.e., reduce the maximum link utilization. We propose that ISPs use multiple servers to deliver rich content to balance the link utilization and propose server allocation and server selection methods for parallel delivery. We evaluate the effect of parallel delivery using 23 actual commercial ISP networks.

KW - Link utilization

KW - Network topology

KW - Parallel delivery

KW - Video streaming

UR - http://www.scopus.com/inward/record.url?scp=79955737137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955737137&partnerID=8YFLogxK

U2 - 10.1016/j.comcom.2010.12.003

DO - 10.1016/j.comcom.2010.12.003

M3 - Article

AN - SCOPUS:79955737137

VL - 34

SP - 1182

EP - 1194

JO - Computer Communications

JF - Computer Communications

SN - 0140-3664

IS - 10

ER -