LBA: Location and Bandwidth Awareness overlay for P2P live video streaming

Kai Zhang*, Kan Li

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Peer-to-peer streaming technology using mesh-based overlay has emerged as a promising scalable solution for live video streaming. However, the mechanism of nodes randomly selecting neighbors without considering peer location and bandwidth can cause a serious video diffusion delay which is undesirable. In this paper, we propose a Location and Bandwidth Awareness (LBA) overlay scheme aiming to achieve low delay. We make use of the concept of Location and Bandwidth (LB) balance which regulates the ratio of nearby neighbors and high bandwidth neighbors and give LB balance model. Each peer must obey LB balance so that the peers are organized into a hierarchy. In order to construct LBA overlay, we present a centralized algorithm which peers select their proper neighbors based on the LB balance. Simulation shows that our LBA overlay can achieve desirable performance, and substantially outperforms traditional and state-of-the-art approaches.

Original languageEnglish
Title of host publication2010 International Conference on Networking and Digital Society, ICNDS 2010
Pages327-330
Number of pages4
DOIs
Publication statusPublished - 2010
Event2nd International Conference on Networking and Digital Society, lCNDS 2010 - Wenzhou, China
Duration: 30 May 201031 May 2010

Publication series

Name2010 International Conference on Networking and Digital Society, ICNDS 2010
Volume2

Conference

Conference2nd International Conference on Networking and Digital Society, lCNDS 2010
Country/TerritoryChina
CityWenzhou
Period30/05/1031/05/10

Keywords

  • Balance
  • Diffusion delay
  • Location and bandwidth awareness
  • Peer to peer streaming

Fingerprint

Dive into the research topics of 'LBA: Location and Bandwidth Awareness overlay for P2P live video streaming'. Together they form a unique fingerprint.

Cite this