An efficient caching scheme for on-demand streaming service on overlay networks

Hui Guo, Kwok Tung Lo, Jiang Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

3 Citations (Scopus)

Abstract

Recently, peer-to-peer (P2P) overlay networks have become popular and many P2P applications such as file sharing and content distribution have been introduced. Naturally, P2P cooperative caching schemes for streaming were introduced. However, these approaches manifest inefficiency of cache utilization due to inappropriate cache replacement algorithms, and no consideration of dynamic membership changes of peer nodes. In this paper, we investigate an efficient cooperative caching mechanism for VOD streaming service over P2P overlay networks. The target of the system is to provide low-latency and high-quality services by virtue of pees' collaboration. The storage and replacement of caching content are based on segment-based strategy. And a utility-based fine-grained cooperative cache (DUFQ policy was proposed for cache replacement. We demonstrate the effectiveness of the proposed scheme and compare with traditional LRUF scheme through extensive simulation experiments over large, Internet-like topologies.
Original languageEnglish
Title of host publication2007 4th Annual IEEE Consumer Communications and Networking Conference, CCNC 2007
Pages322-326
Number of pages5
DOIs
Publication statusPublished - 27 Nov 2007
Event2007 4th Annual IEEE Consumer Communications and Networking Conference, CCNC 2007 - Las Vegas, NV, United States
Duration: 11 Jan 200713 Jan 2007

Conference

Conference2007 4th Annual IEEE Consumer Communications and Networking Conference, CCNC 2007
CountryUnited States
CityLas Vegas, NV
Period11/01/0713/01/07

Keywords

  • Cooperative caching
  • Peer to peer networks
  • Segment-based caching
  • Video on demand

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this