• DocumentCode
    1873691
  • Title

    Enhancing peer-to-peer live multicast quality using helpers

  • Author

    Wang, Jiajun ; Ramchandran, Kannan

  • Author_Institution
    Dept. of EECS, Univ. of California, Berkeley, CA
  • fYear
    2008
  • fDate
    12-15 Oct. 2008
  • Firstpage
    2300
  • Lastpage
    2303
  • Abstract
    Peer-to-peer (P2P) video streaming over the Internet plays an important role in reshaping today\´s Internet traffic. The performance of a P2P system is typically bottlenecked by the limited upload bandwidth of the participating peers, which typically have asymmetric upload/download bandwidth connections to the Internet. Increasing the streaming bitrate in P2P systems beyond what is sustainable with participating peers\´ upload bandwidths therefore places extra burden on the content server, clearly not a desirable solution in terms of scalability. Motivated by this, we explore here an alternative architecture based on the notion of "helpers", who are online users with spare upload capacity. We show how efficient utilization of helpers\´ spare upload capacity can lead to significantly improved streaming bitrate in a P2P network without incurring additional server burden. For instance, a 2000 node P2P system with an average upload bandwidth of 512 kbps can sustain streaming rate of 512 kbps with very little server usage. But with an additional 533 helpers, the system can stream at 640 kbps without incurring any additional server load.
  • Keywords
    Internet; peer-to-peer computing; telecommunication traffic; video streaming; Internet traffic; P2P network; asymmetric upload/download bandwidth; average upload bandwidth; enhancing peer-to-peer live multicast quality; peer-to-peer video streaming; upload capacity; Bandwidth; Bit rate; Multimedia communication; Network servers; Peer to peer computing; Protocols; Scalability; Streaming media; Web and internet services; Web server; Communication systems; broadcasting; protocols;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
  • Conference_Location
    San Diego, CA
  • ISSN
    1522-4880
  • Print_ISBN
    978-1-4244-1765-0
  • Electronic_ISBN
    1522-4880
  • Type

    conf

  • DOI
    10.1109/ICIP.2008.4712251
  • Filename
    4712251