• DocumentCode
    2739542
  • Title

    Cluster Based Peers Configuration Using HCNP in Peer-to-Peer Overlay Networks

  • Author

    Kazmi, Irum ; Aslam, Saira ; Javed, M.Y.

  • Author_Institution
    Dept. of Comput. Eng., NUST, Rawalpindi, Pakistan
  • fYear
    2010
  • fDate
    28-30 July 2010
  • Firstpage
    158
  • Lastpage
    163
  • Abstract
    The paper addresses the need of efficient collaboration of peers with different levels of heterogeneity in order to share resources in p2p overlay networks. Here the heterogeneity reflects differences in peers physical resources like free storage space, processor speed etc. A non-hierarchical cluster-based approach has been introduced to make the network comprising of heterogeneous nodes, more efficient and scalable. NP (newscast protocol) has been used to generate the nodes (peers) randomly in the network, where nodes also maintain the properties of its neighboring nodes in a cache associated to each node. NP has proved to be the most efficient protocol to maintain the current state of the network. In this paper a heterogeneous cluster-based NP (HCNP) has been introduced, which, not only preserves the properties of NP, but also configures clusters on the basis of changes in physical parameters of the node at any particular time instant.
  • Keywords
    peer-to-peer computing; protocols; workstation clusters; HCNP; cluster based peers configuration; heterogeneous based newscast protocol; nonhierarchical cluster-based approach; peer-to-peer overlay networks; peers physical resources; Accuracy; Clustering algorithms; Data structures; Network topology; Peer to peer computing; Protocols; Topology; Capability Level; Cluster Identifier; Heterogeneity; Newscast Protocol; Physical Parameters;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence, Communication Systems and Networks (CICSyN), 2010 Second International Conference on
  • Conference_Location
    Liverpool
  • Print_ISBN
    978-1-4244-7837-8
  • Electronic_ISBN
    978-0-7695-4158-7
  • Type

    conf

  • DOI
    10.1109/CICSyN.2010.30
  • Filename
    5614578