• DocumentCode
    480025
  • Title

    Dependability Research of Cluster System Based on Stochastic Petri Net

  • Author

    Shixi, Liu ; Zhicai, Xu ; Xianwen, Fang

  • Author_Institution
    Comput. Sci. & Technol. Dept., Chuzhou Univ., Chuzhou
  • Volume
    3
  • fYear
    2008
  • fDate
    12-14 Dec. 2008
  • Firstpage
    481
  • Lastpage
    485
  • Abstract
    Cluster system has become infrastructure, which constructs high performance distributed systems. The quality of service (QoS) that offers for users will be affected by dependability at large. Stochastic Petri nets (SPN) is a kind of flexible modeling tool, and it has established matured theory system on the research of dependability. The SPN is taken advantage of to model front-end dispatcher and backend workers respectively, and the SPN model of the whole cluster system is presented. It has taken the repairing assurance into consideration when modeling cluster system. Based on the model analyzing, different dependable parameters of the cluster system are given out, and then the model is simulated. The simulation results show that the dependability of cluster system model will increase largely after the key system front-end dispatcher has been given necessary repairing assurance.
  • Keywords
    Petri nets; distributed processing; quality of service; stochastic processes; workstation clusters; backend workers; cluster system; dependability research; high performance distributed systems; key system front-end dispatcher; matured theory system; model front-end dispatcher; quality of service; repairing assurance; stochastic Petri net; Computer bugs; Computer science; Distributed computing; Quality of service; Software engineering; State-space methods; Stochastic processes; Stochastic systems; Switches; Time sharing computer systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Software Engineering, 2008 International Conference on
  • Conference_Location
    Wuhan, Hubei
  • Print_ISBN
    978-0-7695-3336-0
  • Type

    conf

  • DOI
    10.1109/CSSE.2008.238
  • Filename
    4722388