• DocumentCode
    2497889
  • Title

    Biologically-Inspired Design of Autonomous and Adaptive Grid Services

  • Author

    Lee, Chonho ; Suzuki, Junichi

  • Author_Institution
    Dept. of Comput. Sci., Massachusetts Univ., Boston, MA
  • fYear
    2006
  • fDate
    16-18 July 2006
  • Firstpage
    20
  • Lastpage
    20
  • Abstract
    This paper describes and evaluates a biologically-inspired network architecture that allows grid services to autonomously adapt to dynamic environment changes in the network. Based on the observation that the immune system has elegantly achieved autonomous adaptation, the proposed mechanism, the iNet artificial immune system, is designed after the mechanisms behind how the immune system detects antigens (e.g., viruses) and specifically reacts to them. iNet models a set of environment conditions (e.g., network traffic and resource availability) as an antigen and a behavior of grid services (e.g., migration and replication) as an antibody. iNet allows each grid service to autonomously sense its surrounding environment conditions (an antigen) to evaluate whether it adapts well to the sensed conditions, and if it does not, adaptively perform a behavior (an antibody) suitable for the sensed conditions. Simulation results show that iNet allows grid services to autonomously adapt their population and location to environmental changes for improving their performance (e.g., response time and throughput) and balancing workload
  • Keywords
    artificial intelligence; genetic algorithms; grid computing; adaptive grid services; autonomous grid services; biologically-inspired design; biologically-inspired network architecture; iNet artificial immune system; Application software; Availability; Computer architecture; Delay; Immune system; Performance evaluation; Telecommunication traffic; Throughput; Traffic control; Viruses (medical);
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Autonomic and Autonomous Systems, 2006. ICAS '06. 2006 International Conference on
  • Conference_Location
    Silicon Valley, CA
  • Print_ISBN
    0-7695-2653-5
  • Type

    conf

  • DOI
    10.1109/ICAS.2006.15
  • Filename
    1690230