• DocumentCode
    3140832
  • Title

    Adaptive client side object replication for response time improvement in pervasive environments

  • Author

    Katmon, Norizam ; Ryan, Caspar

  • Author_Institution
    Sch. of Comput. Sci., RMIT Univ., Melbourne, VIC, Australia
  • fYear
    2011
  • fDate
    21-25 March 2011
  • Firstpage
    164
  • Lastpage
    171
  • Abstract
    Due to the high cost of replication, incurred mainly by consistency management, it may be infeasible to use uninformed object replication in collaborative applications in pervasive environments, since resources are constrained, nodes are heterogeneous, and application behaviour is highly dynamic. Consequently, this paper proposes an adaptive replication scheme that dynamically creates and releases replicas on client nodes during runtime, with the objective of improving response time performance. This is based on both the runtime information of the execution environments, and application behaviours of both client and server nodes. The adaptive replication algorithm is simulated with resource utilisation and response times compared to no replication and full replication schemes. Results show that the adaptive scheme is able to improve response time in a greater range of execution contexts than either no or full replication, while introducing less synchronisation overhead than the full replication scheme.
  • Keywords
    resource allocation; ubiquitous computing; adaptive client side object replication; adaptive replication scheme; client node; pervasive environment; resource utilization; response time improvement; server node; Adaptation model; Collaboration; Context; Servers; Synchronization; Time factors; Adaptation; Context-Awareness; Cost-Benefit; Object Replication; Resource Utilisation; Response Time;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pervasive Computing and Communications (PerCom), 2011 IEEE International Conference on
  • Conference_Location
    Seattle, WA
  • Print_ISBN
    978-1-4244-9530-6
  • Electronic_ISBN
    978-1-4244-9528-3
  • Type

    conf

  • DOI
    10.1109/PERCOM.2011.5767581
  • Filename
    5767581