• DocumentCode
    3409680
  • Title

    Network availability prediction: Can it be done?

  • Author

    Seneviratne, Aruna ; Pedrasa, Jhoanna Rhodette ; Rathnayake, Upendra

  • Author_Institution
    Nat. ICT Australia, Sydney, NSW, Australia
  • fYear
    2011
  • fDate
    4-6 Aug. 2011
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    With the availability of more powerful mobile devices and a variety of access networks, users are expecting more and more services whilst on the move. There have been many attempts develop methods of providing these types of services form a user as well as a service provider perspective. All of these methods are based on the ability to predict the future. In this paper, will first present an overview of the research on one aspect of this, namely network availability prediction. We first, summarise the work that has been done in network availability prediction and categorize them. Using the categorisation, we show that one of the existing mechanisms provide the necessary accuracy and robustness. Then we present a hybrid design which overcome the limitations of the current systems. We show the viability of the the proposed hybrid system by summarising a dynamic Bayesian network and report exchange based predication mechanisms. We conclude the paper with a brief discussion on the open issues of developing such a hybrid scheme.
  • Keywords
    belief networks; mobile radio; subscriber loops; access networks; dynamic Bayesian network; hybrid design; network availability prediction; powerful mobile devices; service provider perspective; Availability; Current measurement; IEEE 802.11 Standards; Mobile communication; Peer to peer computing; Throughput; Wireless networks;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Global Information Infrastructure Symposium (GIIS), 2011
  • Conference_Location
    Da Nang
  • Print_ISBN
    978-1-4577-1262-3
  • Electronic_ISBN
    978-1-4577-1260-9
  • Type

    conf

  • DOI
    10.1109/GIIS.2011.6026700
  • Filename
    6026700