• DocumentCode
    2042620
  • Title

    Bandwidth Provisioning in Internet Access Nodes Using EWMA and ADM Algorithms

  • Author

    Inaty, Elie ; Sleiman, Marwan

  • Author_Institution
    Dept. of Comput. Eng., Univ. of Balamand, Lebanon
  • fYear
    2007
  • fDate
    24-27 Nov. 2007
  • Firstpage
    528
  • Lastpage
    531
  • Abstract
    Nowadays there is a tremendous debate about the treatment required for managing the heavily loaded and expanding traffic demands. Building a universal communication system is extremely challenging, given the lack of scalable communication technologies. Researchers have recently been seeking for solutions and expansions for the existing networking models; they have been focusing on optimizing the use of available resources like bandwidth and hardware. In this paper, we studied Internet bandwidth provisioning in Internet access nodes. We gathered Internet traffic and then we use the exponentially weighted moving average (EWMA) and the adaptive dynamic model (ADM) algorithms to predict the traffic bandwidth. Using real Internet traffic, we have shown that the EWMA algorithm is better that the ADM algorithm in provisioning of bandwidth in Internet access nodes.
  • Keywords
    Internet; bandwidth allocation; moving average processes; telecommunication traffic; ADM algorithms; EWMA algorithms; Internet access nodes; Internet traffic; adaptive dynamic model algorithms; bandwidth provisioning; exponentially weighted moving average algorithms; universal communication system; Bandwidth; Communication system traffic; Communications technology; Hardware; Heuristic algorithms; Internet; Prediction algorithms; Predictive models; Telecommunication traffic; Traffic control; ADM; EWMA; Internet traffic; dynamic bandwidth provisioning; internet pricing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Communications, 2007. ICSPC 2007. IEEE International Conference on
  • Conference_Location
    Dubai
  • Print_ISBN
    978-1-4244-1235-8
  • Electronic_ISBN
    978-1-4244-1236-5
  • Type

    conf

  • DOI
    10.1109/ICSPC.2007.4728372
  • Filename
    4728372