• DocumentCode
    3569722
  • Title

    A fuzzy dynamic bandwidth re-allocator

  • Author

    Slonowsky, Dean ; Jiang, Qingshan ; Srinivasan, Raj

  • Author_Institution
    Dept. of Stat., Manitoba Univ., Winnipeg, Man., Canada
  • Volume
    2
  • fYear
    2002
  • fDate
    6/24/1905 12:00:00 AM
  • Firstpage
    815
  • Abstract
    A high-speed network typically assigns each admitted connection a fixed bandwidth, somewhere between its mean and peak transmission rate. As an alternative, we develop a novel scheme for re-assigning network resources periodically on the basis of current network conditions. Our algorithm, which employs the theory of fuzzy logic control, is computationally efficient, making frequent bandwidth re-allocations over relatively small time intervals feasible. In situations where traffic intensities change drastically over short time intervals, our algorithm, tested against both static and non-fuzzy bandwidth re-allocation schemes, significantly lowers data loss while increasing network efficiency.
  • Keywords
    fuzzy control; resource allocation; telecommunication control; telecommunication networks; telecommunication traffic; bandwidth allocation; data loss; dynamic bandwidth re-allocator; fuzzy logic control; network conditions; network efficiency; network resource assignment; Bandwidth; Communication system traffic control; Data mining; Distributed Bragg reflectors; Fuzzy logic; High-speed networks; Mathematics; Mining industry; Statistics; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on
  • ISSN
    0840-7789
  • Print_ISBN
    0-7803-7514-9
  • Type

    conf

  • DOI
    10.1109/CCECE.2002.1013047
  • Filename
    1013047