• DocumentCode
    1269913
  • Title

    Asymptotic properties of queuing networks

  • Author

    Coury, S. ; Harrison, P.G.

  • Author_Institution
    Dept. of Comput., Imperial Coll. of Sci., Technol. & Med., London, UK
  • Volume
    144
  • Issue
    5
  • fYear
    1997
  • fDate
    9/1/1997 12:00:00 AM
  • Firstpage
    249
  • Lastpage
    254
  • Abstract
    A new approach to the analysis of asymptotic properties of closed queuing networks with both constant service rates and, in certain cases, load-dependent service rates is developed. The method is based on a decomposition of the generating function of the normalising constant into simpler node functions which are easily inverted term by term. An exact closed form is obtained for the normalising constant in some cases and an approximation, based on an integral formula, in others. These results are applied to model a large computer system with terminals, which is also used to illustrate the main properties of the normalising constant and the system throughput function as the population increases. The authors´ method is compared with others in terms of both accuracy and efficiency. Finally, it is indicated how multi-class networks can be handled, essentially by reduction to a collection of single-class networks
  • Keywords
    Markov processes; computer networks; functions; interactive terminals; queueing theory; switching theory; accuracy; approximation; asymptotic properties; closed queuing networks; computer system modelling; computer terminals; constant service rates; efficiency; exact closed form; generating function decomposition; integral formula; load-dependent service rates; multi-class network reduction; network modelling; node function inversion; normalising constant; single-class networks; stochastic networks; system throughput function;
  • fLanguage
    English
  • Journal_Title
    Computers and Digital Techniques, IEE Proceedings -
  • Publisher
    iet
  • ISSN
    1350-2387
  • Type

    jour

  • DOI
    10.1049/ip-cdt:19971285
  • Filename
    627901