Demands for service at a public facility during some unit time are assumed to be independent, normally distributed random variables, with a parabolic mean function of time and constant variance. With the model used, consecutive m-minute demands starting each minute form a non-stationary process, whose mean and covariance functions of time depend on M and on the four other parameters of the distribution function of the unit time demand. Empirical joint distribution functions for the maximum m-minute demand (M = 1,5) and the total demand for a longer period of time n (n/m = 3, 5, 9) were obtained by computer simulation of this process for various values of the parameters corresponding to a wide range of practical situations. The results indicate that counts for both nonoverlapping short time demands and overlapping longer time demands are needed to relate fluctuations in demand to capacity. Also, the choice of the length of observation for the average demand is not very consequential for the variance of the observed ratio of the maximum fluctuations to the average demand or the variance of its difference with the appropriate fraction of the average, although the former tends to be smaller for longer observations of the maximum demand. (A). /TRRL/

  • Corporate Authors:

    Pergamon Press, Incorporated

    Maxwell House, Fairview Park
    Elmsford, NY  United States  10523
  • Authors:
    • Oppenheim, N
  • Publication Date: 1977-2


  • English

Media Info

  • Features: References; Tables;
  • Pagination: p. 33-37
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 00164253
  • Record Type: Publication
  • Source Agency: Transport and Road Research Laboratory (TRRL)
  • Report/Paper Numbers: Analytic
  • Files: ITRD, TRIS
  • Created Date: Jan 30 1978 12:00AM