Premium
Interval estimation of mean response time for a G/M/1 queueing system: empirical Laplace function approach
Author(s) -
Chu YunnKuang,
Ke JauChuan
Publication year - 2007
Publication title -
mathematical methods in the applied sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.719
H-Index - 65
eISSN - 1099-1476
pISSN - 0170-4214
DOI - 10.1002/mma.806
Subject(s) - mathematics , estimator , confidence interval , queueing theory , laplace transform , interval (graph theory) , function (biology) , point estimation , statistics , interval estimation , variance (accounting) , mathematical analysis , combinatorics , evolutionary biology , biology , accounting , business
Mean response time is an important performance measure for a queueing system. In this paper, we propose a consistent and asymptotically normal (CAN) estimator of the mean response time for a G/M/1 queueing system, which is based on the fixed point of empirical Laplace function. The confidence interval for the mean response time can be constructed by applying the proposed CAN estimator and its estimated variance. And we carried out a simulation study to perform the accuracy of the constructed confidence interval by calculating the coverage percentage and the relative average length of confidence interval. Detailed discussions of all simulation results for three various models of G/M/1‐type system are presented and some valuable conclusions are provided. Copyright © 2006 John Wiley & Sons, Ltd.