Bias correction for estimation of performance measures of a Markovian queue

  • M. A. C. Almeida
  • F. R. B. Cruz
  • F. L. P. Oliveira
  • G. de Souza
Original Paper
  • 68 Downloads

Abstract

There are several situations in our daily lives in which queues are present, such as cafeterias, supermarkets, banks, gas stations, and so forth. The performance of such queues can be described by several measures. In this article, the focus is on estimates of traffic intensity (\(\rho\)), also called the utilization factor of the service station, the expected number of customers in the system (L), and the average queue size (\({L_{q}}\) ) for infinite single-serve queues with Poisson arrivals and exponential (Markovian) service times. The computational experiments show that the maximum likelihood estimators (MLEs) of the performance measures are biased for small and moderate samples (\(n < 50\)). Thus, a version corrected by the nonparametric bootstrap method is analyzed, demonstrating that researchers could achieve with an extra computational effort bias-corrected estimates for samples of size \(n=10\) with average errors equivalent to the estimates from the MLE for samples of size \(n=200\). This reduction can be very important in practical applications because of the cost and time reduction that it may bring to the process of estimating the performance measures of a queueing system.

Keywords

Bias correction Markovian queues Performance measures Bootstrap 

Notes

Acknowledgements

This research has been partially funded by the Brazilian agencies CNPq (Conselho Nacional de Desenvolvimento Científico e Tecnológico of the Ministry for Science and Technology) under grants 304671/2014-2 and 300825/2016-1, and FAPEMIG (Fundação de Amparo à Pesquisa do Estado de Minas Gerais) under grant CEX-PPM-00564-17, and by UFOP and UFPA. Special thanks to Carolina and Gabriel for their helpful advice with the algebra.

Compliance with ethical standards

Conflicts of interest

The authors declare that there are no conflicts of interest regarding the publication of this article.

References

  1. Almeida MAC, Cruz FRB (2017) A note on Bayesian estimation of traffic intensity in single-server Markovian queues. Commun Stat Simul Comput. doi: 10.1080/03610918.2017.1353614 Google Scholar
  2. Armero C, Bayarri MJ (1994a) Bayesian prediction in \(M/M/1\) queues. Queueing Syst 15(1–4):401–417CrossRefGoogle Scholar
  3. Armero C, Bayarri MJ (1994b) Prior assessments for prediction in queues. J R Stat Soc Series D 43(1):139–153Google Scholar
  4. Armero C, Bayarri MJ (1996) Bayesian questions and answers in queues. Bayesian Stat 5:3–23Google Scholar
  5. Armero C, Bayarri MJ (1997) A Bayesian analysis of a queueing system with unlimited service. J Stat Plan Inference 58(2):241–261CrossRefGoogle Scholar
  6. Armero C, Bayarri MJ (1999) Multivariate analysis, design of experiments and survey sampling. In: Ghosh S (ed) Dealing with uncertainties in queues and networks of queues: a Bayesian approach. Springer Science+Business Media. Marcel Dekker, New York, NY, pp 579–608Google Scholar
  7. Armero C, Bayarri MJ (2015) Queues. In: Wright JD (ed) International encyclopedia of the social & behavioral sciences. Elsevier, Oxford, pp 784–789CrossRefGoogle Scholar
  8. Armero C, Conesa D (1998) Inference and prediction in bulk arrival queues and queues with service in stages. Appl Stoch Models Data Anal 14(1):35–46CrossRefGoogle Scholar
  9. Armero C, Conesa D (2000) Prediction in Markovian bulk arrival queues. Queueing Syst 34(1–4):327–350CrossRefGoogle Scholar
  10. Armero C, Conesa D (2004) Statistical performance of a multiclass bulk production queueing system. Eur J Oper Res 158(3):649–661CrossRefGoogle Scholar
  11. Armero C, Conesa D (2006) Bayesian hierarchical models in manufacturing bulk service queues. J Stat Plan Inference 136(2):335–354CrossRefGoogle Scholar
  12. Choudhury A, Borthakur AC (2008) Bayesian inference and prediction in the single server Markovian queue. Metrika 67(3):371–383CrossRefGoogle Scholar
  13. Chowdhury S, Mukherjee SP (2013) Estimation of traffic intensity based on queue length in a single \(M/M/1\) queue. Commun Stat Theory Methods 42(13):2376–2390CrossRefGoogle Scholar
  14. Clarke AB (1957) Maximum likelihood estimates in a simple queue. Ann Math Stat 28(4):1036–1040CrossRefGoogle Scholar
  15. Cruz FRB, Colosimo EA, Smith JM (2004) Sample size corrections for the maximum partial likelihood estimator. Commun Stat Simul Comput 33(1):35–47CrossRefGoogle Scholar
  16. Cruz FRB, Quinino RC, Ho LL (2016) Bayesian estimation of traffic intensity based on queue length in a multi-server \(M/M/s\) queue. Commun Stat Simul Comput. doi: 10.1080/03610918.2016.1236953 Google Scholar
  17. Efron B, Tibshirani R (1993) An introduction to the bootstrap. Chapman & Hall, LondonCrossRefGoogle Scholar
  18. Gontijo GM, Atuncar GS, Cruz FRB, Kerbache L (2011) Performance evaluation and dimensioning of \(GIX/M/c/N\) systems through kernel estimation. Math Probl Eng 2011:348262. doi: 10.1155/2011/348262 CrossRefGoogle Scholar
  19. Gross D, Shortle JF, Thompson JM, Harris CM (2009) Fundamentals of queueing theory, 4th edn. Wiley-Interscience, New YorkGoogle Scholar
  20. Ke JC, Chu YK (2009) Comparison on five estimation approaches of intensity for a queueing system with short run. Comput Stat 24(4):567–582CrossRefGoogle Scholar
  21. Kendall DG (1953) Stochastic processes occurring in the theory of queues and their analysis by the method of embedded Markov chains. Ann Math Stat 24:338–354CrossRefGoogle Scholar
  22. Little JDC (1961) A proof for the queuing formula: \(L = \lambda W\). Oper Res 9(3):383–387CrossRefGoogle Scholar
  23. Mcgrath MF, Gross D, Singpurwalla ND (1987) A subjective Bayesian approach to the theory of queues I—modeling. Queueing Syst 1(4):317–333CrossRefGoogle Scholar
  24. McGrath MF, Singpurwalla ND (1987) A subjective Bayesian approach to the theory of queues II—inference and information in \(M/M/1\) queues. Queueing Syst 1(4):335–353CrossRefGoogle Scholar
  25. Muddapur MV (1972) Bayesian estimates of parameters in some queueing models. Ann Inst Stat Math 24(1):327–331CrossRefGoogle Scholar
  26. Mukhopadhyay N (2000) Probability and statistical inference. Marcel Dekker, New YorkGoogle Scholar
  27. Quinino RC, Cruz FRB (2017) Bayesian sample sizes in an \(M/M/1\) queueing system. Int J Adv Manuf Technol 88(1):995–1002CrossRefGoogle Scholar
  28. R Core Team: R (2017) A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/
  29. Schruben L, Kulkarni R (1982) Some consequences of estimating parameters for the \(M/M/1\) queue. Oper Res Lett 1(2):75–78CrossRefGoogle Scholar
  30. Sohn SY (1996) Empirical Bayesian analysis for traffic intensity: \(M/M/1\) queues with covariates. Queueing Syst 22(3):383–401CrossRefGoogle Scholar
  31. Sohn SY (1996) Influence of a prior distribution on traffic intensity estimation with covariates. J Stat Comput Simul 55(3):169–180CrossRefGoogle Scholar
  32. Wagner HM (1975) Principles of Operations Research: with applications to managerial decisions, 2nd edn. Prentice-Hall Inc, Englewood CliffsGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  • M. A. C. Almeida
    • 1
  • F. R. B. Cruz
    • 2
  • F. L. P. Oliveira
    • 3
  • G. de Souza
    • 4
  1. 1.Pró-Reitoria de Planejamento e DesenvolvimentoUniversidade Federal do ParáBelémBrazil
  2. 2.Departamento de EstatísticaUniversidade Federal de Minas GeraisBelo HorizonteBrazil
  3. 3.Departamento de EstatísticaUniversidade Federal de Ouro PretoOuro PretoBrazil
  4. 4.Departamento de MatemáticaUniversidade Federal de Ouro PretoOuro PretoBrazil

Personalised recommendations