Comparing M/G/1 queue estimators in Monte Carlo simulation through the tested generator “getRDS” and the proposed “getLHS” using variance reduction
-
Meriem Boubalou
,
Megdouda Ourbih-Tari
Abstract
In this paper, we propose a Latin hypercube sampling (LHS) number generator in C language under Linux called getLHS in order to compare both methods LHS and refined descriptive sampling (RDS) method. It was highly tested by adequate statistical tests and compared statistically to the getRDS number generator. We noticed that getRDS has passed all tests better than the proposed getLHS generator. A simulation of M/G/1 queues is performed using getRDS to sample inputs from the RDS method and getLHS to sample inputs from the LHS method. The results obtained through simulation demonstrate that the RDS method produces more accurate point estimates of the true parameters than the LHS method. Moreover, the RDS method can significantly improve the performance of the studied queues compared to the well-known LHS method since its variance reduction factor is quite good in almost all cases. It is then proved that RDS is an improvement over LHS at least on queues.
References
[1] C. Aistleitner, M. Hofer and R. Tichy, A central limit theorem for Latin hypercube sampling with dependence and application to exotic basket option pricing, Int. J. Theor. Appl. Finance 15 (2012), no. 7, Article ID 1250046. 10.1142/S021902491250046XSuche in Google Scholar
[2] A. O. Allen, Probability, Statistics, and Queueing Theory. With Computer Science Applications, 2nd ed., Academic Press, Boston, 1990. Suche in Google Scholar
[3] A. Aloui and M. Ourbih-Tari, The use of refined descriptive sampling and applications in parallel Monte Carlo Simulation, Comput. Inform. 30 (2011), 681–700. Suche in Google Scholar
[4] A. Aloui, A. Zioui, M. Ourbih-Tari and A. Alioui, A general purpose module using refined descriptive sampling for installation in simulation systems, Comput. Statist. 30 (2015), no. 2, 477–490. 10.1007/s00180-014-0545-7Suche in Google Scholar
[5] L. Baghdali-Ourbih, M. Ourbih-Tari and A. Dahmani, Implementing refined descriptive sampling into three-phase discrete-event simulation models, Comm. Statist. Simulation Comput. 46 (2017), no. 5, 4035–4049. 10.1080/03610918.2015.1085557Suche in Google Scholar
[6] L. Baiche and M. Ourbih-Tari, Large-sample variance of simulation using refined descriptive sampling: Case of independent variables, Comm. Statist. Theory Methods 46 (2017), no. 1, 510–519. 10.1080/03610926.2014.997362Suche in Google Scholar
[7] S. M. Ermakov and W. Wagner, Monte Carlo difference schemes for the wave equation, Monte Carlo Methods Appl. 8 (2002), no. 1, 1–29. 10.1515/mcma.2002.8.1.1Suche in Google Scholar
[8] J. Helton and F. Davis, Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems, Reliab. Eng. Syst. Safety 81 (2003), 23–69. 10.1016/S0951-8320(03)00058-9Suche in Google Scholar
[9]
K. Idjis, M. Ourbih-Tari and L. Baghdali-Ourbih,
Variance reduction in
[10] M. D. McKay, R. J. Beckman and W. J. Conover, A comparison of three methods for selecting values of input variables in the analysis of output from a computer code, Technometrics 21 (1979), no. 2, 239–245. 10.1080/00401706.1979.10489755Suche in Google Scholar
[11] M. Ourbih-Tari and A. Aloui, Sampling methods and parallelism into Monte Carlo simulation, J. Stat. Adv. Theory Appl. 2 (2009), 169–192. Suche in Google Scholar
[12] M. Ourbih-Tari and S. Guebli, A comparison of methods for selecting values of simulation input variables, ESAIM Probab. Stat. 19 (2015), 135–147. 10.1051/ps/2014020Suche in Google Scholar
[13] M. Ourbih-Tari, A. Zioui and A. Aloui, Variance reduction in the simulation of a stationary M/G/1 queuing system using refined descriptive sampling, Comm. Statist. Simulation Comput. 46 (2017), no. 5, 3504–3515. 10.1080/03610918.2015.1096374Suche in Google Scholar
[14] M. Petelet, B. Iooss, O. Asserin and A. Loredo, Latin hypercube sampling with inequality constraints, AStA Adv. Stat. Anal. 94 (2010), no. 4, 325–339. 10.1007/s10182-010-0144-zSuche in Google Scholar
[15] M. Pidd, Computer Simulation in Management Science, 5th ed., John Wiley and Sons, New York, 2004. Suche in Google Scholar
[16] K. K. Sabelfeld and G. Eremeev, A hybrid kinetic-thermodynamic Monte Carlo model for simulation of homogeneous burst nucleation, Monte Carlo Methods Appl. 24 (2018), no. 3, 193–202. 10.1515/mcma-2018-0017Suche in Google Scholar
[17] E. Saliby, Descriptive sampling: A better approach to Monte Carlo simulation, J. Oper. Res. Soc 41 (1990), 1133–1142. 10.1057/jors.1990.180Suche in Google Scholar
[18]
K. Tamiti, M. Ourbih-Tari, A. Aloui and K. Idjis,
The use of variance reduction, relative error and bias in testing the performance of
[19] M. Tari and A. Dahmani, Flowshop simulator using different sampling methods, Oper. Res. 5 (2005), 261–272. 10.1007/BF02944312Suche in Google Scholar
[20] M. Tari and A. Dahmani, The three phase discrete event simulation using some sampling methods, Int. J. Appl. Math. Stat. 3 (2005), no. D05, 37–48. Suche in Google Scholar
[21] M. Tari and A. Dahmani, Refined descriptive sampling: A better approach to Monte Carlo simulation, Simul. Model. Practice Theory 14 (2006), 143–160. 10.1016/j.simpat.2005.04.001Suche in Google Scholar
[22] Z. G. Zhang and C. E. Love, The Threshold Policy in an M/G/1 Queue with an Exceptional First Vacation, Inform. Syst. Oper. Res. 36 (1998), no. 4, 193–204. 10.1080/03155986.1998.11732358Suche in Google Scholar
[23] Z. G. Zhang, R. Vickson and E. Love, The optimal service policies in an M/G/1 queueing system with multiple vacation types, Inform. Syst. Oper. Res. 39 (2001), no. 4, 357–366. 10.1080/03155986.2001.11732448Suche in Google Scholar
© 2019 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- A third-order weak approximation of multidimensional Itô stochastic differential equations
- Particle diffusion Monte Carlo (PDMC)
- Random walk on rectangles and parallelepipeds algorithm for solving transient anisotropic drift-diffusion-reaction problems
- Analysis of a non-Markovian queueing model: Bayesian statistics and MCMC methods
- On solving stochastic differential equations
- On the sample-mean method for computing hyper-volumes
- Comparing M/G/1 queue estimators in Monte Carlo simulation through the tested generator “getRDS” and the proposed “getLHS” using variance reduction
Artikel in diesem Heft
- Frontmatter
- A third-order weak approximation of multidimensional Itô stochastic differential equations
- Particle diffusion Monte Carlo (PDMC)
- Random walk on rectangles and parallelepipeds algorithm for solving transient anisotropic drift-diffusion-reaction problems
- Analysis of a non-Markovian queueing model: Bayesian statistics and MCMC methods
- On solving stochastic differential equations
- On the sample-mean method for computing hyper-volumes
- Comparing M/G/1 queue estimators in Monte Carlo simulation through the tested generator “getRDS” and the proposed “getLHS” using variance reduction
