Comparison of Monte Carlo and Quasi Monte Carlo Sampling Methods in High Dimensional Model Representation

Author

Feil, Balazs ; Kucherenko, Sergei ; Shah, Nilay

Author_Institution

Dept. of Process Eng., Univ. of Pannonia, Veszprem, Hungary

fYear

2009

fDate

20-25 Sept. 2009

Firstpage

12

Lastpage

17

Abstract

A number of new techniques which improve the efficiency of random sampling-high dimensional model representation (RS-HDMR) is presented. Comparison shows that quasi Monte Carlo based HDMR (QRS-HDRM) significantly outperforms RS-HDMR. RS/QRS-HDRM based methods also show faster convergence than the Sobol method for sensitivity indices calculation. Numerical tests prove that the developed methods for choosing optimal orders of polynomials and the number of sampled points are robust and efficient.

Keywords

Monte Carlo methods; random functions; sampling methods; sensitivity analysis; Monte Carlo method; Sobol method; efficiency; faster convergence; high dimensional model representation; polynomial optimal order; quasi Monte Carlo based HDMR; quasi Monte Carlo sampling method; random sampling-high dimensional model representation; robustness; sensitivity indices calculation; Monte Carlo methods; Quasi-Monte Carlo methods; Quasi-Random Sampling-High Dimensional Model Representation; Random Sampling-High Dimensional Model Representation; global sensitivity analysis; metamodelling; sensitivity indices;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in System Simulation, 2009. SIMUL '09. First International Conference on

Conference_Location

Porto

Print_ISBN

978-1-4244-4863-0

Electronic_ISBN

978-0-7695-3773-3

Type

conf

DOI

10.1109/SIMUL.2009.34

Filename

5283976