Stochastic intrinsic Kriging for simulation metamodeling

J.P.C. Kleijnen, Ehsan Mehdad

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Kriging provides metamodels for deterministic and random simulation models. Actually, there are several types of Kriging; the classic type is so-called universal Kriging, which includes ordinary Kriging. These classic types require estimation of the trend in the input-output data of the underlying simulation model; this estimation deteriorates the Kriging metamodel. We therefore consider so-called intrinsic Kriging originating in geostatistics, and derive intrinsic Kriging for deterministic and random simulations. Moreover, for random simulations we derive experimental designs that specify the number of replications that varies with the input combination of the simulation model. To compare the performance of intrinsic Kriging and classic Kriging, we use several numerical experiments with deterministic simulations and random simulations. These experiments show that intrinsic Kriging gives better metamodels, in most experiments.
Original languageEnglish
Pages (from-to)322-337
JournalApplied Stocahstic Models in Business and Industry
Volume34
Issue number3
DOIs
Publication statusPublished - May 2018

Fingerprint

Metamodeling
Kriging
Simulation
Metamodel
Experiments
Design of experiments
Simulation Model
Universal Kriging
Ordinary Kriging
Geostatistics
Intrinsic
Experimental design
Replication
Experiment
Numerical Experiment
Vary
Output

Cite this

@article{d6193646087d468d9ad6ec9785ba9639,
title = "Stochastic intrinsic Kriging for simulation metamodeling",
abstract = "Kriging provides metamodels for deterministic and random simulation models. Actually, there are several types of Kriging; the classic type is so-called universal Kriging, which includes ordinary Kriging. These classic types require estimation of the trend in the input-output data of the underlying simulation model; this estimation deteriorates the Kriging metamodel. We therefore consider so-called intrinsic Kriging originating in geostatistics, and derive intrinsic Kriging for deterministic and random simulations. Moreover, for random simulations we derive experimental designs that specify the number of replications that varies with the input combination of the simulation model. To compare the performance of intrinsic Kriging and classic Kriging, we use several numerical experiments with deterministic simulations and random simulations. These experiments show that intrinsic Kriging gives better metamodels, in most experiments.",
author = "J.P.C. Kleijnen and Ehsan Mehdad",
year = "2018",
month = "5",
doi = "10.1002/asmb.2300",
language = "English",
volume = "34",
pages = "322--337",
journal = "Applied Stocahstic Models in Business and Industry",
issn = "1524-1904",
publisher = "John Wiley and Sons Ltd",
number = "3",

}

Stochastic intrinsic Kriging for simulation metamodeling. / Kleijnen, J.P.C.; Mehdad, Ehsan.

In: Applied Stocahstic Models in Business and Industry, Vol. 34, No. 3, 05.2018, p. 322-337.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Stochastic intrinsic Kriging for simulation metamodeling

AU - Kleijnen, J.P.C.

AU - Mehdad, Ehsan

PY - 2018/5

Y1 - 2018/5

N2 - Kriging provides metamodels for deterministic and random simulation models. Actually, there are several types of Kriging; the classic type is so-called universal Kriging, which includes ordinary Kriging. These classic types require estimation of the trend in the input-output data of the underlying simulation model; this estimation deteriorates the Kriging metamodel. We therefore consider so-called intrinsic Kriging originating in geostatistics, and derive intrinsic Kriging for deterministic and random simulations. Moreover, for random simulations we derive experimental designs that specify the number of replications that varies with the input combination of the simulation model. To compare the performance of intrinsic Kriging and classic Kriging, we use several numerical experiments with deterministic simulations and random simulations. These experiments show that intrinsic Kriging gives better metamodels, in most experiments.

AB - Kriging provides metamodels for deterministic and random simulation models. Actually, there are several types of Kriging; the classic type is so-called universal Kriging, which includes ordinary Kriging. These classic types require estimation of the trend in the input-output data of the underlying simulation model; this estimation deteriorates the Kriging metamodel. We therefore consider so-called intrinsic Kriging originating in geostatistics, and derive intrinsic Kriging for deterministic and random simulations. Moreover, for random simulations we derive experimental designs that specify the number of replications that varies with the input combination of the simulation model. To compare the performance of intrinsic Kriging and classic Kriging, we use several numerical experiments with deterministic simulations and random simulations. These experiments show that intrinsic Kriging gives better metamodels, in most experiments.

U2 - 10.1002/asmb.2300

DO - 10.1002/asmb.2300

M3 - Article

VL - 34

SP - 322

EP - 337

JO - Applied Stocahstic Models in Business and Industry

JF - Applied Stocahstic Models in Business and Industry

SN - 1524-1904

IS - 3

ER -