A Heuristic Procedure for Selecting the Best Feasible Design in the Presence of Stochastic Constraints

Seon Han Choi; Bong Gu Kang; Tag Gon Kim

doi:10.1109/TSMC.2019.2894523

A Heuristic Procedure for Selecting the Best Feasible Design in the Presence of Stochastic Constraints

Seon Han Choi, Bong Gu Kang, Tag Gon Kim

Electronic and Electrical Engineering

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Motivated by the practical needs of simulation-based optimization, this paper considers a problem for selecting the best feasible design from a finite set of alternatives, subject to stochastic constraints given in several secondary objectives. We propose an efficient ranking and selection procedure that maximizes the accuracy of the selection under a limited simulation budget. The proposed procedure sequentially updates the simulation data of designs with a heuristic policy that allocates further simulation replications according to the evaluation results of data based on a statistical hypothesis test. Compared to recent studies, such as OCBA-CO and SCORE, this procedure can be more efficient when the simulation model involves large stochastic noise because its heuristic policy considers the precision of the sample mean ignored by the previous studies. Several experimental results of benchmarks demonstrate its improved efficiency, and a case study on the design of military network system shows its effectiveness for practical problems.

Original language	English
Article number	8632926
Pages (from-to)	1016-1026
Number of pages	11
Journal	IEEE Transactions on Systems, Man, and Cybernetics: Systems
Volume	51
Issue number	2
DOIs	https://doi.org/10.1109/TSMC.2019.2894523
State	Published - Feb 2021

Bibliographical note

Funding Information:
Manuscript received May 16, 2018; revised September 9, 2018; accepted January 18, 2019. Date of publication February 1, 2019; date of current version January 19, 2021. This work was supported by the “Development of Verification Technology for Industrial Convergence New Product Suitability-Certification Support (Standards/Criteria)” funded by the Ministry of Trade, Industry and Energy under Grant 10079284. This paper was recommended by Associate Editor Q. Wei. (Corresponding author: Seon Han Choi.) S. H. Choi is with the Industrial Convergence Infrastructure Office, Korea Institute of Industrial Technology, Ansan 15588, South Korea (e-mail: [email protected]).

Publisher Copyright:
© 2013 IEEE.

Keywords

Constrained optimization
multiobjective system
ranking and selection (R AND S)
statistical hypothesis test
stochastic simulation

Access to Document

10.1109/TSMC.2019.2894523

Cite this

@article{5c3c7dcd25c143f7aa6843a9cb41ec72,

title = "A Heuristic Procedure for Selecting the Best Feasible Design in the Presence of Stochastic Constraints",

abstract = "Motivated by the practical needs of simulation-based optimization, this paper considers a problem for selecting the best feasible design from a finite set of alternatives, subject to stochastic constraints given in several secondary objectives. We propose an efficient ranking and selection procedure that maximizes the accuracy of the selection under a limited simulation budget. The proposed procedure sequentially updates the simulation data of designs with a heuristic policy that allocates further simulation replications according to the evaluation results of data based on a statistical hypothesis test. Compared to recent studies, such as OCBA-CO and SCORE, this procedure can be more efficient when the simulation model involves large stochastic noise because its heuristic policy considers the precision of the sample mean ignored by the previous studies. Several experimental results of benchmarks demonstrate its improved efficiency, and a case study on the design of military network system shows its effectiveness for practical problems. ",

keywords = "Constrained optimization, multiobjective system, ranking and selection (R AND S), statistical hypothesis test, stochastic simulation",

author = "Choi, {Seon Han} and Kang, {Bong Gu} and Kim, {Tag Gon}",

note = "Funding Information: Manuscript received May 16, 2018; revised September 9, 2018; accepted January 18, 2019. Date of publication February 1, 2019; date of current version January 19, 2021. This work was supported by the “Development of Verification Technology for Industrial Convergence New Product Suitability-Certification Support (Standards/Criteria)” funded by the Ministry of Trade, Industry and Energy under Grant 10079284. This paper was recommended by Associate Editor Q. Wei. (Corresponding author: Seon Han Choi.) S. H. Choi is with the Industrial Convergence Infrastructure Office, Korea Institute of Industrial Technology, Ansan 15588, South Korea (e-mail: [email protected]). Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2021",

month = feb,

doi = "10.1109/TSMC.2019.2894523",

language = "English",

volume = "51",

pages = "1016--1026",

journal = "IEEE Transactions on Systems, Man, and Cybernetics: Systems",

issn = "2168-2216",

publisher = "IEEE Advancing Technology for Humanity",

number = "2",

}

TY - JOUR

T1 - A Heuristic Procedure for Selecting the Best Feasible Design in the Presence of Stochastic Constraints

AU - Choi, Seon Han

AU - Kang, Bong Gu

AU - Kim, Tag Gon

N1 - Funding Information: Manuscript received May 16, 2018; revised September 9, 2018; accepted January 18, 2019. Date of publication February 1, 2019; date of current version January 19, 2021. This work was supported by the “Development of Verification Technology for Industrial Convergence New Product Suitability-Certification Support (Standards/Criteria)” funded by the Ministry of Trade, Industry and Energy under Grant 10079284. This paper was recommended by Associate Editor Q. Wei. (Corresponding author: Seon Han Choi.) S. H. Choi is with the Industrial Convergence Infrastructure Office, Korea Institute of Industrial Technology, Ansan 15588, South Korea (e-mail: [email protected]). Publisher Copyright: © 2013 IEEE.

PY - 2021/2

Y1 - 2021/2

N2 - Motivated by the practical needs of simulation-based optimization, this paper considers a problem for selecting the best feasible design from a finite set of alternatives, subject to stochastic constraints given in several secondary objectives. We propose an efficient ranking and selection procedure that maximizes the accuracy of the selection under a limited simulation budget. The proposed procedure sequentially updates the simulation data of designs with a heuristic policy that allocates further simulation replications according to the evaluation results of data based on a statistical hypothesis test. Compared to recent studies, such as OCBA-CO and SCORE, this procedure can be more efficient when the simulation model involves large stochastic noise because its heuristic policy considers the precision of the sample mean ignored by the previous studies. Several experimental results of benchmarks demonstrate its improved efficiency, and a case study on the design of military network system shows its effectiveness for practical problems.

AB - Motivated by the practical needs of simulation-based optimization, this paper considers a problem for selecting the best feasible design from a finite set of alternatives, subject to stochastic constraints given in several secondary objectives. We propose an efficient ranking and selection procedure that maximizes the accuracy of the selection under a limited simulation budget. The proposed procedure sequentially updates the simulation data of designs with a heuristic policy that allocates further simulation replications according to the evaluation results of data based on a statistical hypothesis test. Compared to recent studies, such as OCBA-CO and SCORE, this procedure can be more efficient when the simulation model involves large stochastic noise because its heuristic policy considers the precision of the sample mean ignored by the previous studies. Several experimental results of benchmarks demonstrate its improved efficiency, and a case study on the design of military network system shows its effectiveness for practical problems.

KW - Constrained optimization

KW - multiobjective system

KW - ranking and selection (R AND S)

KW - statistical hypothesis test

KW - stochastic simulation

UR - http://www.scopus.com/inward/record.url?scp=85077816452&partnerID=8YFLogxK

U2 - 10.1109/TSMC.2019.2894523

DO - 10.1109/TSMC.2019.2894523

M3 - Article

AN - SCOPUS:85077816452

SN - 2168-2216

VL - 51

SP - 1016

EP - 1026

JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems

JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems

IS - 2

M1 - 8632926

ER -

A Heuristic Procedure for Selecting the Best Feasible Design in the Presence of Stochastic Constraints

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this