Estimation of the Pareto front in stochastic simulation through stochastic Kriging

Jianxia Zhang, Yizhong Ma, Ta-Ho Yang, Lijun Liu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Multi-objective optimization of simulated stochastic systems aims at estimating a representative set of Pareto optimal solutions and a common approach is to rely on metamodels to alleviate computational costs of the optimization process. In this article, both the objective and constraint functions are assumed to be smooth, highly non-linear and computationally expensive and are emulated by stochastic Kriging models. Then a novel global optimization algorithm, combing the expected hypervolume improvement of approximated Pareto front and the probability of feasibility of new points, is proposed to identify the Pareto front (set) with a minimal number of expensive simulations. The algorithm is suitable for the situations of having disconnected feasible regions and of having no feasible solution in initial design. Then, we also quantify the variability of estimated Pareto front caused by the intrinsic uncertainty of stochastic simulation using nonparametric bootstrapping method to better support decision making. One test function and an (s, S) inventory system experiment illustrate the potential and efficiency of the proposed sequential optimization algorithm for constrained multi-objective optimization problems in stochastic simulation, which is especially useful in Operations Research and Management Science.

Original languageEnglish
Pages (from-to)69-86
Number of pages18
JournalSimulation Modelling Practice and Theory
Volume79
DOIs
Publication statusPublished - 2017 Dec 1

Fingerprint

Pareto Front
Kriging
Stochastic Simulation
Multiobjective optimization
Optimization Algorithm
Management science
Operations Management
Operations research
Pareto Optimal Solution
Stochastic systems
Sequential Algorithm
Feasible region
Inventory Systems
Bootstrapping
Constrained optimization
Operations Research
Multiobjective Optimization Problems
Global optimization
Stochastic models
Constrained Optimization Problem

All Science Journal Classification (ASJC) codes

  • Software
  • Modelling and Simulation
  • Hardware and Architecture

Cite this

@article{857d9ab06d0347a0b93d0e525325c191,
title = "Estimation of the Pareto front in stochastic simulation through stochastic Kriging",
abstract = "Multi-objective optimization of simulated stochastic systems aims at estimating a representative set of Pareto optimal solutions and a common approach is to rely on metamodels to alleviate computational costs of the optimization process. In this article, both the objective and constraint functions are assumed to be smooth, highly non-linear and computationally expensive and are emulated by stochastic Kriging models. Then a novel global optimization algorithm, combing the expected hypervolume improvement of approximated Pareto front and the probability of feasibility of new points, is proposed to identify the Pareto front (set) with a minimal number of expensive simulations. The algorithm is suitable for the situations of having disconnected feasible regions and of having no feasible solution in initial design. Then, we also quantify the variability of estimated Pareto front caused by the intrinsic uncertainty of stochastic simulation using nonparametric bootstrapping method to better support decision making. One test function and an (s, S) inventory system experiment illustrate the potential and efficiency of the proposed sequential optimization algorithm for constrained multi-objective optimization problems in stochastic simulation, which is especially useful in Operations Research and Management Science.",
author = "Jianxia Zhang and Yizhong Ma and Ta-Ho Yang and Lijun Liu",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.simpat.2017.09.006",
language = "English",
volume = "79",
pages = "69--86",
journal = "Simulation Modelling Practice and Theory",
issn = "1569-190X",
publisher = "Elsevier",

}

Estimation of the Pareto front in stochastic simulation through stochastic Kriging. / Zhang, Jianxia; Ma, Yizhong; Yang, Ta-Ho; Liu, Lijun.

In: Simulation Modelling Practice and Theory, Vol. 79, 01.12.2017, p. 69-86.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimation of the Pareto front in stochastic simulation through stochastic Kriging

AU - Zhang, Jianxia

AU - Ma, Yizhong

AU - Yang, Ta-Ho

AU - Liu, Lijun

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Multi-objective optimization of simulated stochastic systems aims at estimating a representative set of Pareto optimal solutions and a common approach is to rely on metamodels to alleviate computational costs of the optimization process. In this article, both the objective and constraint functions are assumed to be smooth, highly non-linear and computationally expensive and are emulated by stochastic Kriging models. Then a novel global optimization algorithm, combing the expected hypervolume improvement of approximated Pareto front and the probability of feasibility of new points, is proposed to identify the Pareto front (set) with a minimal number of expensive simulations. The algorithm is suitable for the situations of having disconnected feasible regions and of having no feasible solution in initial design. Then, we also quantify the variability of estimated Pareto front caused by the intrinsic uncertainty of stochastic simulation using nonparametric bootstrapping method to better support decision making. One test function and an (s, S) inventory system experiment illustrate the potential and efficiency of the proposed sequential optimization algorithm for constrained multi-objective optimization problems in stochastic simulation, which is especially useful in Operations Research and Management Science.

AB - Multi-objective optimization of simulated stochastic systems aims at estimating a representative set of Pareto optimal solutions and a common approach is to rely on metamodels to alleviate computational costs of the optimization process. In this article, both the objective and constraint functions are assumed to be smooth, highly non-linear and computationally expensive and are emulated by stochastic Kriging models. Then a novel global optimization algorithm, combing the expected hypervolume improvement of approximated Pareto front and the probability of feasibility of new points, is proposed to identify the Pareto front (set) with a minimal number of expensive simulations. The algorithm is suitable for the situations of having disconnected feasible regions and of having no feasible solution in initial design. Then, we also quantify the variability of estimated Pareto front caused by the intrinsic uncertainty of stochastic simulation using nonparametric bootstrapping method to better support decision making. One test function and an (s, S) inventory system experiment illustrate the potential and efficiency of the proposed sequential optimization algorithm for constrained multi-objective optimization problems in stochastic simulation, which is especially useful in Operations Research and Management Science.

UR - http://www.scopus.com/inward/record.url?scp=85030459145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030459145&partnerID=8YFLogxK

U2 - 10.1016/j.simpat.2017.09.006

DO - 10.1016/j.simpat.2017.09.006

M3 - Article

AN - SCOPUS:85030459145

VL - 79

SP - 69

EP - 86

JO - Simulation Modelling Practice and Theory

JF - Simulation Modelling Practice and Theory

SN - 1569-190X

ER -