Optimization Versus Robustness in Simulation

A Practical Methodology, With a Production-Management Case-Study

J.P.C. Kleijnen, E.G.A. Gaury

Research output: Working paperDiscussion paperOther research output

238 Downloads (Pure)

Abstract

Whereas Operations Research has always paid much attention to optimization, practitioners judge the robustness of the 'optimum' solution to be of greater importance.Therefore this paper proposes a practical methodology that is a stagewise combination of the following four proven techniques: (1) discrete-event simulation, (2) heuristic optimization, (3) risk or uncertainty analysis, and (4) bootstrapping.This methodology is illustrated through a case study on production control systems.That study defines robustness as the system's capability to maintain a short-term service measure, in a variety of environments (scenarios).More precisely, this measure is the probability of the short-term fill rate remaining within a prespecified range.Besides satisfying this probabilistic constraint, the system should minimize long-term work-in-process.Actually, the case study compares four systems: Kanban, Conwip, Hybrid, and Generic.These systems are studied for a well-known example, namely a production line with four stations and a single product.The conclusion of this case study is that Hybrid is best when risk is not ignored, but otherwise Generic is best: risk considerations do make a difference.
Original languageEnglish
Place of PublicationTilburg
PublisherOperations research
Number of pages24
Volume2001-10
Publication statusPublished - 2001

Publication series

NameCentER Discussion Paper
Volume2001-10

Fingerprint

Operations research
Production control
Uncertainty analysis
Discrete event simulation
Risk analysis
Robustness (control systems)
Control systems

Keywords

  • simulation
  • experimental design
  • statistical methods
  • optimization
  • risk analysis
  • bootstrap
  • production control
  • robustness

Cite this

Kleijnen, J. P. C., & Gaury, E. G. A. (2001). Optimization Versus Robustness in Simulation: A Practical Methodology, With a Production-Management Case-Study. (CentER Discussion Paper; Vol. 2001-10). Tilburg: Operations research.
@techreport{5b506682ac584dd68c4ccbed29f4e6ef,
title = "Optimization Versus Robustness in Simulation: A Practical Methodology, With a Production-Management Case-Study",
abstract = "Whereas Operations Research has always paid much attention to optimization, practitioners judge the robustness of the 'optimum' solution to be of greater importance.Therefore this paper proposes a practical methodology that is a stagewise combination of the following four proven techniques: (1) discrete-event simulation, (2) heuristic optimization, (3) risk or uncertainty analysis, and (4) bootstrapping.This methodology is illustrated through a case study on production control systems.That study defines robustness as the system's capability to maintain a short-term service measure, in a variety of environments (scenarios).More precisely, this measure is the probability of the short-term fill rate remaining within a prespecified range.Besides satisfying this probabilistic constraint, the system should minimize long-term work-in-process.Actually, the case study compares four systems: Kanban, Conwip, Hybrid, and Generic.These systems are studied for a well-known example, namely a production line with four stations and a single product.The conclusion of this case study is that Hybrid is best when risk is not ignored, but otherwise Generic is best: risk considerations do make a difference.",
keywords = "simulation, experimental design, statistical methods, optimization, risk analysis, bootstrap, production control, robustness",
author = "J.P.C. Kleijnen and E.G.A. Gaury",
note = "Pagination: 24",
year = "2001",
language = "English",
volume = "2001-10",
series = "CentER Discussion Paper",
publisher = "Operations research",
type = "WorkingPaper",
institution = "Operations research",

}

Kleijnen, JPC & Gaury, EGA 2001 'Optimization Versus Robustness in Simulation: A Practical Methodology, With a Production-Management Case-Study' CentER Discussion Paper, vol. 2001-10, Operations research, Tilburg.

Optimization Versus Robustness in Simulation : A Practical Methodology, With a Production-Management Case-Study. / Kleijnen, J.P.C.; Gaury, E.G.A.

Tilburg : Operations research, 2001. (CentER Discussion Paper; Vol. 2001-10).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Optimization Versus Robustness in Simulation

T2 - A Practical Methodology, With a Production-Management Case-Study

AU - Kleijnen, J.P.C.

AU - Gaury, E.G.A.

N1 - Pagination: 24

PY - 2001

Y1 - 2001

N2 - Whereas Operations Research has always paid much attention to optimization, practitioners judge the robustness of the 'optimum' solution to be of greater importance.Therefore this paper proposes a practical methodology that is a stagewise combination of the following four proven techniques: (1) discrete-event simulation, (2) heuristic optimization, (3) risk or uncertainty analysis, and (4) bootstrapping.This methodology is illustrated through a case study on production control systems.That study defines robustness as the system's capability to maintain a short-term service measure, in a variety of environments (scenarios).More precisely, this measure is the probability of the short-term fill rate remaining within a prespecified range.Besides satisfying this probabilistic constraint, the system should minimize long-term work-in-process.Actually, the case study compares four systems: Kanban, Conwip, Hybrid, and Generic.These systems are studied for a well-known example, namely a production line with four stations and a single product.The conclusion of this case study is that Hybrid is best when risk is not ignored, but otherwise Generic is best: risk considerations do make a difference.

AB - Whereas Operations Research has always paid much attention to optimization, practitioners judge the robustness of the 'optimum' solution to be of greater importance.Therefore this paper proposes a practical methodology that is a stagewise combination of the following four proven techniques: (1) discrete-event simulation, (2) heuristic optimization, (3) risk or uncertainty analysis, and (4) bootstrapping.This methodology is illustrated through a case study on production control systems.That study defines robustness as the system's capability to maintain a short-term service measure, in a variety of environments (scenarios).More precisely, this measure is the probability of the short-term fill rate remaining within a prespecified range.Besides satisfying this probabilistic constraint, the system should minimize long-term work-in-process.Actually, the case study compares four systems: Kanban, Conwip, Hybrid, and Generic.These systems are studied for a well-known example, namely a production line with four stations and a single product.The conclusion of this case study is that Hybrid is best when risk is not ignored, but otherwise Generic is best: risk considerations do make a difference.

KW - simulation

KW - experimental design

KW - statistical methods

KW - optimization

KW - risk analysis

KW - bootstrap

KW - production control

KW - robustness

M3 - Discussion paper

VL - 2001-10

T3 - CentER Discussion Paper

BT - Optimization Versus Robustness in Simulation

PB - Operations research

CY - Tilburg

ER -