A new framework for parallel ranking & selection using an adaptive standard

Linda Pei, Barry L Nelson, Susan Hunter

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

When we have sufficient computational resources to treat a simulation optimization problem as a ranking & selection (R&S) problem, then it can be “solved.” R&S is exhaustive search-all feasible solutions are simulated-with meaningful statistical error control. High-performance parallel computing promises to extend the R&S limit to even larger problems, but parallelizing R&S procedures in a way that maintains statistical validity while achieving substantial speed-up is difficult. In this paper we introduce an entirely new framework for R&S called Parallel Adaptive Survivor Selection (PASS) that is specifically engineered to exploit parallel computing environments for solving simulation optimization problems with a very large number of feasible solutions.

Original languageEnglish (US)
Title of host publicationWSC 2018 - 2018 Winter Simulation Conference
Subtitle of host publicationSimulation for a Noble Cause
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2201-2212
Number of pages12
ISBN (Electronic)9781538665725
DOIs
StatePublished - Jan 31 2019
Event2018 Winter Simulation Conference, WSC 2018 - Gothenburg, Sweden
Duration: Dec 9 2018Dec 12 2018

Publication series

NameProceedings - Winter Simulation Conference
Volume2018-December
ISSN (Print)0891-7736

Conference

Conference2018 Winter Simulation Conference, WSC 2018
CountrySweden
CityGothenburg
Period12/9/1812/12/18

Fingerprint

Simulation Optimization
Parallel processing systems
Parallel Computing
Ranking
Optimization Problem
Exhaustive Search
Error Control
Speedup
High Performance
Sufficient
Resources
Standards
Framework

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Pei, L., Nelson, B. L., & Hunter, S. (2019). A new framework for parallel ranking & selection using an adaptive standard. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause (pp. 2201-2212). [8632457] (Proceedings - Winter Simulation Conference; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2018.8632457
Pei, Linda ; Nelson, Barry L ; Hunter, Susan. / A new framework for parallel ranking & selection using an adaptive standard. WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2201-2212 (Proceedings - Winter Simulation Conference).
@inproceedings{b9f047721863457d892a0e25dba2cc78,
title = "A new framework for parallel ranking & selection using an adaptive standard",
abstract = "When we have sufficient computational resources to treat a simulation optimization problem as a ranking & selection (R&S) problem, then it can be “solved.” R&S is exhaustive search-all feasible solutions are simulated-with meaningful statistical error control. High-performance parallel computing promises to extend the R&S limit to even larger problems, but parallelizing R&S procedures in a way that maintains statistical validity while achieving substantial speed-up is difficult. In this paper we introduce an entirely new framework for R&S called Parallel Adaptive Survivor Selection (PASS) that is specifically engineered to exploit parallel computing environments for solving simulation optimization problems with a very large number of feasible solutions.",
author = "Linda Pei and Nelson, {Barry L} and Susan Hunter",
year = "2019",
month = "1",
day = "31",
doi = "10.1109/WSC.2018.8632457",
language = "English (US)",
series = "Proceedings - Winter Simulation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2201--2212",
booktitle = "WSC 2018 - 2018 Winter Simulation Conference",
address = "United States",

}

Pei, L, Nelson, BL & Hunter, S 2019, A new framework for parallel ranking & selection using an adaptive standard. in WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause., 8632457, Proceedings - Winter Simulation Conference, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 2201-2212, 2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, 12/9/18. https://doi.org/10.1109/WSC.2018.8632457

A new framework for parallel ranking & selection using an adaptive standard. / Pei, Linda; Nelson, Barry L; Hunter, Susan.

WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2201-2212 8632457 (Proceedings - Winter Simulation Conference; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A new framework for parallel ranking & selection using an adaptive standard

AU - Pei, Linda

AU - Nelson, Barry L

AU - Hunter, Susan

PY - 2019/1/31

Y1 - 2019/1/31

N2 - When we have sufficient computational resources to treat a simulation optimization problem as a ranking & selection (R&S) problem, then it can be “solved.” R&S is exhaustive search-all feasible solutions are simulated-with meaningful statistical error control. High-performance parallel computing promises to extend the R&S limit to even larger problems, but parallelizing R&S procedures in a way that maintains statistical validity while achieving substantial speed-up is difficult. In this paper we introduce an entirely new framework for R&S called Parallel Adaptive Survivor Selection (PASS) that is specifically engineered to exploit parallel computing environments for solving simulation optimization problems with a very large number of feasible solutions.

AB - When we have sufficient computational resources to treat a simulation optimization problem as a ranking & selection (R&S) problem, then it can be “solved.” R&S is exhaustive search-all feasible solutions are simulated-with meaningful statistical error control. High-performance parallel computing promises to extend the R&S limit to even larger problems, but parallelizing R&S procedures in a way that maintains statistical validity while achieving substantial speed-up is difficult. In this paper we introduce an entirely new framework for R&S called Parallel Adaptive Survivor Selection (PASS) that is specifically engineered to exploit parallel computing environments for solving simulation optimization problems with a very large number of feasible solutions.

UR - http://www.scopus.com/inward/record.url?scp=85062640810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062640810&partnerID=8YFLogxK

U2 - 10.1109/WSC.2018.8632457

DO - 10.1109/WSC.2018.8632457

M3 - Conference contribution

T3 - Proceedings - Winter Simulation Conference

SP - 2201

EP - 2212

BT - WSC 2018 - 2018 Winter Simulation Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Pei L, Nelson BL, Hunter S. A new framework for parallel ranking & selection using an adaptive standard. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2201-2212. 8632457. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2018.8632457