Locating arrays: A new experimental design for screening complex Engineered systems

Abraham N. Aldaco, Charles Colbourn, Violet Syrotiuk

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

11 Citations (Scopus)

Abstract

The purpose of a screening experiment is to identify significant factors and interactions on a response for a system. Engineered systems are complex in part due to their size. To apply traditional experimental designs for screening in complex engineered systems requires either restricting the factors considered, which automatically restricts the interactions to those in the set, or restricting interest to main effects, which fails to consider any possible interactions. To address this problem we propose a locating array (LA) as a screening design. Locating arrays exhibit logarithmic growth in the number of factors because their focus is on identification rather than on measurement. This makes practical the consideration of an order of magnitude more factors in experimentation than traditional screening designs. We present preliminary results applying an LA for screening the response of TCP throughput in a simulation model of a mobile wireless network. The full-factorial design for this system is infeasible (over 10 43 design points!) yet an LA has only 421 design points. We validate the significance of the identified factors and interactions independently using the statistical software JMP. Screening using locating arrays is viable and yields useful models.

Original languageEnglish (US)
Title of host publicationOperating Systems Review (ACM)
PublisherAssociation for Computing Machinery
Pages31-40
Number of pages10
Volume49
Edition1
DOIs
StatePublished - Jan 20 2015
Event8th Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2014 - Cambridge, United Kingdom
Duration: Oct 23 2014Oct 24 2014

Other

Other8th Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2014
CountryUnited Kingdom
CityCambridge
Period10/23/1410/24/14

Fingerprint

Design of experiments
Large scale systems
Screening
Wireless networks
Throughput
Experiments

Keywords

  • Locating arrays
  • Screening experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems

Cite this

Aldaco, A. N., Colbourn, C., & Syrotiuk, V. (2015). Locating arrays: A new experimental design for screening complex Engineered systems. In Operating Systems Review (ACM) (1 ed., Vol. 49, pp. 31-40). Association for Computing Machinery. https://doi.org/10.1145/2723872.2723878

Locating arrays : A new experimental design for screening complex Engineered systems. / Aldaco, Abraham N.; Colbourn, Charles; Syrotiuk, Violet.

Operating Systems Review (ACM). Vol. 49 1. ed. Association for Computing Machinery, 2015. p. 31-40.

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

Aldaco, AN, Colbourn, C & Syrotiuk, V 2015, Locating arrays: A new experimental design for screening complex Engineered systems. in Operating Systems Review (ACM). 1 edn, vol. 49, Association for Computing Machinery, pp. 31-40, 8th Workshop on Large-Scale Distributed Systems and Middleware, LADIS 2014, Cambridge, United Kingdom, 10/23/14. https://doi.org/10.1145/2723872.2723878
Aldaco AN, Colbourn C, Syrotiuk V. Locating arrays: A new experimental design for screening complex Engineered systems. In Operating Systems Review (ACM). 1 ed. Vol. 49. Association for Computing Machinery. 2015. p. 31-40 https://doi.org/10.1145/2723872.2723878
Aldaco, Abraham N. ; Colbourn, Charles ; Syrotiuk, Violet. / Locating arrays : A new experimental design for screening complex Engineered systems. Operating Systems Review (ACM). Vol. 49 1. ed. Association for Computing Machinery, 2015. pp. 31-40
@inproceedings{74c356f1ee9b4e618bcf614667f71c1c,
title = "Locating arrays: A new experimental design for screening complex Engineered systems",
abstract = "The purpose of a screening experiment is to identify significant factors and interactions on a response for a system. Engineered systems are complex in part due to their size. To apply traditional experimental designs for screening in complex engineered systems requires either restricting the factors considered, which automatically restricts the interactions to those in the set, or restricting interest to main effects, which fails to consider any possible interactions. To address this problem we propose a locating array (LA) as a screening design. Locating arrays exhibit logarithmic growth in the number of factors because their focus is on identification rather than on measurement. This makes practical the consideration of an order of magnitude more factors in experimentation than traditional screening designs. We present preliminary results applying an LA for screening the response of TCP throughput in a simulation model of a mobile wireless network. The full-factorial design for this system is infeasible (over 10 43 design points!) yet an LA has only 421 design points. We validate the significance of the identified factors and interactions independently using the statistical software JMP. Screening using locating arrays is viable and yields useful models.",
keywords = "Locating arrays, Screening experiments",
author = "Aldaco, {Abraham N.} and Charles Colbourn and Violet Syrotiuk",
year = "2015",
month = "1",
day = "20",
doi = "10.1145/2723872.2723878",
language = "English (US)",
volume = "49",
pages = "31--40",
booktitle = "Operating Systems Review (ACM)",
publisher = "Association for Computing Machinery",
edition = "1",

}

TY - GEN

T1 - Locating arrays

T2 - A new experimental design for screening complex Engineered systems

AU - Aldaco, Abraham N.

AU - Colbourn, Charles

AU - Syrotiuk, Violet

PY - 2015/1/20

Y1 - 2015/1/20

N2 - The purpose of a screening experiment is to identify significant factors and interactions on a response for a system. Engineered systems are complex in part due to their size. To apply traditional experimental designs for screening in complex engineered systems requires either restricting the factors considered, which automatically restricts the interactions to those in the set, or restricting interest to main effects, which fails to consider any possible interactions. To address this problem we propose a locating array (LA) as a screening design. Locating arrays exhibit logarithmic growth in the number of factors because their focus is on identification rather than on measurement. This makes practical the consideration of an order of magnitude more factors in experimentation than traditional screening designs. We present preliminary results applying an LA for screening the response of TCP throughput in a simulation model of a mobile wireless network. The full-factorial design for this system is infeasible (over 10 43 design points!) yet an LA has only 421 design points. We validate the significance of the identified factors and interactions independently using the statistical software JMP. Screening using locating arrays is viable and yields useful models.

AB - The purpose of a screening experiment is to identify significant factors and interactions on a response for a system. Engineered systems are complex in part due to their size. To apply traditional experimental designs for screening in complex engineered systems requires either restricting the factors considered, which automatically restricts the interactions to those in the set, or restricting interest to main effects, which fails to consider any possible interactions. To address this problem we propose a locating array (LA) as a screening design. Locating arrays exhibit logarithmic growth in the number of factors because their focus is on identification rather than on measurement. This makes practical the consideration of an order of magnitude more factors in experimentation than traditional screening designs. We present preliminary results applying an LA for screening the response of TCP throughput in a simulation model of a mobile wireless network. The full-factorial design for this system is infeasible (over 10 43 design points!) yet an LA has only 421 design points. We validate the significance of the identified factors and interactions independently using the statistical software JMP. Screening using locating arrays is viable and yields useful models.

KW - Locating arrays

KW - Screening experiments

UR - http://www.scopus.com/inward/record.url?scp=84955311791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955311791&partnerID=8YFLogxK

U2 - 10.1145/2723872.2723878

DO - 10.1145/2723872.2723878

M3 - Conference contribution

AN - SCOPUS:84955311791

VL - 49

SP - 31

EP - 40

BT - Operating Systems Review (ACM)

PB - Association for Computing Machinery

ER -