Meta-Regression: A Framework for Robust Reactive Optimization

Dan McClary; Violet R. Syrotiuk; Murat Kulahci

doi:10.1109/SASO.2007.37

Meta-Regression: A Framework for Robust Reactive Optimization

Dan McClary, Violet R. Syrotiuk, Murat Kulahci

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Maintaining optimal performance as the conditions of a system change is a challenging problem. To solve this problem, we present meta-regression, a general methodology for alleviating traditional difficulties in nonlinear regression modelling. Meta-regression allows for reactive optimization, in which system components self-organize to changing conditions in a manner that is robust, or affected minimally by other sources of variability. Meta-regression extends profiling, providing a methodology for model-building when there is incomplete knowledge of the mechanisms and interactions of a nonlinear system.

Original language	English
Title of host publication	First IEEE International Conference on Self-Adaptive and Self-Organizing Systems
Publisher	IEEE Computer Society Press
Publication date	2007
Pages	375-378
ISBN (Print)	978-0-7695-2906-6
DOIs	https://doi.org/10.1109/SASO.2007.37
Publication status	Published - 2007
Event	First IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO 2007) - Boston, MA, United States Duration: 9 Jul 2007 → 11 Jul 2007 Conference number: 1

Conference

Conference	First IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO 2007)
Number	1
Country/Territory	United States
City	Boston, MA
Period	09/07/2007 → 11/07/2007

Access to Document

10.1109/SASO.2007.37

http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=5422

OpenUrl availability

Full text

Cite this

@inproceedings{734c6375d6a74b9f9a6bec87eaeba5fa,

title = "Meta-Regression: A Framework for Robust Reactive Optimization",

abstract = "Maintaining optimal performance as the conditions of a system change is a challenging problem. To solve this problem, we present meta-regression, a general methodology for alleviating traditional difficulties in nonlinear regression modelling. Meta-regression allows for reactive optimization, in which system components self-organize to changing conditions in a manner that is robust, or affected minimally by other sources of variability. Meta-regression extends profiling, providing a methodology for model-building when there is incomplete knowledge of the mechanisms and interactions of a nonlinear system.",

author = "Dan McClary and Syrotiuk, {Violet R.} and Murat Kulahci",

year = "2007",

doi = "10.1109/SASO.2007.37",

language = "English",

isbn = "978-0-7695-2906-6",

pages = "375--378",

booktitle = "First IEEE International Conference on Self-Adaptive and Self-Organizing Systems",

publisher = "IEEE Computer Society Press",

note = "First IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO 2007), SASO 2007 ; Conference date: 09-07-2007 Through 11-07-2007",

}

McClary, D, Syrotiuk, VR & Kulahci, M 2007, Meta-Regression: A Framework for Robust Reactive Optimization. in First IEEE International Conference on Self-Adaptive and Self-Organizing Systems. IEEE Computer Society Press, pp. 375-378, First IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO 2007), Boston, MA, United States, 09/07/2007. https://doi.org/10.1109/SASO.2007.37

TY - GEN

T1 - Meta-Regression: A Framework for Robust Reactive Optimization

AU - McClary, Dan

AU - Syrotiuk, Violet R.

AU - Kulahci, Murat

N1 - Conference code: 1

PY - 2007

Y1 - 2007

N2 - Maintaining optimal performance as the conditions of a system change is a challenging problem. To solve this problem, we present meta-regression, a general methodology for alleviating traditional difficulties in nonlinear regression modelling. Meta-regression allows for reactive optimization, in which system components self-organize to changing conditions in a manner that is robust, or affected minimally by other sources of variability. Meta-regression extends profiling, providing a methodology for model-building when there is incomplete knowledge of the mechanisms and interactions of a nonlinear system.

AB - Maintaining optimal performance as the conditions of a system change is a challenging problem. To solve this problem, we present meta-regression, a general methodology for alleviating traditional difficulties in nonlinear regression modelling. Meta-regression allows for reactive optimization, in which system components self-organize to changing conditions in a manner that is robust, or affected minimally by other sources of variability. Meta-regression extends profiling, providing a methodology for model-building when there is incomplete knowledge of the mechanisms and interactions of a nonlinear system.

U2 - 10.1109/SASO.2007.37

DO - 10.1109/SASO.2007.37

M3 - Article in proceedings

SN - 978-0-7695-2906-6

SP - 375

EP - 378

BT - First IEEE International Conference on Self-Adaptive and Self-Organizing Systems

PB - IEEE Computer Society Press

T2 - First IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO 2007)

Y2 - 9 July 2007 through 11 July 2007

ER -

Meta-Regression: A Framework for Robust Reactive Optimization

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this