Optimal design of engineering systems using MPI-enabled genetic algorithm

Subramaniam Rajan, D. T. Nguyen, M. D. Deshpande, L. Harrell

Research output: Contribution to journalArticle

Abstract

The focus of this paper is on the development and implementation of a genetic algorithm (GA)-based software system using message passing interface (MPI) protocol and library. A customized form of simple GA used in previous research [1-4] is parallelized. This MPI-enabled version is used to find the solution to finite element based design optimization problems. Results show that an almost linear speedup is obtained on homogenous hardware cluster and, with proper reworking of the software, on heterogeneous hardware cluster.

Original languageEnglish (US)
Pages (from-to)155-165
Number of pages11
JournalComputer Assisted Mechanics and Engineering Sciences
Volume11
Issue number2-3
StatePublished - 2004

Fingerprint

Message passing
Systems engineering
Interfaces (computer)
Genetic algorithms
Hardware
Computer systems
Network protocols
Optimal design
Design optimization

Keywords

  • Genetic algorithm
  • MPI
  • Parallel processing
  • Structural optimization

ASJC Scopus subject areas

  • Software
  • Computational Mechanics

Cite this

Optimal design of engineering systems using MPI-enabled genetic algorithm. / Rajan, Subramaniam; Nguyen, D. T.; Deshpande, M. D.; Harrell, L.

In: Computer Assisted Mechanics and Engineering Sciences, Vol. 11, No. 2-3, 2004, p. 155-165.

Research output: Contribution to journalArticle

Rajan, Subramaniam ; Nguyen, D. T. ; Deshpande, M. D. ; Harrell, L. / Optimal design of engineering systems using MPI-enabled genetic algorithm. In: Computer Assisted Mechanics and Engineering Sciences. 2004 ; Vol. 11, No. 2-3. pp. 155-165.
@article{e4ace524cd6c4d92a33d35ae5c270dd6,
title = "Optimal design of engineering systems using MPI-enabled genetic algorithm",
abstract = "The focus of this paper is on the development and implementation of a genetic algorithm (GA)-based software system using message passing interface (MPI) protocol and library. A customized form of simple GA used in previous research [1-4] is parallelized. This MPI-enabled version is used to find the solution to finite element based design optimization problems. Results show that an almost linear speedup is obtained on homogenous hardware cluster and, with proper reworking of the software, on heterogeneous hardware cluster.",
keywords = "Genetic algorithm, MPI, Parallel processing, Structural optimization",
author = "Subramaniam Rajan and Nguyen, {D. T.} and Deshpande, {M. D.} and L. Harrell",
year = "2004",
language = "English (US)",
volume = "11",
pages = "155--165",
journal = "Computer Assisted Mechanics and Engineering Sciences",
issn = "1232-308X",
publisher = "Polish Academy of Sciences Publishing House",
number = "2-3",

}

TY - JOUR

T1 - Optimal design of engineering systems using MPI-enabled genetic algorithm

AU - Rajan, Subramaniam

AU - Nguyen, D. T.

AU - Deshpande, M. D.

AU - Harrell, L.

PY - 2004

Y1 - 2004

N2 - The focus of this paper is on the development and implementation of a genetic algorithm (GA)-based software system using message passing interface (MPI) protocol and library. A customized form of simple GA used in previous research [1-4] is parallelized. This MPI-enabled version is used to find the solution to finite element based design optimization problems. Results show that an almost linear speedup is obtained on homogenous hardware cluster and, with proper reworking of the software, on heterogeneous hardware cluster.

AB - The focus of this paper is on the development and implementation of a genetic algorithm (GA)-based software system using message passing interface (MPI) protocol and library. A customized form of simple GA used in previous research [1-4] is parallelized. This MPI-enabled version is used to find the solution to finite element based design optimization problems. Results show that an almost linear speedup is obtained on homogenous hardware cluster and, with proper reworking of the software, on heterogeneous hardware cluster.

KW - Genetic algorithm

KW - MPI

KW - Parallel processing

KW - Structural optimization

UR - http://www.scopus.com/inward/record.url?scp=5144222828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5144222828&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:5144222828

VL - 11

SP - 155

EP - 165

JO - Computer Assisted Mechanics and Engineering Sciences

JF - Computer Assisted Mechanics and Engineering Sciences

SN - 1232-308X

IS - 2-3

ER -