Engineering benchmark generation and performance measurement of evolutionary algorithms

Joong Hoon Kim, Ho Min Lee, Donghwi Jung, Ali Sadollah

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

1 Citation (Scopus)

Abstract

Various evolutionary algorithms are being developed to search the optimal solution of various problems in the real world. Evolutionary algorithms search solutions showing the optimal fitness to given problem using their own operators. Engineering benchmark problems can be used for performance measurement of evolutionary algorithms, and the water distribution network design problem is one of the widely used benchmark problems. In this study, the water distribution network design problems are generated by modifications of five problem characteristic factors. Generated benchmark problems are applied to quantitatively evaluate the performance among evolutionary algorithms. Each algorithm shows its own strength and weakness. Optimization results show that the engineering benchmark generation method suggested in this study can be served as a reliable framework for comparison of performances on various water distribution network design problems.

Original languageEnglish
Title of host publication2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages714-717
Number of pages4
ISBN (Electronic)9781509046010
DOIs
Publication statusPublished - 2017 Jul 5
Event2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Donostia-San Sebastian, Spain
Duration: 2017 Jun 52017 Jun 8

Other

Other2017 IEEE Congress on Evolutionary Computation, CEC 2017
CountrySpain
CityDonostia-San Sebastian
Period17/6/517/6/8

Fingerprint

Evolutionary algorithms
Electric power distribution
Water

Keywords

  • Engineering approach
  • Evolutionary algorithms
  • Performance comparison
  • Water distribution networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing

Cite this

Kim, J. H., Lee, H. M., Jung, D., & Sadollah, A. (2017). Engineering benchmark generation and performance measurement of evolutionary algorithms. In 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings (pp. 714-717). [7969380] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEC.2017.7969380

Engineering benchmark generation and performance measurement of evolutionary algorithms. / Kim, Joong Hoon; Lee, Ho Min; Jung, Donghwi; Sadollah, Ali.

2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 714-717 7969380.

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

Kim, JH, Lee, HM, Jung, D & Sadollah, A 2017, Engineering benchmark generation and performance measurement of evolutionary algorithms. in 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings., 7969380, Institute of Electrical and Electronics Engineers Inc., pp. 714-717, 2017 IEEE Congress on Evolutionary Computation, CEC 2017, Donostia-San Sebastian, Spain, 17/6/5. https://doi.org/10.1109/CEC.2017.7969380
Kim JH, Lee HM, Jung D, Sadollah A. Engineering benchmark generation and performance measurement of evolutionary algorithms. In 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 714-717. 7969380 https://doi.org/10.1109/CEC.2017.7969380
Kim, Joong Hoon ; Lee, Ho Min ; Jung, Donghwi ; Sadollah, Ali. / Engineering benchmark generation and performance measurement of evolutionary algorithms. 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 714-717
@inproceedings{138c91b1fc9447d0b34bc0661f093c96,
title = "Engineering benchmark generation and performance measurement of evolutionary algorithms",
abstract = "Various evolutionary algorithms are being developed to search the optimal solution of various problems in the real world. Evolutionary algorithms search solutions showing the optimal fitness to given problem using their own operators. Engineering benchmark problems can be used for performance measurement of evolutionary algorithms, and the water distribution network design problem is one of the widely used benchmark problems. In this study, the water distribution network design problems are generated by modifications of five problem characteristic factors. Generated benchmark problems are applied to quantitatively evaluate the performance among evolutionary algorithms. Each algorithm shows its own strength and weakness. Optimization results show that the engineering benchmark generation method suggested in this study can be served as a reliable framework for comparison of performances on various water distribution network design problems.",
keywords = "Engineering approach, Evolutionary algorithms, Performance comparison, Water distribution networks",
author = "Kim, {Joong Hoon} and Lee, {Ho Min} and Donghwi Jung and Ali Sadollah",
year = "2017",
month = "7",
day = "5",
doi = "10.1109/CEC.2017.7969380",
language = "English",
pages = "714--717",
booktitle = "2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Engineering benchmark generation and performance measurement of evolutionary algorithms

AU - Kim, Joong Hoon

AU - Lee, Ho Min

AU - Jung, Donghwi

AU - Sadollah, Ali

PY - 2017/7/5

Y1 - 2017/7/5

N2 - Various evolutionary algorithms are being developed to search the optimal solution of various problems in the real world. Evolutionary algorithms search solutions showing the optimal fitness to given problem using their own operators. Engineering benchmark problems can be used for performance measurement of evolutionary algorithms, and the water distribution network design problem is one of the widely used benchmark problems. In this study, the water distribution network design problems are generated by modifications of five problem characteristic factors. Generated benchmark problems are applied to quantitatively evaluate the performance among evolutionary algorithms. Each algorithm shows its own strength and weakness. Optimization results show that the engineering benchmark generation method suggested in this study can be served as a reliable framework for comparison of performances on various water distribution network design problems.

AB - Various evolutionary algorithms are being developed to search the optimal solution of various problems in the real world. Evolutionary algorithms search solutions showing the optimal fitness to given problem using their own operators. Engineering benchmark problems can be used for performance measurement of evolutionary algorithms, and the water distribution network design problem is one of the widely used benchmark problems. In this study, the water distribution network design problems are generated by modifications of five problem characteristic factors. Generated benchmark problems are applied to quantitatively evaluate the performance among evolutionary algorithms. Each algorithm shows its own strength and weakness. Optimization results show that the engineering benchmark generation method suggested in this study can be served as a reliable framework for comparison of performances on various water distribution network design problems.

KW - Engineering approach

KW - Evolutionary algorithms

KW - Performance comparison

KW - Water distribution networks

UR - http://www.scopus.com/inward/record.url?scp=85027895913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027895913&partnerID=8YFLogxK

U2 - 10.1109/CEC.2017.7969380

DO - 10.1109/CEC.2017.7969380

M3 - Conference contribution

AN - SCOPUS:85027895913

SP - 714

EP - 717

BT - 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -