Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem

Extensive work has been reported for the optimization of water distribution networks (WDNs) using different optimization techniques. Out of these techniques, evolutionary algorithms (EAs) were found to be more efficient as compared with conventional techniques like linear programming and dynamic pro...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Nikita Palod, Vishnu Prasad, Ruchi Khare
Formato: article
Lenguaje:EN
Publicado: IWA Publishing 2021
Materias:
Acceso en línea:https://doaj.org/article/3e1e64231a6c4a98a8357d8010b4a43c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3e1e64231a6c4a98a8357d8010b4a43c
record_format dspace
spelling oai:doaj.org-article:3e1e64231a6c4a98a8357d8010b4a43c2021-11-05T19:07:21ZRedefining the application of an evolutionary algorithm for the optimal pipe sizing problem2040-22442408-935410.2166/wcc.2021.288https://doaj.org/article/3e1e64231a6c4a98a8357d8010b4a43c2021-09-01T00:00:00Zhttp://jwcc.iwaponline.com/content/12/6/2299https://doaj.org/toc/2040-2244https://doaj.org/toc/2408-9354Extensive work has been reported for the optimization of water distribution networks (WDNs) using different optimization techniques. Out of these techniques, evolutionary algorithms (EAs) were found to be more efficient as compared with conventional techniques like linear programming and dynamic programming. Most of the EAs are complex meta-heuristics techniques and need tuning of algorithm-specific parameters. Rao algorithms (Rao-I and Rao-II) do not need any algorithm-specific parameters and hence eliminate the process of sensitivity analysis. In the present work, Rao algorithms are applied for the optimal pipe sizing of WDNs. The optimization results in terms of optimal pipe diameters and the number of evaluations for five different benchmark networks are compared with other EAs. For the two-loop, Hanoi, Go-Yang, and Kadu network, computational efficiency in terms of minimum function evaluations for Rao-I and Rao-II is found to be greater than 78.5 and 83.58%, respectively, when compared with the largest number of minimum function evaluations for other evolutionary techniques. It is seen that Rao algorithms are simple to apply and efficient and do not need any parameter tuning which reduces a large number of computational efforts. HIGHLIGHTS Rao algorithms are applied for the optimization of pipe networks for the very first time.; These are parameterless techniques and hence do not require sensitivity analysis.; Reduces the computational efforts to a large extent.; Applied and tested on five benchmark networks.; Compared with other evolutionary techniques based on minimum function evaluations and found to be highly efficient.;Nikita PalodVishnu PrasadRuchi KhareIWA Publishingarticlebenchmark networksevolutionary algorithmoptimizationrao techniquewater supplyEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350ENJournal of Water and Climate Change, Vol 12, Iss 6, Pp 2299-2313 (2021)
institution DOAJ
collection DOAJ
language EN
topic benchmark networks
evolutionary algorithm
optimization
rao technique
water supply
Environmental technology. Sanitary engineering
TD1-1066
Environmental sciences
GE1-350
spellingShingle benchmark networks
evolutionary algorithm
optimization
rao technique
water supply
Environmental technology. Sanitary engineering
TD1-1066
Environmental sciences
GE1-350
Nikita Palod
Vishnu Prasad
Ruchi Khare
Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
description Extensive work has been reported for the optimization of water distribution networks (WDNs) using different optimization techniques. Out of these techniques, evolutionary algorithms (EAs) were found to be more efficient as compared with conventional techniques like linear programming and dynamic programming. Most of the EAs are complex meta-heuristics techniques and need tuning of algorithm-specific parameters. Rao algorithms (Rao-I and Rao-II) do not need any algorithm-specific parameters and hence eliminate the process of sensitivity analysis. In the present work, Rao algorithms are applied for the optimal pipe sizing of WDNs. The optimization results in terms of optimal pipe diameters and the number of evaluations for five different benchmark networks are compared with other EAs. For the two-loop, Hanoi, Go-Yang, and Kadu network, computational efficiency in terms of minimum function evaluations for Rao-I and Rao-II is found to be greater than 78.5 and 83.58%, respectively, when compared with the largest number of minimum function evaluations for other evolutionary techniques. It is seen that Rao algorithms are simple to apply and efficient and do not need any parameter tuning which reduces a large number of computational efforts. HIGHLIGHTS Rao algorithms are applied for the optimization of pipe networks for the very first time.; These are parameterless techniques and hence do not require sensitivity analysis.; Reduces the computational efforts to a large extent.; Applied and tested on five benchmark networks.; Compared with other evolutionary techniques based on minimum function evaluations and found to be highly efficient.;
format article
author Nikita Palod
Vishnu Prasad
Ruchi Khare
author_facet Nikita Palod
Vishnu Prasad
Ruchi Khare
author_sort Nikita Palod
title Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
title_short Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
title_full Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
title_fullStr Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
title_full_unstemmed Redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
title_sort redefining the application of an evolutionary algorithm for the optimal pipe sizing problem
publisher IWA Publishing
publishDate 2021
url https://doaj.org/article/3e1e64231a6c4a98a8357d8010b4a43c
work_keys_str_mv AT nikitapalod redefiningtheapplicationofanevolutionaryalgorithmfortheoptimalpipesizingproblem
AT vishnuprasad redefiningtheapplicationofanevolutionaryalgorithmfortheoptimalpipesizingproblem
AT ruchikhare redefiningtheapplicationofanevolutionaryalgorithmfortheoptimalpipesizingproblem
_version_ 1718444032955252736