Comparison of Monte Carlo Algorithm, genetic algorithms and artificial neural networks for calibration of water supply networks using the epanet2toolkit

A comparison of three water network calibration algorithms was performed using the R epanet2toolkit library. This coupling makes it possible to explore EPANET's hydraulic simulation and evaluation potentials and data analysis in R, with the main result of the work being the comparison of three...

Full description

Saved in:
Bibliographic Details
Published inRevista Ibero-Americana de Ciências Ambientais Vol. 13; no. 9; pp. 72 - 84
Main Authors Barbedo, Matheus David Guimarães, Silva, Fernando das Graças Braga da, Silva, Alex Takeo Yasumura Lima, Marques, Sara Maria, Valério, Victor Eduardo de Mello, Marcondes, Mateus Cortez
Format Journal Article
LanguageEnglish
Published 08.01.2023
Online AccessGet full text
ISSN2179-6858
2179-6858
DOI10.6008/CBPC2179-6858.2022.009.0006

Cover

Abstract A comparison of three water network calibration algorithms was performed using the R epanet2toolkit library. This coupling makes it possible to explore EPANET's hydraulic simulation and evaluation potentials and data analysis in R, with the main result of the work being the comparison of three calibration methods. In the calibration process by the Monte Carlo Algorithm, 100,000 roughness values ​​were randomly generated for each pipe section within the range of 0.008 to 0.09 and new pressure values ​​were generated with these roughnesses, while the calibration by the Genetic Algorithms method was used the rpy2 package that allows the use of R in Python, having 10,000 generations per simulation with 5% chance of mutation and 50% chance of crossover, admitting a deviation of ± 2 m.c.a for each pressure and the reduction of the average error. Finally, the Neural Network calibration also used the rpy2 package, with the network demand defined as the input layer and the output layer as the roughness of the pipes and for the hidden layer the input layer plus four neurons was defined. The results showed that in the smallest network the best performance was obtained by the Genetic Algorithms, followed by Monte Carlo, while the Neural Network had the worst result, and in the most complex network the Neural Network results obtained the best result, followed by the Genetic Algorithms and Monte Carlo. Thus, the potential of using Neural Networks for the calibration of more complex networks is observed, as well as its use combined with optimization techniques for the operation of water distribution networks, taking care to avoid situations of overfitting or underfitting. Uma comparação de três algoritmos de calibração de rede de água foi realizada usando a biblioteca R epanet2toolkit. Este acoplamento permite explorar os potenciais de simulação e avaliação hidráulica do EPANET e análise de dados em R, tendo como principal resultado do trabalho a comparação de três métodos de calibração. No processo de calibração pelo Algoritmo de Monte Carlo, foram gerados aleatoriamente 100.000 valores de rugosidade para cada seção de tubo na faixa de 0,008 a 0,09 e novos valores de pressão foram gerados com essas rugosidades, enquanto a calibração pelo método de Algoritmos Genéticos foi utilizado o pacote rpy2 que permite o uso de R em Python, tendo 10.000 gerações por simulação com 5% de chance de mutação e 50% de chance de crossover, admitindo um desvio de ± 2 m.c.a para cada pressão e a redução do erro médio. Por fim, a calibração da Rede Neural também utilizou o pacote rpy2, com a demanda da rede definida como a camada de entrada e a camada de saída como a rugosidade dos tubos e para a camada oculta foi definida a camada de entrada mais quatro neurônios. Os resultados mostraram que na rede menor o melhor desempenho foi obtido pelos Algoritmos Genéticos, seguido de Monte Carlo, enquanto a Rede Neural teve o pior resultado, e na rede mais complexa os resultados da Rede Neural obtiveram o melhor resultado, seguido da Rede Neural. Algoritmos Genéticos e Monte Carlo. Assim, observa-se o potencial de utilização de Redes Neurais para calibração de redes mais complexas, bem como sua utilização aliada a técnicas de otimização para operação de redes de distribuição de água, tomando-se o cuidado de evitar situações de overfitting ou underfitting.
AbstractList A comparison of three water network calibration algorithms was performed using the R epanet2toolkit library. This coupling makes it possible to explore EPANET's hydraulic simulation and evaluation potentials and data analysis in R, with the main result of the work being the comparison of three calibration methods. In the calibration process by the Monte Carlo Algorithm, 100,000 roughness values ​​were randomly generated for each pipe section within the range of 0.008 to 0.09 and new pressure values ​​were generated with these roughnesses, while the calibration by the Genetic Algorithms method was used the rpy2 package that allows the use of R in Python, having 10,000 generations per simulation with 5% chance of mutation and 50% chance of crossover, admitting a deviation of ± 2 m.c.a for each pressure and the reduction of the average error. Finally, the Neural Network calibration also used the rpy2 package, with the network demand defined as the input layer and the output layer as the roughness of the pipes and for the hidden layer the input layer plus four neurons was defined. The results showed that in the smallest network the best performance was obtained by the Genetic Algorithms, followed by Monte Carlo, while the Neural Network had the worst result, and in the most complex network the Neural Network results obtained the best result, followed by the Genetic Algorithms and Monte Carlo. Thus, the potential of using Neural Networks for the calibration of more complex networks is observed, as well as its use combined with optimization techniques for the operation of water distribution networks, taking care to avoid situations of overfitting or underfitting. Uma comparação de três algoritmos de calibração de rede de água foi realizada usando a biblioteca R epanet2toolkit. Este acoplamento permite explorar os potenciais de simulação e avaliação hidráulica do EPANET e análise de dados em R, tendo como principal resultado do trabalho a comparação de três métodos de calibração. No processo de calibração pelo Algoritmo de Monte Carlo, foram gerados aleatoriamente 100.000 valores de rugosidade para cada seção de tubo na faixa de 0,008 a 0,09 e novos valores de pressão foram gerados com essas rugosidades, enquanto a calibração pelo método de Algoritmos Genéticos foi utilizado o pacote rpy2 que permite o uso de R em Python, tendo 10.000 gerações por simulação com 5% de chance de mutação e 50% de chance de crossover, admitindo um desvio de ± 2 m.c.a para cada pressão e a redução do erro médio. Por fim, a calibração da Rede Neural também utilizou o pacote rpy2, com a demanda da rede definida como a camada de entrada e a camada de saída como a rugosidade dos tubos e para a camada oculta foi definida a camada de entrada mais quatro neurônios. Os resultados mostraram que na rede menor o melhor desempenho foi obtido pelos Algoritmos Genéticos, seguido de Monte Carlo, enquanto a Rede Neural teve o pior resultado, e na rede mais complexa os resultados da Rede Neural obtiveram o melhor resultado, seguido da Rede Neural. Algoritmos Genéticos e Monte Carlo. Assim, observa-se o potencial de utilização de Redes Neurais para calibração de redes mais complexas, bem como sua utilização aliada a técnicas de otimização para operação de redes de distribuição de água, tomando-se o cuidado de evitar situações de overfitting ou underfitting.
Author Silva, Fernando das Graças Braga da
Marques, Sara Maria
Marcondes, Mateus Cortez
Silva, Alex Takeo Yasumura Lima
Valério, Victor Eduardo de Mello
Barbedo, Matheus David Guimarães
Author_xml – sequence: 1
  givenname: Matheus David Guimarães
  orcidid: 0000-0001-9261-3696
  surname: Barbedo
  fullname: Barbedo, Matheus David Guimarães
– sequence: 2
  givenname: Fernando das Graças Braga da
  orcidid: 0000-0002-3803-2257
  surname: Silva
  fullname: Silva, Fernando das Graças Braga da
– sequence: 3
  givenname: Alex Takeo Yasumura Lima
  orcidid: 0000-0003-1883-2414
  surname: Silva
  fullname: Silva, Alex Takeo Yasumura Lima
– sequence: 4
  givenname: Sara Maria
  orcidid: 0000-0003-3713-9607
  surname: Marques
  fullname: Marques, Sara Maria
– sequence: 5
  givenname: Victor Eduardo de Mello
  orcidid: 0000-0003-4127-5951
  surname: Valério
  fullname: Valério, Victor Eduardo de Mello
– sequence: 6
  givenname: Mateus Cortez
  orcidid: 0000-0003-2812-784X
  surname: Marcondes
  fullname: Marcondes, Mateus Cortez
BookMark eNptkdtOwzAMhiMEEmPsHSJxS0fSQ9oKbkbFSRqCC7iu3DTdwrKkSlJNexMel5YxQIILy5bt_5f8-QQdaqMFQmeUTBkh2UVx_VyENM0DliXZNCRhOCUk74OwAzT6nhz-qo_RxLm3foNkhMQ5GaH3wqxbsNIZjU2DH432AhdglcEztTBW-uX6HC-EFl5yDPuWw6BrDNbLRnIJCmvR2c_kN8auHG6MxRyUrCx4ufPegBcWu65t1fZnsXNSL7BfCixa6LuhN0atpD9FRw0oJyZfeYxeb29eivtg_nT3UMzmAackYQFreJWynCVxxOOE1nEaiRrqijcVa-I6rHnN0owmgmY8ohxiHkNWs4r110d5QqMxutr5drqF7QaUKlsr12C3JSXlALrkVcsHhOWAsBxAlz3ocgDdyy93cm6Nc1Y0f9T7N_2n_gDziYpK
ContentType Journal Article
DBID AAYXX
CITATION
ADTOC
UNPAY
DOI 10.6008/CBPC2179-6858.2022.009.0006
DatabaseName CrossRef
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
Database_xml – sequence: 1
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Environmental Sciences
EISSN 2179-6858
EndPage 84
ExternalDocumentID 10.6008/cbpc2179-6858.2022.009.0006
10_6008_CBPC2179_6858_2022_009_0006
GroupedDBID 91A
AAYXX
ABDHV
ALMA_UNASSIGNED_HOLDINGS
CITATION
ML.
M~E
OK1
ADTOC
UNPAY
ID FETCH-LOGICAL-c1056-6fcb7696543c451d473edadbcfb6f4d2dcd67815e18c31ca4c4a8d6b649039513
IEDL.DBID UNPAY
ISSN 2179-6858
IngestDate Tue Aug 19 23:35:12 EDT 2025
Wed Oct 01 06:01:37 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 9
Language English
License http://creativecommons.org/licenses/by-nc-nd/4.0
cc-by-nc-nd
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1056-6fcb7696543c451d473edadbcfb6f4d2dcd67815e18c31ca4c4a8d6b649039513
ORCID 0000-0003-2812-784X
0000-0003-1883-2414
0000-0001-9261-3696
0000-0003-3713-9607
0000-0002-3803-2257
0000-0003-4127-5951
OpenAccessLink https://proxy.k.utb.cz/login?url=https://sustenere.inf.br/index.php/rica/article/download/7633/4580
PageCount 13
ParticipantIDs unpaywall_primary_10_6008_cbpc2179_6858_2022_009_0006
crossref_primary_10_6008_CBPC2179_6858_2022_009_0006
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-01-08
PublicationDateYYYYMMDD 2023-01-08
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-01-08
  day: 08
PublicationDecade 2020
PublicationTitle Revista Ibero-Americana de Ciências Ambientais
PublicationYear 2023
SSID ssj0000800490
Score 2.2088661
Snippet A comparison of three water network calibration algorithms was performed using the R epanet2toolkit library. This coupling makes it possible to explore...
SourceID unpaywall
crossref
SourceType Open Access Repository
Index Database
StartPage 72
Title Comparison of Monte Carlo Algorithm, genetic algorithms and artificial neural networks for calibration of water supply networks using the epanet2toolkit
URI https://sustenere.inf.br/index.php/rica/article/download/7633/4580
UnpaywallVersion publishedVersion
Volume 13
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2179-6858
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800490
  issn: 2179-6858
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3PT9swFLZYkbbTNrahgUZliR2XZnFs1zmWqBVCKuKwSuwU-VcYIkuqJBViB_4O_lzea9NSbTvBKZJjR07y2e97tt_3CPkaCWV4EutgqJkLeB7zIBkyHhgLvoDKzVA63NGdnsvTGT-7FJdbsTANePiot-yRdw5MHS5FA1EpIsR5Iey-Z-hQSr7SLoTxEYdcKHDbd6UAPt4ju7Pzi9FPzCoHaAtQYP01OYbZAWy7Cq2Z2005-IcMBTtRsxJzHm2ZpjeLcq7vbnVRbNmbyTti1z1dHTO5GSxaM7B__hJxfNmrvCdvOzpKR6tKe2THlx_I_vgp-g1udsO_-Uge0k3WQlrldIrKVjTVdVHRUXFV1dftr9_fKEASIyOpXhc1VJeOYkdWchUURTSXl-UR9IYCcaaAFfTcESf47FvgwDVtMOfo3VNFPKV_RYGzUrCiUMraqipurttPZDYZ_0hPgy61Q2CB0MlA5hZgkGBgq-UicnwYe6edsbmROXfMWQdWNBI-UjaOrOaWa-WkkTz5HgMpjPdJr6xK_5lQJXNcyEUqK7hOokSJ3DDvPTOMKZ8cEL7-q9l8peCRgeeDYMjSk4sUwZAhGDIEQwZgwA15eUDEBgH_tFuD6D_tDp_Z7gvptfXCHwHFaU2fvJrej_sdkh8B3rL_qA
linkProvider Unpaywall
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT-MwELVQK7EnYD8QRbvI0u5x0xDHdp1jNypCK4E4bCX2FPkrgAhJlaRC8Ev4uTvTpqUCTuwpkmNHTvLseWN73hDyIxLK8CTWwUgzF_A85kEyYjwwFnwBlZuRdLije3YuT6f896W43IiFacDDR71lj7xzaOpwIRqIShEhzgth9z1Dh1LylXYhjI845EKB296XAvh4j_Sn5xfjv5hVDtAWoMD6NvkOswPYdhVaM7PrcvAPGQp2omYl5jzaME0f5uVMP9zrotiwNye7xK56ujxmcjuct2ZoH1-IOP7fq-yRnY6O0vGy0key5ctPZH_yHP0GN7vh33wmT-k6ayGtcnqGylY01XVR0XFxVdU37fXdTwqQxMhIqldFDdWlo9iRpVwFRRHNxWVxBL2hQJwpYAU9d8QJPvseOHBNG8w5-vBcEU_pX1HgrBSsKJSytqqK25v2C5meTP6kp0GX2iGwQOhkIHMLMEgwsNVyETk-ir3TztjcyJw75qwDKxoJHykbR1Zzy7Vy0kieHMdACuN90iur0h8QqmSOC7lIZQXXSZQokRvmvWeGMeWTAeGrv5rNlgoeGXg-CIYs_XWRIhgyBEOGYMgADLghLwdErBHwqt0KRG-0O3xnu6-k19Zz_w0oTmuOOgz_A-U-_nc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparison+of+Monte+Carlo+Algorithm%2C+genetic+algorithms+and+artificial+neural+networks+for+calibration+of+water+supply+networks+using+the+epanet2toolkit&rft.jtitle=Revista+Ibero-Americana+de+Ci%C3%AAncias+Ambientais&rft.au=Barbedo%2C+Matheus+David+Guimar%C3%A3es&rft.au=Silva%2C+Fernando+das+Gra%C3%A7as+Braga+da&rft.au=Silva%2C+Alex+Takeo+Yasumura+Lima&rft.au=Marques%2C+Sara+Maria&rft.date=2023-01-08&rft.issn=2179-6858&rft.eissn=2179-6858&rft.volume=13&rft.issue=9&rft.spage=72&rft.epage=84&rft_id=info:doi/10.6008%2FCBPC2179-6858.2022.009.0006&rft.externalDBID=n%2Fa&rft.externalDocID=10_6008_CBPC2179_6858_2022_009_0006
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2179-6858&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2179-6858&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2179-6858&client=summon