LAPSE:2023.26403
Published Article
LAPSE:2023.26403
Neural-Based Ensembles and Unorganized Machines to Predict Streamflow Series from Hydroelectric Plants
April 3, 2023
Abstract
Estimating future streamflows is a key step in producing electricity for countries with hydroelectric plants. Accurate predictions are particularly important due to environmental and economic impact they lead. In order to analyze the forecasting capability of models regarding monthly seasonal streamflow series, we realized an extensive investigation considering: six versions of unorganized machines—extreme learning machines (ELM) with and without regularization coefficient (RC), and echo state network (ESN) using the reservoirs from Jaeger’s and Ozturk et al., with and without RC. Additionally, we addressed the ELM as the combiner of a neural-based ensemble, an investigation not yet accomplished in such context. A comparative analysis was performed utilizing two linear approaches (autoregressive model (AR) and autoregressive and moving average model (ARMA)), four artificial neural networks (multilayer perceptron, radial basis function, Elman network, and Jordan network), and four ensembles. The tests were conducted at five hydroelectric plants, using horizons of 1, 3, 6, and 12 steps ahead. The results indicated that the unorganized machines and the ELM ensembles performed better than the linear models in all simulations. Moreover, the errors showed that the unorganized machines and the ELM-based ensembles reached the best general performances.
Estimating future streamflows is a key step in producing electricity for countries with hydroelectric plants. Accurate predictions are particularly important due to environmental and economic impact they lead. In order to analyze the forecasting capability of models regarding monthly seasonal streamflow series, we realized an extensive investigation considering: six versions of unorganized machines—extreme learning machines (ELM) with and without regularization coefficient (RC), and echo state network (ESN) using the reservoirs from Jaeger’s and Ozturk et al., with and without RC. Additionally, we addressed the ELM as the combiner of a neural-based ensemble, an investigation not yet accomplished in such context. A comparative analysis was performed utilizing two linear approaches (autoregressive model (AR) and autoregressive and moving average model (ARMA)), four artificial neural networks (multilayer perceptron, radial basis function, Elman network, and Jordan network), and four ensembles. The tests were conducted at five hydroelectric plants, using horizons of 1, 3, 6, and 12 steps ahead. The results indicated that the unorganized machines and the ELM ensembles performed better than the linear models in all simulations. Moreover, the errors showed that the unorganized machines and the ELM-based ensembles reached the best general performances.
Record ID
Keywords
artificial neural networks, Box-Jenkins models, ensemble, monthly seasonal streamflow series forecasting
Suggested Citation
Belotti J, Siqueira H, Araujo L, Stevan SL Jr, de Mattos Neto PS, Marinho MHN, de Oliveira JFL, Usberti F, Leone Filho MDA, Converti A, Sarubbo LA. Neural-Based Ensembles and Unorganized Machines to Predict Streamflow Series from Hydroelectric Plants. (2023). LAPSE:2023.26403
Author Affiliations
Belotti J: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil; Institute of Computing, State University of Campinas (UNICAMP), Campinas 13083-852, Brazil [ORCID]
Siqueira H: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil [ORCID]
Araujo L: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil
Stevan SL Jr: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil [ORCID]
de Mattos Neto PS: Departamento de Sistemas de Computação, Centro de Informática, Universidade Federal de Pernambuco, (UFPE), Recife 50740-560, Brazil [ORCID]
Marinho MHN: Polytechnic School of Pernambuco, University of Pernambuco, Recife 50100-010, Brazil [ORCID]
de Oliveira JFL: Polytechnic School of Pernambuco, University of Pernambuco, Recife 50100-010, Brazil [ORCID]
Usberti F: Institute of Computing, State University of Campinas (UNICAMP), Campinas 13083-852, Brazil [ORCID]
Leone Filho MDA: Venidera Pesquisa e Desenvolvimento, Campinas 13070-173, Brazil [ORCID]
Converti A: Department of Civil, Chemical and Environmental Engineering, University of Genoa (UNIGE), 16126 Genoa, Italy [ORCID]
Sarubbo LA: Department of Biotechnology, Catholic University of Pernambuco (UNICAP), Recife 50050-900, Brazil; Advanced Institute of Technology and Innovation (IATI), Recife 50751-310, Brazil [ORCID]
Siqueira H: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil [ORCID]
Araujo L: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil
Stevan SL Jr: Graduate Program in Computer Sciences, Federal University of Technology−Parana (UTFPR), Ponta Grossa 84017-220, Brazil [ORCID]
de Mattos Neto PS: Departamento de Sistemas de Computação, Centro de Informática, Universidade Federal de Pernambuco, (UFPE), Recife 50740-560, Brazil [ORCID]
Marinho MHN: Polytechnic School of Pernambuco, University of Pernambuco, Recife 50100-010, Brazil [ORCID]
de Oliveira JFL: Polytechnic School of Pernambuco, University of Pernambuco, Recife 50100-010, Brazil [ORCID]
Usberti F: Institute of Computing, State University of Campinas (UNICAMP), Campinas 13083-852, Brazil [ORCID]
Leone Filho MDA: Venidera Pesquisa e Desenvolvimento, Campinas 13070-173, Brazil [ORCID]
Converti A: Department of Civil, Chemical and Environmental Engineering, University of Genoa (UNIGE), 16126 Genoa, Italy [ORCID]
Sarubbo LA: Department of Biotechnology, Catholic University of Pernambuco (UNICAP), Recife 50050-900, Brazil; Advanced Institute of Technology and Innovation (IATI), Recife 50751-310, Brazil [ORCID]
Journal Name
Energies
Volume
13
Issue
18
Article Number
E4769
Year
2020
Publication Date
2020-09-12
ISSN
1996-1073
Version Comments
Original Submission
Other Meta
PII: en13184769, Publication Type: Journal Article
Record Map
Published Article
LAPSE:2023.26403
This Record
External Link
https://doi.org/10.3390/en13184769
Publisher Version
Download
Meta
Record Statistics
Record Views
181
Version History
[v1] (Original Submission)
Apr 3, 2023
Verified by curator on
Apr 3, 2023
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2023.26403
Record Owner
Auto Uploader for LAPSE
Links to Related Works
(0.36 seconds) 0.05 + 0.02 + 0.16 + 0.06 + 0 + 0.02 + 0.01 + 0 + 0.01 + 0.02 + 0 + 0