Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods
The forecasting of monthly seasonal streamflow time series is an important issue for countries where hydroelectric plants contribute significantly to electric power generation. The main step in the planning of the electric sector’s operation is to predict such series to anticipate behaviors and issu...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/16/4236 |
| _version_ | 1797557720356749312 |
|---|---|
| author | Hugo Siqueira Mariana Macedo Yara de Souza Tadano Thiago Antonini Alves Sergio L. Stevan Domingos S. Oliveira Manoel H.N. Marinho Paulo S.G. de Mattos Neto João F. L. de Oliveira Ivette Luna Marcos de Almeida Leone Filho Leonie Asfora Sarubbo Attilio Converti |
| author_facet | Hugo Siqueira Mariana Macedo Yara de Souza Tadano Thiago Antonini Alves Sergio L. Stevan Domingos S. Oliveira Manoel H.N. Marinho Paulo S.G. de Mattos Neto João F. L. de Oliveira Ivette Luna Marcos de Almeida Leone Filho Leonie Asfora Sarubbo Attilio Converti |
| author_sort | Hugo Siqueira |
| collection | DOAJ |
| description | The forecasting of monthly seasonal streamflow time series is an important issue for countries where hydroelectric plants contribute significantly to electric power generation. The main step in the planning of the electric sector’s operation is to predict such series to anticipate behaviors and issues. In general, several proposals of the literature focus just on the determination of the best forecasting models. However, the correct selection of input variables is an essential step for the forecasting accuracy, which in a univariate model is given by the lags of the time series to forecast. This task can be solved by variable selection methods since the performance of the predictors is directly related to this stage. In the present study, we investigate the performances of linear and non-linear filters, wrappers, and bio-inspired metaheuristics, totaling ten approaches. The addressed predictors are the extreme learning machine neural networks, representing the non-linear approaches, and the autoregressive linear models, from the Box and Jenkins methodology. The computational results regarding five series from hydroelectric plants indicate that the wrapper methodology is adequate for the non-linear method, and the linear approaches are better adjusted using filters. |
| first_indexed | 2024-03-10T17:21:27Z |
| format | Article |
| id | doaj.art-6f2fe753d91143b1863d358a9b45a4fd |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T17:21:27Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-6f2fe753d91143b1863d358a9b45a4fd2023-11-20T10:20:09ZengMDPI AGEnergies1996-10732020-08-011316423610.3390/en13164236Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection MethodsHugo Siqueira0Mariana Macedo1Yara de Souza Tadano2Thiago Antonini Alves3Sergio L. Stevan4Domingos S. Oliveira5Manoel H.N. Marinho6Paulo S.G. de Mattos Neto7 João F. L. de Oliveira8Ivette Luna9Marcos de Almeida Leone Filho10Leonie Asfora Sarubbo11Attilio Converti12Department of Electronics, Federal University of Technology–Parana (UTFPR), Ponta Grossa (PR) 84017-220, BrazilBioComplex Lab, Department of Computer Science, University of Exeter, Exeter EX4 4PY, UKDepartment of Mathematic, Federal University of Technology–Parana (UTFPR), Ponta Grossa (PR) 84017-220, BrazilDepartment of Mechanical Engineering, Federal University of Technology–Parana (UTFPR), Ponta Grossa (PR) 84017-220, BrazilDepartment of Electronics, Federal University of Technology–Parana (UTFPR), Ponta Grossa (PR) 84017-220, BrazilDepartamento de Sistemas de Computação, Centro de Informática, Universidade Federal de Pernambuco (UFPE), Recife (PE) 50670-901, BrazilPolytechnic School of Pernambuco, University of Pernambuco (UPE), Recife (PE) 50720-001, BrazilDepartamento de Sistemas de Computação, Centro de Informática, Universidade Federal de Pernambuco (UFPE), Recife (PE) 50670-901, BrazilPolytechnic School of Pernambuco, University of Pernambuco (UPE), Recife (PE) 50720-001, BrazilDepartment of Economic Theory, Institute of Economics, State University of Campinas (UNICAMP), Campinas (SP) 13083-857, BrazilVenidera Pesquisa e Desenvolvimento, Campinas 13070-173, BrazilDepartment of Biotechnology, Catholic University of Pernambuco (UNICAP), Recife (PE) 50050-900, BrazilDepartment of Civil, Chemical and Environmental Engineering, University of Genoa (UNIGE), 16145 Genoa, ItalyThe forecasting of monthly seasonal streamflow time series is an important issue for countries where hydroelectric plants contribute significantly to electric power generation. The main step in the planning of the electric sector’s operation is to predict such series to anticipate behaviors and issues. In general, several proposals of the literature focus just on the determination of the best forecasting models. However, the correct selection of input variables is an essential step for the forecasting accuracy, which in a univariate model is given by the lags of the time series to forecast. This task can be solved by variable selection methods since the performance of the predictors is directly related to this stage. In the present study, we investigate the performances of linear and non-linear filters, wrappers, and bio-inspired metaheuristics, totaling ten approaches. The addressed predictors are the extreme learning machine neural networks, representing the non-linear approaches, and the autoregressive linear models, from the Box and Jenkins methodology. The computational results regarding five series from hydroelectric plants indicate that the wrapper methodology is adequate for the non-linear method, and the linear approaches are better adjusted using filters.https://www.mdpi.com/1996-1073/13/16/4236monthly forecastingautoregressive modelwrapperbio-inspired metaheuristics extreme learning machines neural networks |
| spellingShingle | Hugo Siqueira Mariana Macedo Yara de Souza Tadano Thiago Antonini Alves Sergio L. Stevan Domingos S. Oliveira Manoel H.N. Marinho Paulo S.G. de Mattos Neto João F. L. de Oliveira Ivette Luna Marcos de Almeida Leone Filho Leonie Asfora Sarubbo Attilio Converti Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods Energies monthly forecasting autoregressive model wrapper bio-inspired metaheuristics extreme learning machines neural networks |
| title | Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods |
| title_full | Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods |
| title_fullStr | Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods |
| title_full_unstemmed | Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods |
| title_short | Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods |
| title_sort | selection of temporal lags for predicting riverflow series from hydroelectric plants using variable selection methods |
| topic | monthly forecasting autoregressive model wrapper bio-inspired metaheuristics extreme learning machines neural networks |
| url | https://www.mdpi.com/1996-1073/13/16/4236 |
| work_keys_str_mv | AT hugosiqueira selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT marianamacedo selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT yaradesouzatadano selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT thiagoantoninialves selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT sergiolstevan selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT domingossoliveira selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT manoelhnmarinho selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT paulosgdemattosneto selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT joaofldeoliveira selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT ivetteluna selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT marcosdealmeidaleonefilho selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT leonieasforasarubbo selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods AT attilioconverti selectionoftemporallagsforpredictingriverflowseriesfromhydroelectricplantsusingvariableselectionmethods |