Selection of Temporal Lags for Predicting Riverflow Series from Hydroelectric Plants Using Variable Selection Methods

• Published in: Energies (Basel) Vol. 13; no. 16; p. 4236
• Main Authors: Siqueira, Hugo, Macedo, Mariana, Tadano, Yara de Souza, Alves, Thiago Antonini, Stevan, Sergio L., Oliveira, Domingos S., Marinho, Manoel H.N., Neto, Paulo S.G. de Mattos, Oliveira, João F. L. de, Luna, Ivette, Filho, Marcos de Almeida Leone, Sarubbo, Leonie Asfora, Converti, Attilio
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-08-2020
• Subjects: Accuracy; Alternative energy sources; autoregressive model; Autoregressive models; bio-inspired metaheuristics extreme learning machines neural networks; Computer applications; Electric filters; Electric power; Electric power generation; Electricity distribution; Feature selection; Filters; Fluid filters; Forecasting; Genetic algorithms; Hydroelectric plants; Hydroelectric power; Learning algorithms; Linear filters; Model accuracy; monthly forecasting; Neural networks; Nonlinear filters; Optimization; Power plants; Principal components analysis; River flow; Stream discharge; Stream flow; Time series; Variables; wrapper; Brazil; Canada; United States > US; China
• DOI: 10.3390/en13164236
• EISSN: 1996-1073

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.