Modeling and predicting the electricity production in hydropower using conjunction of wavelet transform, long short-term memory and random forest models. (June 2021)

• Record Type: Journal Article
• Authors: Zolfaghari, Mehdi; Golabi, Mohammad Reza
• Is Part Of: Renewable energy. Volume 170(2021)
• Page Start: 1367
• Page End: 1381
• Publication Date: 2021-06
• Subjects: Hydropower -- Wavelet transform -- Long short-term memory -- RF Algorithm; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2021.02.017
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: Electricity is an important pillar for the economic growth and the development of societies. Surveying and predicting the electricity production (EP) is a valuable factor in the hands of electricity industry managers to make strategic decisions, especially if electricity is generated by renewable resources for environmental considerations. However, because the EP series is non-stationary and nonlinear, traditional methods are less robust to predict it. In this study, we offer a hybrid model which combines adaptive wavelet transform (AWT), long short-term memory (LSTM) and random forest (RF) algorithm (AWT-LSTM-RF) to predict the EP in hydroelectric power plant. We also apply the exogenous affecting variables on EP in the structure of hybrid model, which were selected by ant colony optimization (ACO) algorithm. To evaluate the predictive power of the AWT-LSTM-RF model, we compared its predictive results with the benchmark models including RF, ARIMA-GARCH, wavelet transform-feed forward neural network (WT-FFNN), wavelet transform-random forest (WT-RF), wavelet transform-LSTM (WT-LSTM), and WT-FFNN-RF. The empirical results indicate that the hybrid model of AWT-LSTM-RF outperforms the benchmark models. The results also suggest that applying the wavelet transform on input data of the RF algorithm (WT-RF) can improve the predictive power of the RF. Highlights: A hybrid model which combines AWT, LSTM and RF is proposed for EP prediction in hydroelectric power plant. The optimal input combination is selected via ACO algorithm and finalized via RF algorithm. An adaptive layer is added into structure of WT-LSTM to increase forecast accuracy. The predicted values of the sub-signals via RF are integrated nonlinearly to get the final output. AWT-LSTM-RF outperforms the benchmark models including RF, ARIMA-GARCH, WT-FFNN, WT-RF, WT-LSTM, and WT- FFNN-RF.