Improving the accuracy of daily solar radiation prediction by climatic data using an efficient hybrid deep learning model: Long short-term memory (LSTM) network coupled with wavelet transform

Abstract

Accurate daily solar radiation prediction is a crucial task for the management and generation of solar energy as one of the alternatives to fossil fuels. In this study, the prediction accuracy of new machine learning methods, wavelet long short-term memory (WLSTM), wavelet multi-layer perceptron artificial neural network (WMLPANN), long short-term memory (LSTM), multi-layer perceptron artificial neural network (MLPANN), and multivariate adaptive regression splines (MARS), was assessed for modeling daily solar radiation using various input combinations of climatic data of maximum and minimum relative humidity, potential evapotranspiration, maximum and minimum temperature, precipitation and wind speed from two stations, Brownstown and Carbondale located in Illinois, USA. For accurate assessment of prediction accuracy of the proposed models, four reliable statistical metrics, root mean squared error (RMSE), Nash–Sutcliffe efficiency coefficient (NSE), coefficient of determination (R2), and One-Tailed Wilcoxon Signed-Rank Test were employed. Comparison of results, based on the RMSE values, indicated that the WLSTM method performed better than the WMLPANN, LSTM, MLPANN and MARS methods in the estimation of solar radiation values at both stations. The average RMSE values of WMLPANN, LSTM, MLPANN, and MARS approaches was decreased by 6%, 4%, 7.3%, and 13.5% using WLSTM method at Brownstown Station, by 6%, 5.2%, 13.2%, and 14.3% at Carbondale Station, respectively. The overall results during the testing phase of both stations revealed the successful application of hybridization of the LSTM model with the wavelet transform technique for improving the prediction accuracy of solar radiation based on climatic parameters.