Deep Neural Networks for Predicting Solar Radiation at Hail Region, Saudi Arabia

• Published in: IEEE access Vol. 9; pp. 36719 - 36729
• Main Authors: Boubaker, Sahbi, Benghanem, Mohamed, Mellit, Adel, Lefza, Ayoub, Kahouli, Omar, Kolsi, Lioua
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aeronautics; Air temperature; Aridity; Artificial neural networks; Atmospheric models; BiGRU; BiLSTM; CNN; CNN-BiLSTM; CNN-LSTM; Correlation coefficients; Data models; deep learning; Distribution functions; Forecasting; Global horizontal irradiation; GRU; Hail; Logic gates; LSTM; Meteorology; Model accuracy; Neural networks; Parameters; Performance evaluation; Photovoltaic cells; prediction; Prediction algorithms; Prediction models; Predictive models; Programming languages; Radiation effects; recurrent neural networks; Relative humidity; Solar radiation; Weather; Wind direction; Wind speed; Saudi Arabia
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3062205

Forecasted global horizontal irradiation (GHI) can help for designing, sizing and performances analysis of photovoltaic (PV) systems including water PV pumping systems used for irrigation applications. In this paper, various deep neural networks (DNN) models for one day-ahead prediction of GHI at Hail city (Saudi Arabia) are developed and investigated. The considered DNN models include long-short-term memory (LSTM), bidirectional-LSTM (BiLSTM), gated recurrent unit (GRU), bidirectional-GRU (Bi-GRU), one-dimensional convolutional neural network (CNN 1D ) and other hybrid configurations such as CNN-LSTM and CNN-BiLSTM. A dataset of daily GHI recordings collected during January 1, 2000 to June 30, 2020 from National Aeronautics and Space Administration (NASA) at an arid location (Hail, Saudi Arabia) is used to develop and compare the above DNN-based models. The parameters affecting the accuracy of the models have been also deeply analyzed. Only historical values of daily GHI have been used to build the DNN-based models whereas additional weather parameters such as air temperature, wind speed, wind direction, atmospheric pressure and relative humidity are not considered in this work. Keras library and Python language have been used to develop and compare the GHI forecasting models. The evaluation metrics such as correlation coefficient (<inline-formula> <tex-math notation="LaTeX">r </tex-math></inline-formula>), Mean Absolute Percent Error (MAPE), Mean Absolute Error (MAE), cumulative distribution function (CDF) and standard deviation (<inline-formula> <tex-math notation="LaTeX">\sigma </tex-math></inline-formula>) are opted to evaluate the performance of the prediction models. The obtained results showed that the DNN models have provided globally good performances with a maximum reached value of <inline-formula> <tex-math notation="LaTeX">r=96 </tex-math></inline-formula>%, for daily GHI forecasting.