Acnn-Bilstmbased Deep Learning Model For Mid-Term Solar Radiation Prediction

The penetrations of solar power plants are increasing their presence worldwide. The solar power plants have uncertain power output as its output depends on solar radiation, which is environmental dependent, so solar radiation prediction is a crucial step in integrating these plants into the power grid. In this work, a convolution neural network (CNN) and bi-direction long short term memory (BiLSTM) based hybrid deep learning (DL) model is proposed for effective midterm solar radiation prediction. The CNN architecture in this model captures the feature in solar radiation input data, and BiLSTM exploits the dependencies of this time series data. The proposed model is tested for three different geographical locations on the same latitude as it receives approximately the same solar radiation. The proposed hybrid DL model is compared with different recently proposed DL models. Moreover, distribution errors such as, skew and kurtosis errors are included for evaluating the distribution of predicted solar radiation. The outcome shows that the proposed hybrid DL model is robust and further enhancing the recently proposed DL models for midterm solar radiation prediction.