Solar radiation and wind speed forecasting using deep learning technique

Solar radiation and wind speed are the fundamental parameters for the design and operations of solar and wind energy systems. Renewable energy sources (RESs) are intermittent and dependent on different atmospheric parameters. Therefore, it is crucial to accurately forecast RESs, such as solar radiation and wind speed. In this study, a deep learning-based random forest technique is proposed to predict solar radiation and wind speed. A novel coot algorithm (CA) is suggested to optimize the number of decision trees of the random forest model, and the performance of the CA is compared with the existing particle swarm optimization (PSO) technique. The results show that the performance of CA is better than PSO