Abstract
The paradigm of renewable energy has been increasing in popularity in recent years. This is due to the acceleration of global warming and its effects that are visible quite clearly on the rising sea levels and the melting ice caps. Therefore, the governments have been providing incentives to shift to a much more renewable source of energy other than the fossil fuels that are predominant nowadays. This has led to increased applications of renewable energy that are being used by a large number of organizations and individuals. One of the most common forms of renewable energy sources is solar energy. As we know the harvesting of solar energy is purely based on the amount of solar radiation obtained on that particular given day. Hence, the early prediction of solar energy harvesting can boost the production of the same. Machine learning algorithms play an important role in the prediction mechanism. The LSTM and the CNN algorithms have been implemented in this research article on solar radiation dataset to predict the solar output. LSTM plays an important role in handling time series data which is a recurrent neural network, uses a deep learning model to predict the results. On the other hand, CNN is a deep learning neural network that efficiently handles the solar radiation prediction attributes in 1D mode. The results show both LSTM and CNN yield a good result for the parameter of root mean square error (RMSE).