Predictions of solar potential for these systems’ production are important, whether they ensure sound activity or the perfect control of an energy discharge heading to the solar system. It is important to base the prediction on solar irradiance before predicting solar systems performance. The measurement of solar radiation elements is a very significant criterion for applications of solar energy. Several globalized solar radiation prediction modes can be done in the two major categories: cloud imagery with physical models and machine learning techniques are correlated. In this paper, the methods used to predict solar radiation are explained with machine learning algorithms.