Abstract
Solar energy's probabilistic and changeable nature raises serious challenges about ensuring dependable, cheap, and secure control of power energy networks through the usage of solar energy globally for a green and efficient society. The most recent advancements in renewable energy have provided new insights on how to overcome the limits of various power sources. It is critical to correctly estimate statistics in order to ensure that energy PV systems be used to their full potential. The ability to predict changes in sun irradiation with greater accuracy could help to improve service quality. This combination of solar electricity and precision forecasting can help with distribution and planning. Emerging technologies such as artificial intelligence and machine learning, which are designed primarily to cope with difficulties related to renewable source intermittency and ambiguity, represent a possibility to address these issues. This paper analyses the integration of artificial intelligence in many sectors of renewable power systems, such as the forecasting of the realistic model employed by AI.To forecast solar energy via Artificial Neural Networks (ANN), SVM, and Random Forest we offer three distinct types of solar prediction algorithms (RF). The results showed that our approach obtained MAE = 0.9558 (Training phase), 1.7853 (Testing phase) and MFE = 0.4456 (Training phase), 0.5621 (Testing phase) outstanding per-formance for artificial neural network algorithm compared to SVM and RF algorithm.