Performance Analysis of Regression Models in Solar PV Forecasting

Solar energy is increasingly becoming one of the promising sources of renewable energy for versatile purposes including residential and commercial applications. Forecasting of the power output of solar photovoltaic (PV) systems with high accuracy in the short term is of significant importance for production, delivery, and storage in the energy market. This work aims to produce reliable short-term forecasting using machine learning methods such as Linear Regression, Random Forest Regression, and Decision Tree Regression. Results show 99% percent accuracy for the proposed models. The work also detects faults and abnormalities occurring in Solar PV panels with the help of results thereby enhancing the production.