Forecasting Solar Irradiance Using Machine Learning Methods

Abstract

Solar generation must be integrated into the power system to meet rising energy demand and reduce dependency on fossil fuels. The intermittent nature of solar energy output threatens the grid's stability and efficient functioning. Accurate solar power forecasting is essential to ensure the proper operation of the grid and the suitable placement of storage resources. In this work, we thoroughly investigate machine learning-based short-term solar irradiance forecasting. We assess how well several models-including gradient boosting regression, random forest, and KNN-perform using data from Izmir, Turkey. Our findings demonstrate that machine learning approaches outperform conventional time series models, with the KNN and random forest models generally demonstrating the highest performance. The suggested model may be applied practically in solar power plants and expanded to anticipate power production by incorporating pertinent input variables. Our research sheds light on the potential of machine learning methods for forecasting solar irradiance. It emphasizes the significance of precise forecasting for the reliability and efficient functioning of the electricity grid. Future studies can examine various feature engineering techniques and determine how machine learning models perform over extended periods.