A Machine Learning Framework for Prediction Interval based Technique for Short-Term Solar Energy Forecast

The stochastic nature of photovoltaic (PV) power generation can have significant impacts on the power grid stability and reliability. Hence, it is essential to have an accurate forecasting of the PV power generation. In this paper, a new machine learning (ML) framework is presented for short-term solar energy forecast based on prediction interval (PI) technique. Simulation results conducted show how PI is more reliable and accurate as compared to deterministic methods using evaluation metrics.