Solar Irradiance Prediction Interval Estimation and Deterministic Forecasting Model Using Ground-based Sky Image

Abstract

Due to the explosive penetration of photovoltaic (PV) systems in the power grid, accurate and well-informed solar PV power forecasting has become extraordinarily crucial, while accurate irradiance prediction is the basis of PV power forecasting. Yet most research on PV power/irradiance forecasting focus on deterministic forecasting, whereas it is difficult to express the credibility of the forecasting results, especially in the scene of instantaneous fluctuation of irradiance and photovoltaic power caused by cloud movement. Therefore, in this paper, we use the ground-based sky image to accurately estimate and track the rapid fluctuation of solar irradiance and meanwhile considers the uncertain constrained optimization problem to establish a high-quality joint point-interval real-time estimation model, which can not only provide the result points from deterministic forecasting, but also achieve the prediction intervals. The results show that the model can produce tight intervals while simultaneously achieving deterministic forecasting results of high quality and strong robustness, regardless of the weather conditions. Besides, compared with the traditional way of taking the middle position of the interval as the deterministic forecasting result, the performance of our model is greatly enhanced.