Forecasting global solar radiation using a robust regularization approach with mixture kernels

Abstract

Accurately forecasting global solar radiation plays a key role in photovoltaic evaluations. To quantify and control the uncertainties in global solar radiation forecasting, this study developed a robust and accurate forecasting model. This was constructed in the reproducing kernel Hilbert space with a novel regularization. Global solar radiation datasets were collected from the autonomous region of Tibet in China. Experimental results demonstrate that the proposed model can quantify uncertainties and obtain more accurate forecasting compared with machine learning models.

Unlocking renewable energy potential: Harnessing machine learning and intelligent algorithms

“…In applications for renewable energy, Huber Regression is used to estimate the energy output from wind turbines and solar panels, where data may be noisy and include large outliers brought on by fast changes in meteorological circumstances. The Huber loss function balances the robustness of absolute deviation with the sensitivity of least squares; it is quadratic for small errors and linear for large errors (Huang et al, 2018;Jiang, 2023). As it guarantees that outliers do not have a disproportionate effect on the model, Huber Regression is, therefore, a reliable method for modeling and forecasting renewable energy outputs (Ibidoja et al, 2023;Lin et al, 2022).…”