The rapidly growing capacity of globally distributed solar generation systems (DSGs) has imposed new challenges for solar forecasting research: the need for high-fidelity spatial solar forecasts across utility scale areas with minimized capital, …
To fully exploit the spectral information of modern geostationary satellites, this work proposes a deep learning framework using convolutional neural networks (CNNs) and attention mechanism for 5-min ground-level global horizontal irradiance (GHI) …