Domain adaptation framework for PV power forecasting

A team of researchers have developed a domain adaption framework capable of transferring knowledge from solar power plants with abundant data to plants that need to be trained without labelled data. The framework has been tested at three solar power sites in Germany and was found to perform better than reference models.Researchers from Germany's Constructor University have developed a novel unsupervised domain adaptation framework for solar power forecasting. Their technique learns transferable features from one solar plant with abundant data, and transfers this knowledge to another solar power ...

Den vollständigen Artikel lesen ...