Satellite solar radiation forecasting by next-frame prediction — Advances and future opportunities
Angela Meyer (Bern University of Applied Sciences, TU Delft - Civil Engineering & Geosciences)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Solar radiation forecasting is essential for operating energy systems with high shares of photovoltaic power generation as solar radiation can fluctuate rapidly with cloud cover and atmospheric conditions. Accurate solar forecasts help utilities and grid operators schedule reserves, balance supply and demand, and reduce reliance on fossil backup. Skilful solar forecasts also support energy market operations, battery control, and congestion management by predicting when and where solar generation will increase or drop. Classic weather prediction models struggle with long forecast latency times, timely assimilation of the latest satellite observations, spatial resolution, and low forecast update frequencies. Satellite-based solar forecast models can outperform classic forecast models for lead times of up to several hours. We review spatiotemporal solar forecast models that leverage satellite observations and machine learning for accurate solar intraday forecasts based on next-frame prediction. We discuss recent progress in this field, opportunities, challenges, and future research directions.
help_outline