Predicting variability of horizontal surface solar irradiance using machine learning
- Renewable energies play an increasingly important role for energy production in Europe. Unlike coal or gas powerplants, solar energy production is highly variable in space and time. This is due to the strong variability of cloudsand their influence on the surface solar irradiance. Especially in regions with large contribution from photovoltaicpower production, the intermittent energy feed-in to the power grid can be a risk for grid stability. Therefore goodforecasts of temporal and spatial variability of surface irradiance are necessary to be able to properly regulate thepower supply.
Document Type: | Conference Object |
---|---|
Language: | English |
Author: | Felix Gödde, Bernhard Mayer, Tobias Zinner, Jonas Witthuhn, Hartwig Deneke, Christopher Schirrmeister |
Parent Title (English): | EMS Annual Meeting Abstracts |
Volume: | 16 |
Article Number: | 796-1 |
URN: | urn:nbn:de:hbz:1044-opus-49959 |
Publisher: | Copernicus |
Place of publication: | Göttingen |
Publishing Institution: | Hochschule Bonn-Rhein-Sieg |
Date of first publication: | 2019/09/11 |
Copyright: | © Author(s) 2019. CC Attribution 4.0 License. |
Note: | EMS Annual Meeting: European Conference for Applied Meteorology and Climatology 2019, Copenhagen, Denmark, 9-13 September 2019 |
Departments, institutes and facilities: | Fachbereich Ingenieurwissenschaften und Kommunikation |
Internationales Zentrum für Nachhaltige Entwicklung (IZNE) | |
Projects: | MetPVNet - Entwicklung innovativer satellitengestützter Methoden zur verbesserten PV-Ertragsvorhersage auf verschiedenen Zeitskalen für Anwendungen auf Verteilnetzebene (DE/BMWi/0350009A) |
Dewey Decimal Classification (DDC): | 5 Naturwissenschaften und Mathematik / 55 Geowissenschaften, Geologie / 551 Geologie, Hydrologie, Meteorologie |
Entry in this database: | 2020/07/22 |
Licence (German): | ![]() |