Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning

 
: Vogt, Stephan; Braun, Axel; Dobschinski, Jan; Sick, Bernhard

:
Volltext urn:nbn:de:0011-n-5746276 (648 KByte PDF)
MD5 Fingerprint: a54235e7a3c56d0124cf87f2794e649e
Erstellt am: 28.1.2020


Betancourt, U. ; Energynautics GmbH, Darmstadt:
18th Wind Integration Workshop 2019 : International Workshop on Large-Scale Integration of Wind Power into Power Systems as well as on Transmission Networks for Offshore Wind Power Plants; 16-18 October 2019, Dublin, Ireland; Digital proceedings; CD-ROM
Darmstadt: Energynautics GmbH, 2019
ISBN: 978-3-9820080-5-9
9 S.
Wind Integration Workshop (WIW) <18, 2019, Dublin>
International Workshop on Large-Scale Integration of Wind Power into Power Systems as well as on Transmission Networks for Offshore Wind Power Plants <18, 2019, Dublin>
Bundesministerium fur Wirtschaft und Energie BMWi (Deutschland)
6. EFP; 0350004A; Gridcast
Erhöhung der Netzsicherheit durch flexibilisierte Wetter- und Leistungsprognosemodelle auf Basis physikalischer Hybridmethoden
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IEE ()
wind power forecasting; deep learning; transfer learning

Abstract
State-of-the-art forecasting systems are often based on single machine learning models that have been trained for individual wind farms. The data of a each wind farm is typically used exclusively for its ”own” model. This article presents two approaches with deep neural networks to make the data usable across wind farms with transfer learning. In the first case, the adaptation to individual wind farms is achieved by an separate output layer for each wind farm. With the second approach, a Bayesian wind farm embedding is proposed. An experiment with realistic forecast conditions based on power measurements and weather forecasts of 19 wind farms is carried out. The proposed techniques are compared to established single wind farm models such as random forests, gradient boosted regression trees, and simple multi layer perceptrons. Our results indicate that a significant improvement in prediction quality can be achieved using multi-task learning, especially with a short time span of historical training data.

: http://publica.fraunhofer.de/dokumente/N-574627.html