Articles | Volume 45
Adv. Geosci., 45, 13–17, 2018
https://doi.org/10.5194/adgeo-45-13-2018
Adv. Geosci., 45, 13–17, 2018
https://doi.org/10.5194/adgeo-45-13-2018

  19 Jul 2018

19 Jul 2018

Probabilistic short term wind power forecasts using deep neural networks with discrete target classes

Martin Felder et al.

Viewed

Total article views: 1,848 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,484 291 73 1,848 31 33
  • HTML: 1,484
  • PDF: 291
  • XML: 73
  • Total: 1,848
  • BibTeX: 31
  • EndNote: 33
Views and downloads (calculated since 19 Jul 2018)
Cumulative views and downloads (calculated since 19 Jul 2018)

Viewed (geographical distribution)

Total article views: 1,675 (including HTML, PDF, and XML) Thereof 1,632 with geography defined and 43 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 20 Sep 2021
Download
Short summary
In current applications of short term wind power forecasts, reliability information for the forecast is important because it helps decision making. Forecast errors are often estimated using ensembles of slightly disturbed weather predictions. Since this is very computation intensive, we propose a new method: A Deep Neural Network learns how reliable to forecast is, by comparing the current weather forecast with historical forecasts and the corresponding wind power production.