Articles | Volume 45
Adv. Geosci., 45, 13–17, 2018
Adv. Geosci., 45, 13–17, 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.

Related authors

Cirrus cloud retrieval with MSG/SEVIRI using artificial neural networks
Johan Strandgren, Luca Bugliaro, Frank Sehnke, and Leon Schröder
Atmos. Meas. Tech., 10, 3547–3573,,, 2017
Short summary

Cited articles

Delle Monache, L., Nipen, T., Liu, Y., Roux, G., and Stull, R.: Kalman filter and analog schemes to postprocess numerical weather predictions, Mon. Weather Rev., 139, 3554–3570, 2011. a
Hersbach, H.: Decomposition of the continuous ranked probability score for ensemble prediction systems, Weather Forecast., 15, 559–570, 2000. a
Junk, C., Delle Monache, L., Alessandrini, S., Cervone, G., and von Bremen, L.: Predictor-weighting strategies for probabilistic wind power forecasting with an analog ensemble, Meteorol. Z., 24, 361–379, 2015. a
Riedmiller, M. and Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm, in: Proc. of IEEE International Conference on Neural Networks, IEEE, 28 March–1 April 1993, San Francisco, CA, USA, 586–591,, 1993. a
Schmidhuber, J.: Deep learning in neural networks: An overview, Neural networks, 61, 85–117, 2015. a
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.