Journal cover Journal topic
Wind Energy Science The interactive open-access journal of the European Academy of Wind Energy
Journal topic
Discussion papers
https://doi.org/10.5194/wes-2019-80
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-2019-80
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 07 Nov 2019

Submitted as: research article | 07 Nov 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Wind Energy Science (WES).

Model-free Estimation of Available Power using Deep Learning

Tuhfe Göçmen, Jaime Liew, Albert Meseguer Urban, and Alan Wai Hou Lio Tuhfe Göçmen et al.
  • Department of Wind Energy, Technical University of Denmark, Frederiksborgvej 399, DK-4000 Roskilde

Abstract. In order to assess the level of power reserves during down-regulation, the available power of a wind turbine needs to be estimated. The current practice in available power estimation is heavily dependent on the pre-defined performance parameters of the turbine and the curtailment strategy followed. This paper proposes a model-free approach for a single input, dynamic estimation of the available power using recurrent neural networks. The unsteady patterns in the turbulent flow are represented via Long Short-Term Memory (LSTM) neurons which are trained during a period of normal operation.

The model-free approach requires only 1-Hz wind speed measurements as the input and generates 1-Hz available power estimation as the output. The neural network is trained, tested and validated using the DTU 10 MW reference wind turbine HAWC2 model under realistic atmospheric conditions. The adaptability of the network to changing inflow conditions is ensured via transfer learning, where the last LSTM layer is updated using new measurements. It is seen that the sensitivity of the networks to changing wind speed is much higher than that of turbulence, and the updates are to be implemented solely based on the altering inflow velocity. The validation of the trained LSTM networks on time series with 7, 9 and 11 m/s mean wind speeds demonstrates high accuracy (less than 1 % bias) and capability of transfer-learning. Including highly turbulent inflow cases, the networks have shown to easily comply with the most recent grid codes, which require the quality of the available power estimations to be evaluated with high accuracy (less than 3.3 % standard deviation of the error) at 1-min intervals.

Tuhfe Göçmen et al.
Interactive discussion
Status: open (until 28 Dec 2019)
Status: open (until 28 Dec 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Tuhfe Göçmen et al.
Data sets

DTU 10MW reference turbine HAWC2 simulations for Model-free estimation of available power with deep learning training A. M. Urban, J. Liew, and T. Göçmen https://doi.org/10.5281/zenodo.3531410

Model code and software

Deep learning for available power estimation T. Göçmen, J. Liew, and A. M. Urban https://doi.org/10.5281/zenodo.3531414

Tuhfe Göçmen et al.
Viewed  
Total article views: 149 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
107 41 1 149 3 1
  • HTML: 107
  • PDF: 41
  • XML: 1
  • Total: 149
  • BibTeX: 3
  • EndNote: 1
Views and downloads (calculated since 07 Nov 2019)
Cumulative views and downloads (calculated since 07 Nov 2019)
Viewed (geographical distribution)  
Total article views: 119 (including HTML, PDF, and XML) Thereof 119 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 22 Nov 2019
Publications Copernicus
Download
Short summary
Currently, the available power estimation is heavily dependent on the pre-defined performance parameters of the turbine and the curtailment strategy followed. This paper proposes a model-free approach for a single input, dynamic estimation of the available power using RNNs. The unsteady patterns are represented by LSTM neurons, and the network is adapted to changing inflow conditions via transfer learning. Including highly turbulent flows, the validation shows easy compliance with the grid codes.
Currently, the available power estimation is heavily dependent on the pre-defined performance...
Citation