DTU 10MW reference turbine HAWC2 simulations for Model-free estimation of available power with deep learning training

The time series of DTU 10MW HAWC2 model simulations of two channels: hub-height wind speed and produced power. They are generated to train model-free estimation of available power approach, using wind speed and its moving standard deviation as inputs. They include 3-hour length 100Hz simulations of 3 mean wind speeds (7 m/s, 9m/s and 11m/s) as well as 3 levels of turbulence intensity (TI = 7%, 10% and 20%). 

The dataset and the training algorithm can also be found here: https://gitlab.windenergy.dtu.dk/tuhf/deep-learning-for-available-power-estimation/tree/master