A data-driven machine learning approach for yaw control applications of wind farms

This study proposes a cost-effective machine-learning based model for predicting velocity and turbulence kinetic energy fields in the wake of wind turbines for yaw control applications. The model consists of an auto-encoder convolutional neural network (ACNN) trained to extract the features of turbine wakes using instantaneous data from large-eddy simulation (LES). The proposed framework is demonstrated by applying it to the Sandia National Laboratory Scaled Wind Farm Technology facility consisting of three 225 kW turbines. LES of this site is performed for different wind speeds and yaw angles to generate datasets for training and validating the proposed ACNN. It is shown that the ACNN accurately predicts turbine wake characteristics for cases with turbine yaw angle and wind speed that were not part of the training process. Specifically, the ACNN is shown to reproduce the wake redirection of the upstream turbine and the secondary wake steering of the downstream turbine accurately. Compared to the brute-force LES, the ACNN developed herein is shown to reduce the overall computational cost required to obtain the steady state first and second-order statistics of the wind farm by about 85%.

Automated summary

This study proposes a machine-learning based model for predicting velocity and turbulence kinetic energy fields in the wake of wind turbines. The model accurately predicts turbine wake characteristics and reduces computational cost significantly.