This study proposes a cost-effective machine-learning based model for predicting velocity and turbulence kineticenergy fields in the wake of wind turbines for yaw control applications.The model consists of an auto-enc...This study proposes a cost-effective machine-learning based model for predicting velocity and turbulence kineticenergy fields in the wake of wind turbines for yaw control applications.The model consists of an auto-encoderconvolutional neural network(ACNN)trained to extract the features of turbine wakes using instantaneous datafrom large-eddy simulation(LES).The proposed framework is demonstrated by applying it to the Sandia NationalLaboratory Scaled Wind Farm Technology facility consisting of three 225 kW turbines.LES of this site is performedfor 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 angleand wind speed that were not part of the training process.Specifically,the ACNN is shown to reproduce thewake 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 costrequired to obtain the steady state first and second-order statistics of the wind farm by about 85%.展开更多
基金supported by the National Offshore Wind Research and Development Consortium (NOWRDC) under agreement number 147503a grant from the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under the Water Power Technologies Office (WPTO) Award Number DE-EE0009450
文摘This study proposes a cost-effective machine-learning based model for predicting velocity and turbulence kineticenergy fields in the wake of wind turbines for yaw control applications.The model consists of an auto-encoderconvolutional neural network(ACNN)trained to extract the features of turbine wakes using instantaneous datafrom large-eddy simulation(LES).The proposed framework is demonstrated by applying it to the Sandia NationalLaboratory Scaled Wind Farm Technology facility consisting of three 225 kW turbines.LES of this site is performedfor 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 angleand wind speed that were not part of the training process.Specifically,the ACNN is shown to reproduce thewake 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 costrequired to obtain the steady state first and second-order statistics of the wind farm by about 85%.
