Wind Speed Extrapolation Using Machine Learning Methods and LiDAR Measurements

Accurate wind energy assessments require wind speed (WS) at the hub height. The cost of WS measurements grows enormously with height. This paper utilizes deep neural network (DNN) algorithm for the extrapolation of the WS to higher heights based on measured values at lower heights. LiDAR measurements at lower heights are used for training the system and at higher heights for performance analysis. These measurements are made at 10, 20, ..., and 120 m heights. First, the measured WS values at 10-40 m were used to extrapolate values up to 120 m. In the second scenario, the WS at 10-50 m were used to extrapolate values up to 120 m. This continued until the last scenario, in which the WS at 10-100 m were used to estimate values at 110 and 120 m. A relationship between heights of measurements and the accuracy of the WS estimation at hub height is presented. The WS extrapolated using the present approach is compared with the measured values and with local wind shear exponent (LWSE)-based extrapolated WS. Furthermore, to analyze the performance of the DNN relative to other machine learning methods, we compared its performance with that of classical feedforward artificial neural networks trained using a genetic algorithm to find the initial weights and the Levemberg-Marquardt (LM) method (GANN) for training. The mean absolute percent error between measured and extrapolated WS at height 120 m based on measurements between 10-50 musing DNN, GANN, and LWSE are 9.65%, 12.77%, and 9.79%, respectively.