Authors

Abstract

Wind farm design primarily depends on the variability of the wind turbine wake flows to the atmospheric wind conditionsand the interaction between wakes. Physics-based models that capture the wake flow field with high-fidelity are computationally very expensive to perform layout optimization of wind farms, and, thus, data-driven reduced-order models canrepresent an efficient alternative for simulating wind farms. In this work, we use real-world light detection and ranging(LiDAR) measurements of wind-turbine wakes to construct predictive surrogate models using machine learning. Specifically, we first demonstrate the use of deep autoencoders to find a low-dimensional latent space that gives a computationally tractable approximation of the wake LiDAR measurements. Then, we learn the mapping between the parameterspace and the (latent space) wake flow fields using a deep neural network. Additionally, we also demonstrate the use of aprobabilistic machine learning technique, namely, Gaussian process modeling, to learn the parameter-space-latent-spacemapping in addition to the epistemic and aleatoric uncertainty in the data. Finally, to cope with training large datasets, wedemonstrate the use of variational Gaussian process models that provide a tractable alternative to the conventionalGaussian process models for large datasets. Furthermore, we introduce the use of active learning to adaptively build andimprove a conventional Gaussian process model predictive capability. Overall, we find that our approach provides accurateapproximations of the wind-turbine wake flow field that can be queried at an orders-of-magnitude cheaper cost than thosegenerated with high-fidelity physics-based simulations.