Physics-guided machine learning for wind-farm power prediction: Toward interpretability and generalizability

Abstract

With the increasing amount of available data from simulations and experiments, research for the development of data-driven models for wind-farm power prediction has increased significantly. While the data-driven models can successfully predict the power of a wind farm with similar characteristics as those in the training ensemble, they generally do not have a high degree of flexibility for extrapolation to unseen cases in contrast to the physics-based models. In this paper, we focus on data-driven models with improved interpretability and generalizability levels that can predict the performance of turbines in wind farms. To prepare the datasets, several cases are defined based on the layouts of operational wind farms, and massive computational fluid dynamics simulations are performed. The extreme gradient boosting algorithm is used afterward to build models, which have turbine-level geometric inputs in combination with the efficiency from physics-based models as the features. After training, to analyze the models' capability in generalization, their predictions for the unseen cases with different operating conditions, inflow turbulence levels, and wind-farm layouts are compared to the Park model and an empirical-analytical Gaussian wake model. Results show that the physics-guided machine-learning models outperform both physics-based models showing a high degree of generalizability, and the machine is not sensitive to the choice of the physics-based guide model.