Improving Site-Dependent Wind Turbine Performance Prediction Accuracy Using Machine Learning

Data-driven wind turbine performance predictions, such as power and loads, are important for planning and operation. Current methods do not take site-specific conditions such as turbulence intensity and shear into account, which could result in errors of up to /0%. In this work, four different machine learning models (k-nearest neighbors regression, random forest regression, extreme gradient boosting regression and artificial neural networks (ANN)) are trained and tested, first on a simulation dataset and then on a real dataset. It is found that machine learning methods that take site-specific conditions into account can improve prediction accuracy by a factor of two to three, depending on the error indicator chosen. Similar results are observed for multi-output ANNs for simulated in- and out-of-plane rotor blade tip deflection and root loads. Future work focuses on understanding transferability of results between different turbines within a wind farm and between different wind turbine types.

Automated summary

Data-driven wind turbine performance predictions can be significantly improved with machine learning methods that consider site-specific conditions. The study also found that different machine learning models have varying effects on different error indicators. Additionally, similar results were observed for multi-output artificial neural networks in predicting rotor blade deflection and root loads.