Hyperparameter tuning framework for calibrating analytical wake models using SCADA data of an offshore wind farm applied on FLORIS

Abstract. Calibrating analytical wake models for wind farm yield assessment and wind farm flow control presents significant challenges. This study provides a robust methodology for the calibration of the velocity deficit parameters of an analytical wake model. Initially, a sensitivity analysis of wake parameters of the Gauss-Curl Hybrid model and their linear correlation is conducted, followed by a calibration using SCADA data and a Tree-Structured Parzen Estimator. Results show that the tuning parameters that are multiplied with the turbine-specific turbulence intensity pose higher sensitivity than tuning parameters not giving weight to the turbulence intensity. It is also observed that the optimization converges with a higher residual error when inflow wind conditions are affected by neighbouring wind farms. The significance of this effect becomes apparent when the energy yield of turbines situated in close proximity to nearby wind farms is compared. Sensitive parameters show strong convergence, while parameters with low sensitivity show significant variance after optimization. The study also observes coastal influences on the calibrated results, resulting in faster wake recovery, compared to wind from sea.