This thesis investigates the potential of data-driven modelling to enhance wind farm monitoring, control, and operations and maintenance (O&M) strategies by leveraging the extensive SCADA data generated by offshore wind farms. Focusing on the Lillgrund offshore wind farm, the study develops regression-based surrogate models using XGBoost, artificial neural networks, and Gaussian process regression to predict two critical targets: the blade root flapwise and tower bottom fore-aft damage equivalent loads. All models are found to effectively capture the underlying patterns from the input features. Among them, XGBoost consistently outperforms the others in terms of prediction accuracy, computational efficiency, and robustness. Its superior performance is further validated across multiple preprocessing settings and operational scenarios, including its capacity to generalise across turbines and exploit spatial information. Finally, the applicability of the models is demonstrated through a simplified use case that estimates fatigue damage over a specific period. The findings underline the value of integrating machine learning-based surrogate models into operational workflows to reduce O&M costs and support decision-making in wind farm management.

Floating offshore wind farms are a promising technological development that can help provide large amounts of energy from sites previously not feasible for wind farm development. To suc- cessfully develop floating wind farms, knowledge about the involved aerodynamics are crucial. A first building block of this is the understanding of the wake of a single floating wind turbine un- dergoing floating motion in turbulent wind fields. Using an actuator line model within the Large Eddy Simulation framework YALES2 the wake of a floating wind turbine undergoing surge motion has been investigated at varying amplitudes and frequencies. Special attention was given to the inflow conditions, comparing laminar and low turbulent inflow conditions modeled using Mann turbulence boxes. Varying the surge amplitude at a surge frequency equivalent to St = 0.4, the investigations show that the influence of the motion on the wake is greatly reduced even when low turbulence levels are present. Already at a turbulence intensity of 2.5% the wake deficit and wake turbulence in- tensity were indistinguishable from a fixed turbine’s wake for lower surge amplitudes. Large surge amplitudes were required to significantly change these wake statistics, starting from an amplitude of A/D = 0.16 rotor diameters.Using proper orthogonal decomposition the dynamics in the wake have been analyzed. It was found that the effect of the rotor motion on the wake is lower when the inflow turbulence intensity is increased. Varying the motion frequency in the range of St ∈ [0.2, 0.8] at a amplitude of A/D = 0.04, it was shown that a surge motion at a frequency corresponding to St = 0.6 has the highest impact on the wake in terms of the reduction of modal time series correlations. However, even in that case the wake deficit and turbulence intensity in the wake are not changed significantly.