What question did this study set out to answer?

The aim is to develop and evaluate advanced forecasting models for offshore wind power using machine learning techniques.

Forecasting beyond the storm: machine learning models for offshore wind power under operational constraints

View Full Paper

Ask AI

Bookmark

Authors

Evaluates machine learning forecasts for offshore wind power, highlighting accuracy improvements under operational constraints.

The aim is to develop and evaluate advanced forecasting models for offshore wind power using machine learning techniques.
Utilized machine learning techniques such as gradient boosting (XGBoost) and neural networks (MLPs).
Conducted comprehensive analysis of input features, including numerical weather predictions and past production values.
Addressed data pre-processing for curtailment and distinguished between physical variability and grid-induced limitations.
Performed experiments with real-world offshore wind farm data.
Demonstrated high forecast accuracy of models like XGBoost and MLP under various conditions.
Highlighted the importance of feature engineering and data treatment for improving model performance.
Showed potential for machine learning models to enhance offshore wind power integration into the power system.

Bahr et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark