SCADA-based feature analysis and Bayesian-optimized machine learning for short-term turbine-level wind power forecasting

Abstract

Most wind power forecasting studies rely primarily on historical turbine output time series, while environmental and operational parameters remain insufficiently explored. This paper investigates short-term turbine-level wind power forecasting using SCADA data collected from a wind farm in Vietnam, incorporating both environmental and operational variables. A filter-based feature selection method is first applied to identify significant predictors based on p-values. The ARIMAX model is adopted as a statistical baseline. In addition, several machine learning models, including Gaussian process regression, support vector machine, random forest, least-squares boosting, and feedforward neural network, are implemented. Bayesian optimization is employed for hyperparameter tuning. Forecasting performance is evaluated using MAE and RMSE, which are further combined into a weighted objective function. Results indicate that, within the investigated one-month SCADA dataset, the optimized machine-learning models achieved lower MAE and RMSE values than the traditional ARIMAX baseline. These findings demonstrate the effectiveness of the proposed framework for short-term turbine-level forecasting under the investigated operating conditions, while broader seasonal generalization requires validation using longer-term SCADA datasets.