Short-term wind turbine energy yield forecasting is crucial for effectively integrating wind energy into the electricity grid and fulfilling day-ahead scheduling obligations in electricity markets such as Nord Pool and EPEX SPOT. This study presents a forecasting approach utilising operational data from two wind turbines in Latvia, as well as meteorological inputs from the NORA 3 reanalysis dataset, sensor measurements from the turbines, and data provided by the Latvian Environment, Geology and Meteorology Centre (LEGMC). Forecasts with lead times of 1 to 36 h are generated to support accurate day-ahead generation estimates. Several modelling techniques, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), artificial neural networks (ANNs), XGBoost, CatBoost, LightGBM, linear regression, and Ridge regression, are evaluated, incorporating wind and atmospheric parameters from three datasets: operational turbine data, meteorological measurements from LEGMC, and the NORA 3 reanalysis dataset. Model performance is assessed using standard error metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared (R2). This study demonstrates the effectiveness of integrating reanalysis-based meteorological data with turbine-level operational measurements to enhance the accuracy and reliability of short-term wind energy forecasting, thereby supporting efficient day-ahead market scheduling and the integration of clean energy.
Dmitrijevs et al. (Mon,) studied this question.