Automatic Feature Selection and Forecast Combination to Enhance and Generalize Renewable Energy Forecasting

Dennis van der Meer (1) , Simon Camal (1) , George Kariniotakis (1)

1 PERSEE - Centre Procédés, Énergies Renouvelables, Systèmes Énergétiques

Spatially aggregating renewable power plants is beneficial when participating in electricity markets. In this context, a substantial number of features is available from various data sources. In machine learning, feature selection is common so as to relieve the curse of dimensionality and avoid overfitting. However, there is no guarantee that the selected features result in reliable forecasts and post-processing can therefore be valuable. In this study, we combine model agnostic feature selection with linear and nonlinear probabilistic forecast combination techniques. Moreover, the filters automatically compute the weights for our analog ensemble (AnEn) forecast model that does not require training. We verify our model chain by generating intra-day forecasts of the aggregated output of 60 wind turbines and 20 photovoltaic power plants using 831 input features in total. We show that automatic feature selection improves forecast accuracy while forecast combination improves reliability.

Mots clés: Renewable Energies; Forecasting; Feature selection; Electricity markets; Analog Ensembles; SmartGrids; Forecasts reliability; Forecasts combination; Probabilistic forecasting

Domaines: Energie électrique; Machine Learning [stat.ML]; Applications [stat.AP]; Optimisation et contrôle [math.OC]; Probabilités [math.PR]; Statistiques [math.ST]

Dennis van der Meer, Simon Camal, George Kariniotakis. Automatic Feature Selection and Forecast Combination to Enhance and Generalize Renewable Energy Forecasting. WindEurope Technology Workshop 2022, Jun 2022, Bruxelles, Belgium. , 2022. ⟨hal-03710711⟩