Forecasting regional wind production based on weather similarity and site clustering for the EEM20 Competition

Kevin Bellinguer (1) , Valentin Mahler (1) , Simon Camal (1) , Georges Kariniotakis (1)

1 PERSEE - Centre Procédés, Énergies Renouvelables, Systèmes Énergétiques

Precise probabilistic forecasting tools of wind power generation are essential for solving problems related to the impact of wind generation uncertainty on electrical systems. In this context, the International Conference on the European Energy Market EEM20 set up a competition aiming at forecasting wind power generation for the four Swedish bidding zones. Participants had to generate day-ahead quantile forecasts of the aggregated wind power production from Numerical Weather Predictions (NWPs) ensembles provided all over the country [1].

Mots clés: Artificial Intelligence; Renewable Energy; Power systems; Wind power; Forecasting

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

Kevin Bellinguer, Valentin Mahler, Simon Camal, Georges Kariniotakis. Forecasting regional wind production based on weather similarity and site clustering for the EEM20 Competition. 40th International Symposium on Forecasting, International Institute of Forecasters, Oct 2020, Virtual Event, Brazil. ⟨hal-03157849⟩