Evaluation of the MORE-CARE wind power prediction platform. Perfrmance of the fuzzy logic based models

Georges Kariniotakis (1) , Pierre Pinson (1)

1 CEP/Sophia

The paper presents an advanced wind forecasting system that uses on-line SCADA measurements, as well as numerical weather predictions as input to predict the power production of wind parks 48 hours ahead. The prediction tool integrates models based on adaptive fuzzy-neural networks configured either for short-term or long-term forecasting. In each case, the model architecture is selected through non-linear optimization techniques. The forecasting system is integrated within the MORE-CARE EMS software developed in the frame of a European research project. Within this on-line platform, the forecasting module provides forecasts and confidence intervals for the wind farms in a power system, which can be directly used by economic dispatch and unit commitment functions. The platform can run also as a stand-alone application destined only for wind forecasting. Detailed results are presented on the performance of the developed models over a one-year evaluation period on five real wind farms in Ireland, using HIRLAM numerical weather prediction and SCADA data as input.

Mots clés: Wind Power; Time-series forecasting; numerical weather predictions; on-line software; adaptive fuzzy-neural networks

Domaines: Energie électrique; Energétique

Georges Kariniotakis, Pierre Pinson. Evaluation of the MORE-CARE wind power prediction platform. Perfrmance of the fuzzy logic based models. EWEC 2003 - European Wind Energy Conference, Jun 2003, Madrid, Spain. ⟨hal-00530467⟩