论文信息 - Artificial neural network models for wind power short-term forecasting using weather predictions

Artificial neural network models for wind power short-term forecasting using weather predictions

The use of wind energy has developed significantly worldwide. Wind power is the strongest growing form of renewable energy, ideal for a future with pollution-free electric power. But the integration of wind farms in power networks has become an important problem for the unit commitment and control of power plants in electric power systems. The intermittent nature of wind makes it difficult to forecast wind-produced electric energy in a wind farm even in the next hours. This paper compares the results obtained with a set of selected models for hourly electric power production forecasting in a real-life wind farm. The results show a significant improvement if previous numerical weather forecasts are used as input in hourly power forecasting models.

[1] Halbert White,et al. Artificial Neural Networks: Approximation and Learning Theory , 1992 .

[2] Henrik Madsen,et al. Short‐term Prediction—An Overview , 2003 .

[3] G. Grell,et al. A description of the fifth-generation Penn State/NCAR Mesoscale Model (MM5) , 1994 .

[4] J. Torres,et al. Forecast of hourly average wind speed with ARMA models in Navarre (Spain) , 2005 .

[5] Kurt Hornik,et al. Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[6] Athanasios Sfetsos,et al. A novel approach for the forecasting of mean hourly wind speed time series , 2002 .