Please login first
LSTM model for wind speed and power generation nowcasting.
* , * ,
1  Center for Atmospheric Physics, Meteorological Institute of Cuba
Academic Editor: Anthony Lupo


In the following work, the design of an LSTM-type neural network model for wind speed and power generation nowcasting, every 10 minutes and up to two hours, is presented. For this, the wind speed measurements were used every 10 minutes at different heights above the ground, coming from the Measurement Tower located in Los Cocos, in the province of Holguín (Cuba), where the wind farms Gibara I and II are located. The real data is complemented with the wind speed numerical hourly forecasts from SisPI. The data covered the period between February 1, 2019 and January 31, 2020, that is, one year of measurement. Several LSTM models were built and evaluated considering only the measurements and combining the measurements with the forecasts generated by SisPI. The results suggest that the constructed models perform better than other more traditional statistical models and than other neural network models used in the country for similar purposes.

Keywords: wind speed and power generation nowcasting; renewable energy sources; artificial neural networks; SisPI