Short-Term Wind Power Forecasting Using LSTM for Microgrid Operation in Bonavista, NL

For enhancing the operations of microgrids, especially in places like Bonavista in Newfoundland and Labrador, accurate short-term wind power forecasting is critically important. This is more so for communities which integrate renewable energy. This paper aims to develop and implement deep learning Long Short-Term Memory (LSTM) models for wind power forecasting for three months ahead based on one year of historical data. With a Mean Absolute Error (MAE) of 0.27 m/s and a Root Mean Squared Error (RMSE) of 0.39 m/s, the model demonstrates high predictive accuracy. Estimated power output was calculated using a standard wind turbine power curve, assuming representative turbine parameters, in order to convert wind speed forecasts into useful power inputs for microgrid operations. The LSTM’s potential and significance in microgrid planning and optimization are highlighted by the results, which show that its yield power estimates closely match actual generation.