Ultra Short-Term Wind Power Forecasting Based on Sparrow Search Algorithm Optimization Deep Extreme Learning Machine

Improving the accuracy of wind power forecasting is an important measure to deal with uncertainty and volatility power. Wind speed direction are most factors affecting generation turbines. In this paper, we propose a method that combines sparrow search algorithm (SSA) deep extreme learning machine (DELM). Based on DELM model, length time series’ influence performance neural network validated through comparison forecast error indexes, optimal series determined. The used optimize its parameters solve problem random changes in model input weights thresholds. proposed SSA-DELM using measured data certain turbine, various indexes compared several current methods. experimental results show has better ultra-short-term forecasting, coefficient determination (R²), mean absolute (MAE), root square (RMSE) 0.927, 69.803, 115.446, respectively.