Real-time wind power forecasting for grid operations using numerical weather model in Jeju
First, to enhance the reliability of the simulation and reduce the uncertainties due to model physics imperfections and initial conditions, the sensitivity experiments with different physics schemes and a time-lagged ensemble method of different initial conditions is performed. Second, the hybrid statistical model (ARIMA+Neural network) is optimized for short-term prediction. Lastly, the optimization of wind power calculation is carried out using wind speed applied by wake loss ratios of each turbine with wind direction.
Based on the validation, the real-time wind power forecasting developed in this study shows the reasonable performance in ahead 24, demonstrating the potential utilization for operating wind power in electricity grid..