Short-Term Wind Speed Forecasting of Oak Park Weather Station By Using Different ANN Algorithms

摘要

Renewable energy resources such as wind power generators are important alternatives in electric power systems considering their congenial environmental effects. Short-term wind speed forecasting have a huge impact on the load variation decisions and economic load dispatch in the wind-integrated power systems. Wind power is intermittent and is sometimes non-dispatchable because of its dependency on the atmospheric conditions, therefore accurate forecasting becomes necessary. In this paper different ANN algorithms i.e Levenberg-Marquardt back propagation, Bayesian Regularization & Scaled Conjugate Gradient algorithms has been applied in short-term wind speed forecasting that is one hour-ahead hourly forecast of the wind speed of Oak Park Weather Station, Ireland using MATLAB R14a. The data used in the forecasting are hourly historical data of the wind speed, temperature and wind direction. The simulation results have shown accurate one hour ahead forecasts with small error in wind speed forecasting.