Title :
Probabilistic Wind Power Forecasting Using Radial Basis Function Neural Networks
Author :
Sideratos, George ; Hatziargyriou, Nikos D.
Author_Institution :
Nat. Tech. Univ. of Athens, Athens, Greece
Abstract :
A novel methodology for probabilistic wind power forecasting is described. The method is based on artificial intelligence and concentrates on the uncertainty information about the future wind power production predicting a set of quantiles with predefined nominal probabilities. The proposed model uses the point predictions of an existing state-of-the-art wind power forecasting model and forecasts the prediction uncertainties due to the inaccuracies of the numerical weather predictions (NWP), the weather stability and the deterministic forecasting model. The performance of the proposed model is evaluated on two wind farms that are located in areas with different weather conditions.
Keywords :
load forecasting; power engineering computing; radial basis function networks; wind power plants; NWP; deterministic forecasting model; numerical weather predictions; predefíned nominal probabilities; prediction uncertainties; probabilistic wind power forecasting; radial basis function neural networks; state-of-the-art wind power forecasting model; weather stability; wind farms; wind power production prediction; Forecasting; Predictive models; Radial basis function networks; Self organizing feature maps; Uncertainty; Wind power generation; Probabilistic wind power forecasting; radial basis function neural network; self-organized map;
Journal_Title :
Power Systems, IEEE Transactions on
DOI :
10.1109/TPWRS.2012.2187803
