Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting

Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.