The growth of wind power connected to the power grid has increased the importance of accurate wind power prediction that exhibits non-linearity and non-stationarity. The goal of this study is to forecast wind power by...
详细信息
The growth of wind power connected to the power grid has increased the importance of accurate wind power prediction that exhibits non-linearity and non-stationarity. The goal of this study is to forecast wind power by using the generalized regression neural network (GRNN) coupled with ensemble empirical mode decomposition (EEMD) and assessment of prediction accuracy. EEMD technologies are used to perform decomposition, and each intrinsic mode function is predicted and forecasted by using a GRNN based on cross-validated parameters. The forecasting results of the sub-series are superimposed as the results of wind power prediction. Results show that the proposed method has high prediction accuracy and is highly effective in forecasting wind power.
The recent emphasis on metadata standards must be accompanied by vigilance in unbiased reporting of geometric accuracy. A cross-validation technique is shown to be capable of providing more accurate estimates of geome...
详细信息
The recent emphasis on metadata standards must be accompanied by vigilance in unbiased reporting of geometric accuracy. A cross-validation technique is shown to be capable of providing more accurate estimates of geometric error than the traditional method of using transformation residuals when modest numbers of ground control points are available. This method also provides a much more accurate indication of the effects of choosing different polynomial orders.
暂无评论