Xingjie Liu, Tianyun Cen, and Wenshu Zheng
Wind power prediction, Distribution characteristic, SCCF, Grouping model, RBF neural network
Accurate wind power forecasting is significant for safe dispatching and stable operation of power system. In this paper, based on the wind speed distribution characteristics in wind farm, a novel approach for wind power real-time forecasting is proposed. Firstly, the space distribution characteristics of wind speed were analysed greatly. Then, WTGs (Wind Turbine Group) were divided into several groups with grouping model method based on SCCF (Sample Cross Correlation Function, SCCF), and the turbines of approximately identically-distributed were divided into the same group. Finally, the direct multi-step forecasting of grouped wind power was carried out with radial basis function neural network, then the whole power of wind farm was obtained by superposition. The simulation results for real data of wind farm at two typical areas in China, coastal areas and North China, show that the prediction accuracy is improved and the prediction computation is significantly reduced with the presented method.
Important Links:
Go Back
