基于数值天气预报风速误差修正的风电功率日前预测

Day-ahead Prediction of Wind Power Based on NWP Wind Speed Error Correction

风电预测技术对构建高比例新能源的新型电力系统具有重要意义。数值天气预报(numerical weather prediction,NWP)的数据质量对风电功率日前预测的准确性有较大影响。然而,NWP的预报误差、NWP预报点与风电场间的空间距离和局地差异,往往导致NWP预报数据与风电场实测数据间存在时间横向误差和幅值纵向误差。对此,提出了一种基于时间序列相关性检验和残差通道注意力网络的NWP风速误差修正模型,将预报点处NWP风速修正为风电场轮毂风速。然后,结合修正后的NWP风速和风电场实时出力数据构建了基于双向门控循环网络的风电预测模型。最后,以华东某风电场的数据验证了所提方法的有效性。

The technology of wind power prediction is of great significance for constructing a new power system with renewable energy as the main body.The data quality of the Numerical Weather Prediction(NWP) has a great impact on the accuracy of the day-ahead prediction of wind power.However,the prediction errors of the NWP products,the spatial distance and the local differences between the NWP prediction locations and the wind farms often lead to lateral errors in time and the longitudinal errors in amplitude between the NWP data and the measured data of the wind farms.To solve this problem,a NWP wind speed error correction model based on the time series correlation test and the residual channel attention network is proposed to correct the NWP wind speed at the prediction location to the wind speed of the wind farm hubs.Finally,combining the revised NWP wind speed and the real-time power data of the wind farm,a wind power prediction model based on the bidirectional gated recurrent unit is constructed.The effectiveness of the proposed method is verified by the data of a wind farm in East China.