基于诱导有序加权平均算法的风电场短期功率的预测

Short-term Power Forecast of Wind Farm Based on IOWA Algorithm

为了提高风电场发电功率的预测精度,提出一种基于诱导有序加权平均(induced ordered weighted averaging,IOWA)算法的风电场功率组合预测模型;该方法通过误差信息矩阵法筛选出优选模型进行组合,消除了冗余模型对预测精度的影响;结合华北某风电场历史功率数据及该地区的数值天气预报数据建立了风电场短期功率预测模型,以误差平方和最小值为准则,对未来48 h的风电场发电功率进行预测。结果表明:经优选后的组合预测模型降低了预测误差,提高了预测精度,缩短了预测时间。

In order to improve the prediction accuracy of power generation,a power combination forecasting model of wind farm based on induced ordered weighted averaging (IOWA) algorithm was proposed.This method selected the preferred model by error information matrix method.The influence of the redundancy model on the prediction accuracy was eliminated.The wind power short-term power prediction model was established based on the historical power data of wind farm in North China and the numerical weather prediction data of the region.The wind power of the next 48 hours is predicted based on the error squared minimum.The results show that the preferred combined prediction model reduces the prediction error,improves the prediction accuracy and shortens the prediction time.