利用灰色预测法、人工神经网络法、ARMA时间序列法3种不同的预测模型对某风电场的风电功率进行了预测研究。计算结果表明,利用单一预测模型进行预测的精度有待提高。提出建立组合预测模型对风电功率进行预测,为了充分利用单一预测方法的优势,引入熵值理论。利用熵值法确定组合预测模型中的权重,进而建立熵权组合预测模型。模拟结果表明,熵权组合预测模型可以有效地提高风电功率的预测精度。
Three different prediction models are investigated for wind power prediction of a wind farm. The re- sults show that using a single forecasting model to predict the accuracy to be improved, the establishment of combi- nation forecasting model for wind power prediction is proposed, in order to take full advantage of a single forecasting method, the entropy theory is introduced. The weights are determined by the method of entropy and then the entro- py method and combined prediction are given, the results show that the entropy combination forecasting model can effectively improve the prediction accuracy of wind power.