深度神经网络在风电功率预测中的应用研究

风电功率预测对于电网建设具有重要意义。文中提出一种基于深度神经网络的风电功率预测方法,该方法充分考虑了影响风电功率的若干因素,如风速、风向、空气密度和季节,通过深度神经网络训练、学习给出最佳的功率预测值。通过深度神经网络学习的特征能够更为有效地反映实际情况,因此提高了风电功率预测的稳健性。基于内蒙古某风电厂的实测数据进行了验证实验,结果表明了提出方法的有效性。

Research on application of deep neural networks to wind power prediction

Wind power prediction is important to the development of wind power station.A wind power prediction method based on deep neural networks is proposed in this paper.The proposed method fully considers the factors like wind speed,wind direction,air density,and season,which may affect the wind power and the optimal prediction can be output via the training and learning in the deep convolutional neural networks.The features learned in deep neural networks could better reflect the actual conditions thus improve the prediction precision of wind power.Experiments are conducted on the measured data from a certain wind station in Inner Mongolia and the results show the effectiveness of the proposed method.