Deep learning based ensemble approach for probabilistic wind power forecasting
Deep learning based ensemble approach for probabilistic wind power forecasting
复制标题
基于深度学习的概率风电预测集成方法
DOI：
10.1016/j.apenergy.2016.11.111
复制
发表时间：
2017-02-15
期刊：
影响因子：
11.2
通讯作者：
Liu, Yi-tao
中科院分区：
文献类型：
--
作者：
Wang, Huai-zhi;Li, Gang-qiang;Liu, Yi-tao
风力发电因其良好的经济效益和环境效益，正成为一种极具发展前景的发电补充能源。然而，风电数据中表现出的不确定性通常大得令人无法接受。因此，运营商应该对数据进行准确的评估，以有效地降低风电对电力系统运行的风险。认识到这一挑战，提出了一种新的基于深度学习的概率风电功率预测集成方法。在该方法中，首次提出了一种基于小波变换和卷积神经网络的先进的点预测方法。利用小波变换将原始风电数据分解成不同的频率。然后利用卷积神经网络有效地学习用于提高预测精度的各个频率上的非线性特征。之后，对风电数据中的不确定性，即模型误判和数据噪声分别进行了识别。因此，可以统计地表示风电数据的概率分布。利用中国的实际风电场数据对所提出的集成方法进行了广泛的评估，结果表明，该方法可以更好地学习风电数据中的不确定性，并获得了具有竞争力的性能。(C)2016爱思唯尔有限公司。保留所有权利。
Due to the economic and environmental benefits, wind power is becoming one of the more promising supplements for electric power generation. However, the uncertainty exhibited in wind power data is generally unacceptably large. Thus, the data should be accurately evaluated by operators to effectively mitigate the risks of Wind power on power system operations. Recognizing this challenge, a novel deep learning based ensemble approach is proposed for probabilistic wind power forecasting. In this approach, an advanced point forecasting method is originally proposed based on wavelet transform and convolutional neural network. Wavelet transform is used to decompose the raw wind power data into different frequencies. The nonlinear features in each frequency that are used to improve the forecast accuracy are later effectively learned by the convolutional neural network. The uncertainties in wind power data, i.e., the model misspecification and data noise, are separately identified thereafter. Consequently, the probabilistic distribution of wind power data can be statistically formulated. The proposed ensemble approach has been extensively assessed using real wind farm data from China, and the results demonstrate that the uncertainties in wind power data can be better learned using the proposed approach and that a competitive performance is obtained. (C) 2016 Elsevier Ltd. All rights reserved.