CEEMDAN-WPE-CLSA超短期风电功率预测方法研究  

Ultra-Short-Term Wind Power Prediction Based on CEEMDAN-WPE-CLSA Model

作　　者：李杰[1] 孟凡熙 牛明博 张懿璞[1] LI Jie;MENG Fanxi;NIU Mingbo;ZHANG Yipu(School of Electronics and Control Engineering,Chang'an University,Xi'an 710064,China)

机构地区：[1]长安大学能源与电气工程学院,陕西西安710064 [2]长安大学电子与控制工程学院,陕西西安710064

出　　处：《大连交通大学学报》2024年第2期101-108,共8页Journal of Dalian Jiaotong University

基　　金：国家重点研发计划项目(2021YFB2601300);陕西省重点研发计划项目(2022GY-178)。

摘　　要：提出了一种结合自适应噪声完全集合经验模态分解、加权排列熵、卷积神经网络、长短期记忆网络和自注意力机制的超短期风电功率预测方法。首先,利用自适应噪声完全集合经验模态分解将原始风电功率时间序列自适应分解为一系列的模态分量,降低原始序列的非线性和波动性;其次,根据加权排列熵计算各模态分量间的相似性并对相似的分量进行重组,以修正自适应噪声完全集合经验模态分解的过度分解问题,使得修正后的模态分量更具规律性;最后,将重组后的分量输入卷积长短期记忆网络进行时序建模,并利用自注意力机制对卷积长短期记忆网络的神经元权重进行重新分配,提高了卷积长短期记忆网络对输入特征不确定性的适应能力。在此基础上,明确了自注意力机制和自适应噪声完全集合经验模态分解、加权排列熵在风电功率预测中的作用机制,以及风电功率信号包含的重要物理信息,证明了自适应噪声完全集合经验模态分解、加权排列熵以及自注意力机制在风电功率信号模态分解和长短期记忆网络隐层输出权重分配中的有效性。An ultra-short-term wind power prediction method based on CEEMDAN,WPE,CNN,LSTM and SAM is proposed.Firstly,the original wind power time series is decomposed by the CEEMDAN to reduce the nonlinearity and volatility of the original series.Secondly,the similarity between components is calculated by WPE method,and the similar components are recombined to correct the over decomposition problem of CEEMDAN and make the modified modal components more regular.Finally,the recombined components are input into the CNN-LSTM network for time series modeling,and the neural weights of this network are redistributed by SAM,which improves the adaptability of the network to the uncertainty of input characteristics.On this basis,the mechanism of SAM,CEEMDAN and WPE in wind power prediction and the crucial physical information contained in wind power signals are clarified,which proves the effectiveness of them in wind power signal modal decomposition and the hidden layer output weight allocation of LSTM.

关 键 词：超短期风电功率预测 自适应噪声完全集合经验模态分解 加权排列熵 卷积长短期记忆网络 自注意力机制 

分 类 号：TM614[电气工程—电力系统及自动化] TP183[自动化与计算机技术—控制理论与控制工程]