VMD和混合深度学习框架融合的短期风速预测  

Short-term Wind Speed Prediction Based on VMD and Hybrid Deep Learning Framework

作　　者：李延满 张军 胡杨 赵英男[2] LI Yan-Man;ZHANG Jun;HU Yang;ZHAO Ying-Nan(NARI Nanjing Control System Co.Ltd.,Nanjing 210031,China;School of Computer&Software,Nanjing University of Information Science&Technology,Nanjing 210044,China)

机构地区：[1]国电南瑞南京控制系统有限公司,南京210031 [2]南京信息工程大学计算机与软件学院,南京210044

出　　处：《计算机系统应用》2023年第9期169-176,共8页Computer Systems & Applications

基　　金：国家自然科学基金青年项目(61601235);国电南瑞项目(524608190024)。

摘　　要：风速预测是影响风电场效率和稳定性的重要因素.文中基于风速的时空特征,融合变分模态分解(VMD)和混合深度学习框架进行短期风速预测,即VHSTN (VMD-based hybrid spatio-temporal network).其中,混合深度学习框架由卷积神经网络(CNN)、长短时记忆网络(LSTM)以及自注意力机制(SAM)组成.该算法对原始数据清洗后,采用VMD将多站点风速的时空数据分解为固有模态函数(intrinsic mode functions, IMF)分量,去除风速数据的不稳定性;然后针对各IMF分量,应用底部的CNN抽取空域特征;再用顶层LSTM提取时域特征,之后用SAM通过自适应加权加强对隐藏特征的提取并得到各分量的预测结果;最后合并获得最终预测风速.在数据集WIND上进行实验,并和相关典型算法对比,实验结果表明了该算法的有效性和优越性.Wind speed prediction is an important factor affecting the efficiency and stability of wind farms.Based on the spatio-temporal features of wind speed,the VMD-based hybrid spatio-temporal network(VHSTN)integrates variational modal decomposition(VMD)and hybrid deep learning framework to predict the short-term wind speed.The hybrid deep learning framework is composed of convolutional neural network(CNN),long and short-term memory(LSTM),and selfattention mechanism(SAM).After the cleaning of raw data,the VMD is employed to decompose the spatio-temporal data of wind speed for multiple sites into intrinsic mode functions(IMF)components,eliminating the instability of the wind speed data.For each IMF component,the spatial features are extracted by the CNN at the bottom of the model.Next,the temporal features are captured by the top-level LSTM.Then,SAM is applied to strengthen the extraction of key hidden features through adaptive weighting and obtain the prediction results of each component.Finally,the results are amalgamated to determine the final predicted wind speed.Experiments are conducted on the commonly used dataset WIND in this study.The experimental results prove the effectiveness and superiority of the proposed algorithm compared with related typical algorithms.

关 键 词：风速预测 时空特征 变分模态分解(VMD) 卷积神经网络(CNN) 长短时记忆网络(LSTM) 自注意力机制(SAM) 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TM614[自动化与计算机技术—控制科学与工程]