首页|基于STAGCN-Informer时空组合模型的风电功率预测方法

基于STAGCN-Informer时空组合模型的风电功率预测方法

扫码查看
原文链接
  • 万方数据
  • 维普
针对风电功率预测中,空间信息受时空波动性和随机性影响无法有效提取,导致预测精度不足的问题,提出一种基于变分模态分解(Variational Mode Decomposition,VMD)、融合时空注意力图卷积网络(Spatiotemporal Attention Graph Convolutional Network,STAGCN)和改进Informer的组合模型(STAGCN-Informer-DCP).首先运用VMD对原始特征进行模态分解,提取出不同时间尺度上的特征信息.同时利用北方苍鹰算法(Northern Goshawk Optimization,NGO)优化VMD的核心参数(惩罚因子和K值)选择.其次,利用融合时空注意力的STAGCN模块动态捕捉目标风机与近邻相似风机的时空特征,并将其与原始的信号分量融合获得携带空间尺度信息的特征向量.最后使用改进的Informer模型提取时序上下文的长期依赖关系,并实现多步输出预测.实验结果表明,该组合模型能较好地捕捉动态时空依赖,并有效提高了中长期风电预测的准确度.
Wind Power Prediction Method Based on STAGCN-Informer Spatiotemporal Fusion Model
Aiming at the problem that the spatial information cannot be effectively extracted due to the influence of spatiotempo-ral fluctuation and randomness in wind power forecasting,resulting in insufficient prediction accuracy,a model named STAGCN-Informer-DCP is proposed based on Variational Mode Decomposition(VMD),fusion of Spatiotemporal Attention Graph Convolutional Network(STAGCN)and improved Informer combination model.Firstly,VMD is used to perform modal de-composition on the original features,and the feature information on different time scales is extracted.At the same time,the selec-tion of core parameters(penalty factor and K value)of VMD is optimized by using northern goshawk optimization(NGO).Sec-ondly,the STAGCN module that integrates spatio-temporal attention is used to dynamically capture the spatio-temporal features of the target wind turbine and its neighbors,and fuses them with the original signal components to obtain a feature vector carrying spatial scale information.Finally,the improved Informer model is used to extract the long-term dependencies of temporal context and realizes multi-step output prediction.The experimental results show that the combination model can better capture the dy-namic space-time dependence,and effectively improve the accuracy of medium and long-term wind power forecasting.

variational mode decompositionspatiotemporal attention mechanismInformer modelnorthern goshawk optimiza-tiongraph convolutional network

杨绍祖、王海程、吴金雅、马纪颖

展开 >

沈阳化工大学计算机科学与技术学院,辽宁 沈阳 110142

辽宁省化工过程工业智能化技术重点实验室,辽宁 沈阳 110142

变分模态分解 时空注意力机制 Informer模型 北方苍鹰优化算法 图卷积网络

国家外国专家计划项目辽宁省自然科学基金资助项目辽宁省教育厅基本科研项目

G2022006008L2022-MS-291LJKMZ20220781

2024

10.3969/j.issn.1006-2475.2024.07.003

计算机与现代化
江西省计算机学会 江西省计算技术研究所

计算机与现代化

CSTPCD
影响因子：0.472
ISSN：1006-2475
年,卷(期)：2024.(7)
  • 15