基于可学习小波自注意力模型的海上风电功率超短期预测  

Ultra-short Term Prediction of Offshore Wind Power Based on Learnable Wavelet Self-attention Model

作　　者：汪敏 荣腾飞 李茜[1] 魏澈 张安安[1] WANG Min;RONG Tengfei;LI Qian;WEI Che;ZHANG An’an(School of Electrical Engineering and Information,Southwest Petroleum University,Chengdu 610500,China;CNOOC Research Institute Ltd.,Beijing 100028,China)

机构地区：[1]西南石油大学电气信息学院,成都610500 [2]中海油研究总院有限责任公司,北京100028

出　　处：《高电压技术》2025年第3期1422-1433,I0011-I0015,共17页High Voltage Engineering

基　　金：国家自然科学基金(62006200);中央引导地方科技发展专项资金(2021ZYD0042)。

摘　　要：为了提高海上风电功率预测的精度以及其预测结果的可信度,提出了一种融合可学习小波的自注意力模型,有效提升了海上风电功率预测的精度,并且具备一定的预测过程分析能力。首先,将小波分解与深度学习模型融合,使模型具备从不同频域提取特征的能力。其次,构建稀疏自注意力预测网络,实现对全局信息特征的有效提取,提高模型的预测性能。接着,提出一种时序“敏感度”量化分析方法,在多维度下对海上风电参量输入进行重要性评估,在一定程度上对预测机理进行合理的分析。最后,基于风场实际运行数据进行相关实验。实验结果表明,相较对比模型,所提模型在海上风电超短期预测任务上具有更高的预测精度。In order to improve the accuracy of offshore wind power prediction and the reliability of its prediction results,a self-attention model integrating learnable wavelet is proposed,which effectively improves the accuracy of offshore wind power prediction and has a certain ability of forecasting process analysis.First,the wavelet decomposition is integrated with the deep learning model,so that the model has the ability to extract features from different frequency domains.Sec-ond,a sparse self-attention prediction network is constructed to extract global information features effectively and improve the prediction performance of the model.Then,a time-series“sensitivity”quantitative analysis method is pro-posed to evaluate the importance of offshore wind power parameter input in multiple dimensions,and to analyze the prediction mechanism reasonably to a certain extent.Finally,relevant experiments are carried out based on actual opera-tion data of wind field.The experimental results show that,compared with the model,the proposed model has higher prediction accuracy in the ultra-short term prediction task of offshore wind power.

关 键 词：海上风能 深度学习 功率预测 自注意力 敏感度分析 小波分解 

分 类 号：TM614[电气工程—电力系统及自动化]