| 174 | 0 | 11 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】短期海上风电功率预测为国家电力系统的安全与稳定发挥着重要的作用，然而由于海上监测站点稀疏，导致风速、波浪等关键气象数据不足，且由于海上风浪流等多物理场耦合与风电机组电力电子设备开关控制相互作用的影响，让海上风电本身存在非线性和多频等特性，使得海上风电功率预测困难，为提高海上风电功率预测的准确度，更好地支持电力系统的稳定性。【方法】本文提出一种基于VMD-BiGRU与自注意力机制融合的短期海上风电功率预测方法。首先，利用变分模态分解（variational mode decomposition,VMD）算法，将原始数据分解为不同频率的本征模函数（intrinsic mode function,IMF），然后将IMF和原始数据输入，用双向门控循环单元（bidirectional gated recurrent unit,BiGRU）网络和自注意力机制（self-attention mechanism,SAM）对短期风电功率进行预测，其中BiGRU与SAM采用残差连接和维度拼接的方法进行特征融合。最后，为了验证所提出方法的可行性和优越性对比利时2024年海上风场短期风电功率进行预测，并与其他三种预测方法进行比较。【结果】结果表明，基于VMD-BiGRU与自注意力机制融合的短期海上风电功率预测方法将均方根误差减小至0.016 4，与其他方法相比具有更加优越的预测性能。【结论】基于VMD-BiGRU与自注意力机制融合的方法有效提升了短期海上风电功率预测精度，其多模块协同设计增强了模型的时序特征捕捉能力和鲁棒性。未来可通过参数优化和数据集扩展进一步提高模型的泛化能力。
Abstract：[Objective] Short-term offshore wind power prediction plays an important role for the safety and stability of the national power system, however, due to the sparse offshore monitoring stations, resulting in insufficient key meteorological data such as wind speed, waves, etc., and due to the influence of multi-physical fields such as offshore wind and wave currents coupled with the interaction between the switching and control of the wind turbine's power electronic equipment, the offshore wind power itself has nonlinear and multi-frequency characteristics, making offshore wind power prediction difficult. [Methods] Aiming at this problem, a short-term offshore wind power prediction method based on the fusion of VMD-BiGRU and self-attention mechanism is proposed. Firstly, the original data are decomposed into intrinsic mode functions(IMFs) of different frequencies using the variational mode decomposition(VMD) algorithm, and then the IMFs and the original data are used as inputs for the prediction of short-term offshore wind power using the bidirectional gated recurrent unit(BGRU). bidirectional gated recurrent unit(BiGRU) network and self-attention mechanism(SAM) for short-term wind power prediction, in which BiGRU and SAM are fused using residual linking and dimensional splicing. Finally, in order to verify the feasibility and superiority of the proposed method to predict the shortterm wind power of offshore wind farms in Belgium in 2024, and to compare it with the other three prediction methods. [Results] The results show that the short-term offshore wind power prediction method based on the fusion of VMDBiGRU and self-attention mechanism reduces the root-mean-square error to 0.016 4, which provides a more superior prediction performance compared with other methods. [Conclusion] The method based on the fusion of VMD-BiGRU and self-attention mechanism effectively improves the accuracy of short-term offshore wind power prediction, and its multi-module synergistic design strengthens the ability of time-series feature capture and robustness of the model. The generalisation ability of the model can be further improved by parameter optimisation and dataset extension in the future.
[1]徐思文,李卓函,韩滟赢.基于DBO-SVM的风力发电功率短期预测[J].现代工业经济和信息化,2024,14(9):210-212.XU Siwen,LI Zhuohan,HAN Yanying. Short-term prediction of wind power generation based on DBO-SVM[J]. Modern Industrial Economy and Informationization,2024,14(9):210-212.
[2]陈大为，张玮，慕龙.LSTM与XGBoost混合模型在风力发电功率预测中的应用[J].无线互联科技，2025,22(1):63-66.CHEN Dawei,ZHANG Wei,MU Long. Application of LSTM and XGBoost hybrid model in wind power generation forecasting[J].Wireless Internet Science and Technology,2025,22(1):63-66.
[3]张志瑞，陈磊，蔡坤哲，等.基于相似日与加权马尔可夫模型的风力发电功率区间预测[J].现代电子技术，2024,47(17):153-158.ZHANG Zhirui,CHEN Lei,CAI Kunzhe,et al. Wind power interval prediction based on similar day and weighted Markov model[J]. Modern Electronics Technique,2024,47(17):153-158.
[4]叶星汝，董树锋，严秋雨，等.海上风场短时风速混合威布尔逼近方法[J].太阳能学报，2023,44(11):224-230.YE Xingru,DONG Shufeng,YAN Qiuyu,et al. Mixed weibull distribution approximation of short-term offshore wind speed[J].Acta Energiae Solaris Sinica,2023,44(11):224-230.
[5]刘林，王大龙，綦晓，等.基于双锁相环的海上风场综合惯量调频策略研究[J].发电技术，2024,45(2):282-290.LIU Lin,WANG Dalong,QI Xiao,et al. Study on double phaselocked loop on the synthetic inertia control of offshore wind farm frequency regulation[J]. Power Generation Technology,2024,45(2):282-290.
[6]何志福，徐戈.面向风电功率预测的关键技术及应用综述[J].现代工业经济和信息化，2024,14(10):129-130.HE Zhifu,XU Ge. A review of key technologies and applications for wind power prediction[J]. Modern Industrial Economy and Informationization,2024,14(10):129-130.
[7]李国全，李玲玲.基于极限学习机模型的风电功率预测方法[J].华北科技学院学报，2024,21(3):75-82.LI Guoquan,LI Lingling. A wind power prediction method based on extreme learning machine model[J]. Journal of North China Institute of Science and Technology,2024,21(3):75-82.
[8]张中丹，李加笑，冯智慧，等.基于RF-TCN-SA及误差修正的风电功率超短期预测[J].电网与清洁能源，2025,41(2):113-119.ZHANG Zhongdan,LI Jiaxiao,FENG Zhihui,et al. The ultrashort-term wind power prediction based on RF-TCN-SA and error correction[J]. Power System and Clean Energy,2025,41(2):113-119.
[9]应润宇，王玉林.基于DBO-LSTM-attention模型的风电功率预测模型[J].现代工业经济和信息化，2024,14(11):289-290+293.YING Runyu,WANG Yulin. Wind power prediction model based on DBO-LSTM-attention modeling[J]. Modern Industrial Economy and Informationization,2024,14(11):289-290+293.
[10] XU W,DAI W J,LI D Y,et al. Short-term wind power prediction based on a variational mode decomposition-BiTCN-psformer hybrid model[J]. Energies,2024,17(16):4089.
[11] GAO Y L,XING F,KANG L P,et al. Ultra-short-term wind power forecasting based on DT-DSCTransformer model[J]. IEEE Access,2025,13:22919-22930.
[12] TAN N,ZHOU Z Y,ZOU M J. Research on a novel wind power prediction method based on VMD-IMPA-BiLSTM[J]. IEEE Access,2024,12:73451-73469.
[13]汪繁荣，梅涛，卢璐.基于相似日聚类和VMD-LTWDBOBiLSTM的短期光伏功率预测[J].智慧电力，2024,52(10):56-63+111.WANG Fanrong,MEI Tao,LU Lu. Short-term PV power prediction based on similar day clustering with VMD-LTWDBOBiLSTM[J]. Smart Power,2024,52(10):56-63+111.
[14]刘锦峰，崔家铭，林宇龙，等.基于VMD-SSA-LSTM的多维时序光伏功率预测模型[J].现代工业经济和信息化，2024,14(9):261-262+266.LIU Jinfeng,CUI Jiaming,LIN Yulong,et al. Multi-dimensional time-series photovoltaic power prediction model based on VMDSSA-LSTM[J]. Modern Industrial Economy and Informationization,2024,14(9):261-262+266.
[15]安源，高嘉伟，罗畅，等.基于数据优化和CQR-CNN-BiGRU模型的光伏功率超短期区间预测[J].电气应用，2024,43(8):90-99.AN Yuan,GAO Jiawei,LUO Chang,et al. Ultra-short-term interval prediction of PV power based on data optimization and CQR-CNN-BiGRU model[J]. Electrotechnical Application,2024,43(8):90-99.
[16]邹邦杰，刘国巍.基于SGMD的CNN-BiGRU光伏功率预测[J].无线互联科技，2023,20(23):128-130.ZOU Bangjie,LIU Guowei. CNN-BiGRU photovoltaic power prediction based on SGMD[J]. Wireless Internet Science and Technology,2023,20(23):128-130.
[17]王家乐，张耀，林帆，等.基于自注意力特征提取的光伏功率组合概率预测[J].太阳能学报，2024,45(12):123-131.WANG Jiale,ZHANG Yao,LIN Fan, et al. Combining probabilistic prediction of pv power based on self-attention feature extraction mechanism[J]. Acta Energiae Solaris Sinica,2024,45(12):123-131.
[18]李祺彬，卢箫扬，林培杰，等.基于DBSCAN-PCA和改进自注意力机制的光伏功率预测[J].电气开关，2024,62(1):6-12.LI Qibin,LU Xiaoyang,LIN Peijie,et al. Photovoltaic power prediction based on DBSCAN-PCA and improved self-attention mechanism[J]. Electric Switchgear,2024,62(1):6-12.
[19] SHEN S,HE J J. SGCS:A signal reconstruction method based on Savitzky-Golaysgz filtering and compressed sensing for wavelength modulation spectroscopy[J]. Optics Express,2021,29(22):35848-35863.
[20]闫馨月，张海鹏，李然，等.综合成本导向的风电短期功率预测[J].中国电机工程学报，2024,44(增刊1):240-252.YAN Xinyue,ZHANG Haipeng,LI Ran,et al. Comprehensive cost-oriented short-term wind power prediction[J]. Proceedings of the CSEE,2024,44(S1):240-252.
[21]黄泽，毕贵红，谢旭，等.基于MBI-PBI-ResNet的超短期光伏功率预测[J].电力系统保护与控制，2024,52(2):165-176.HUANG Ze,BI Guihong,XIE Xu,et al. Ultra-short-term PV power prediction based on MBI-PBI-ResNet[J]. Power System Protection and Control,2024,52(2):165-176.
[22]杨梅，李忠，吴昊，等.基于多尺度时间特征LSTM的短期负荷预测[J].控制工程，2022,29(9):1722-1728.YANG Mei,LI Zhong,WU Hao,et al. Short-term load f prediction of LSTM based on multi-scale time characteristics[J].Control Engineering of China,2022,29(9):1722-1728.
[23]张浩然，马萍，张宏立，等.基于路径重积分特征提取的轴承故障诊断[J].组合机床与自动化加工技术，2024,(8):134-138+144.ZHANG Haoran,MA Ping,ZHANG Hongli,et al. Feature extraction of time series signal path signature and its application in fault diagnosis[J]. Modular Machine Tool&Automatic Manufacturing Technique,2024,(8):134-138+144.
[24]宫文峰，张美玲，陈辉.基于深度学习的旋转机械大数据智能故障诊断方法[J].计算机集成制造系统，2025,31(1):264-277.GONG Wenfeng,ZHANG Meiling,CHEN Hui. Intelligent fault diagnosis method based on deep learning of rotating machinery under big data[J]. Computer Integrated Manufacturing Systems,2025,31(1):264-277.
[25]宋蒙恩，罗敏.基于双路神经网络多尺度特征提取的轴承故障诊断[J].组合机床与自动化加工技术，2025,(2):163-170.SONG Mengen,LUO Min. Fault diagnosis of bearings based on dual-path neural network with multi-scale feature extraction[J].Modular Machine Tool&Automatic Manufacturing Technique,2025,(2):163-170.
基本信息:
DOI：10.19944/j.eptep.1674-8069.2025.04.016
中图分类号:TM614;TP18
引用信息:
[1]孙秋,王鹏,宋忠民,等.基于VMD-BiGRU与自注意力机制融合的短期海上风电功率预测[J].电力科技与环保,2025,41(04):676-684.DOI:10.19944/j.eptep.1674-8069.2025.04.016.
基金信息:
中国高校产学研创新基金项目(2024HY031)
2025-04-17
2025
2025-11-17
2025
1
2025-08-15
2025-08-15