1.东北电力大学 现代电力系统仿真控制与绿色电能新技术教育部重点实验室,吉林 吉林 132012
2.广东电网有限责任公司中山供电局,广东 中山 528400
3.国网内蒙古东部电力有限公司电力科学研究院,内蒙古 呼和浩特 010020
4.中国电力科学研究院有限公司可再生能源并网全国重点实验室,北京 100192
杨 茂(1982 —),男,教授,博士,主要研究方向为电力系统稳定分析与新能源并网(E-mail:yangmao820@163.com);
代博祉(1996 —),男,博士研究生,主要研究方向为电力系统稳定分析与新能源并网(E-mail:daibozhi123@163.com);
马志远(1996 —),男,硕士,主要研究方向为新能源发电功率预测(E-mail:450102025@qq.com)。
收稿:2025-03-05,
修回:2025-06-30,
网络首发:2023-06-07,
纸质出版:2026-05-10
移动端阅览
杨茂,代博祉,马志远等.基于多尺度特征融合与多任务学习的短期风电功率预测方法[J].电力自动化设备,2026,46(05):110-117.
Yang Mao,Dai Bozhi,Ma Zhiyuan,et al.Short-term wind power forecasting method based on multi-scale feature fusion and multi-task learning[J].Electric Power Automation Equipment,2026,46(05):110-117.
杨茂,代博祉,马志远等.基于多尺度特征融合与多任务学习的短期风电功率预测方法[J].电力自动化设备,2026,46(05):110-117. DOI: 10.16081/j.epae.202601010.
Yang Mao,Dai Bozhi,Ma Zhiyuan,et al.Short-term wind power forecasting method based on multi-scale feature fusion and multi-task learning[J].Electric Power Automation Equipment,2026,46(05):110-117. DOI: 10.16081/j.epae.202601010.
为解决广域空间尺度下高维气象特征导致的风电场集群功率预测的高复杂度建模问题,提出一种基于多尺度特征融合与多任务学习的短期风电功率预测方法,其中多尺度特征融合实现了全局、集群、场站3种尺度的特征融合。从全局、集群、场站3个角度分别构建特征提取模块,并基于全局块级注意力与动态混合的稀疏图注意力降低模型的复杂度,提高运算效率;将集群预测任务分解为直接预测、间接预测、融合预测3个任务,通过多任务学习实现集群预测。将所提方法应用于吉林省某风电集群,结果表明,所提方法可以有效提升模型的运算效率和风电功率的预测精度。
In order to solve the problem of high-complexity modeling for wind farm cluster power forecas-ting caused by high-dimensional meteorological features in wide-area spatial scale,a short-term wind power forecasting method based on multi-scale feature fusion and multi-task learning is proposed,in which,the multi-scale feature fusion realizes the feature fusion of global,cluster and station scales. The feature extraction modules are constructed from global,cluster and station perspectives respectively,and on the basis of global block-wise attention and dynamic hybrid sparse graph attention,the model complexity is reduced and the computational efficiency is improved. The cluster forecasting task is decomposed into three tasks of direct prediction,indirect prediction,and fused prediction,and the cluster forecasting is realized through multi-task learning. The proposed method is applied in a wind farm cluster of Jilin Province,and the results show that the proposed method can effectively improve the model computational efficiency and wind power forecasting accuracy.
张海莺 . 一季度能源供应充足 消费结构持续优化 [N]. 中国改革报 , 2025-05-07 (4).
辛保安 . 新型电力系统构建方法论研究 [J]. 新型电力系统 , 2023 , 1 ( 1 ): 1 - 18 .
Xin Baoan . Research on the methodology of constructing new power systems [J]. New Type Power Systems , 2023 , 1 ( 1 ): 1 - 18 .
杨茂 , 韩超 , 张薇 . 基于深度图聚类和特征重构的风电集群功率短期预测方法 [J]. 电力自动化设备 , 2025 , 45 ( 4 ): 53 - 59 .
Yang Mao , Han Chao , Zhang Wei . Short-term power prediction method for wind farm cluster based on deep graph cluste-ring and feature reconstruction [J]. Electric Power Automation Equipment , 2025 , 45 ( 4 ): 53 - 59 .
柳玉 , 赵延顺 , 张沛 . 考虑功率预测偏差和出力调节不确定性的风电集群功率分配策略 [J]. 电力自动化设备 , 2024 , 44 ( 2 ): 110 - 116 .
Liu Yu , Zhao Yanshun , Zhang Pei . Power allocation strategy of wind power cluster considering power forecasting deviation and output regulation uncertainty [J]. Electric Power Automation Equipment , 2024 , 44 ( 2 ): 110 - 116 .
刘鸿鹏 , 李宏伟 , 马建伟 , 等 . 考虑源-荷不确定性的电热联合系统分布鲁棒优化调度 [J]. 电力自动化设备 , 2023 , 43 ( 8 ): 1 - 8 .
Liu Hongpeng , Li Hongwei , Ma Jianwei , et al . Distributionally robust optimal dispatching of integrated electricity and hea-ting system considering source-load uncertainty [J]. Electric Power Automation Equipment , 2023 , 43 ( 8 ): 1 - 8 .
黄玲玲 , 石孝华 , 符杨 , 等 . 基于DCGCN模型的海上风电场超短期功率预测 [J]. 电力系统自动化 , 2024 , 48 ( 15 ): 64 - 72 .
Huang Lingling , Shi Xiaohua , Fu Yang , et al . Ultra-short-term power prediction for offshore wind farms based on dual channel graph convolution network model [J]. Automation of Electric Power Systems , 2024 , 48 ( 15 ): 64 - 72 .
Shanmugam L , Joo Y H . Stability and stabilization for T-S fuzzy large-scale interconnected power system with wind farm via sampled-data control [J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems , 2021 , 51 ( 4 ): 2134 - 2144 .
Ge X L , Qian J , Fu Y , et al . Transient stability evaluation cri-terion of multi-wind farms integrated power system [J]. IEEE Transactions on Power Systems , 2022 , 37 ( 4 ): 3137 - 3140 .
Niu T , Wang J Z , Du P , et al . WPFSAD:wind power forecas-ting system integrating dual-stage attention and deep learning [J]. IEEE Transactions on Industrial Informatics , 2023 , 19 ( 11 ): 11252 - 11264 .
Yang B , Zhu T J , Cao P L , et al . Classification and summa-rization of solar irradiance and power forecasting methods:a thorough review [J]. CSEE Journal of Power and Energy Sys-tems , 2023 , 9 ( 3 ): 978 - 995 .
Liu D G , Wang W Q , Zhang H E , et al . Day-ahead and intra-day optimal scheduling considering wind power forecasting errors [J]. Sustainability , 2023 , 15 ( 14 ): 10892 .
欧阳静 , 秦龙 , 王坚锋 , 等 . 基于PCA-ShapeDTW-QWGRU的分布式光伏集群短期功率预测 [J]. 太阳能学报 , 2024 , 45 ( 5 ): 458 - 467 .
Ouyang Jing , Qin Long , Wang Jianfeng , et al . Short-term power prediction for distributed pv clusters based on PCA-ShapeDTW-QWGRU [J]. Acta Energiae Solaris Sinica , 2024 , 45 ( 5 ): 458 - 467 .
杨茂 , 彭天 , 苏欣 . 基于预测信息二维坐标动态划分的风电集群功率超短期预测 [J]. 中国电机工程学报 , 2022 , 42 ( 24 ): 8854 - 8863 .
Yang Mao , Peng Tian , Su Xin . Ultra-short term wind power prediction based on two-dimensional coordinate dynamic division of prediction information [J]. Proceedings of the CSEE , 2022 , 42 ( 24 ): 8854 - 8863 .
张哲 , 王勃 . 基于CBAM-LSTM的风电集群功率短期预测方法 [J]. 东北电力大学学报 , 2024 , 44 ( 1 ): 1 - 8 .
Zhang Zhe , Wang Bo . Short-term power prediction method of wind power cluster based on CBAM-LSTM [J]. Journal of Northeast Dianli University , 2024 , 44 ( 1 ): 1 - 8 .
乔宽龙 , 董存 , 车建峰 , 等 . 时空特性下基于图卷积神经网络的风电集群功率短期预测方法 [J]. 太阳能学报 , 2024 , 45 ( 5 ): 95 - 103 .
Qiao Kuanlong , Dong Cun , Che Jianfeng , et al . Short-term prediction method of wind power clusters based on graph convolution neural network under spitio-temporal characteristics [J]. Acta Energiae Solaris Sinica , 2024 , 45 ( 5 ): 95 - 103 .
邓韦斯 , 车建峰 , 汪明清 , 等 . 基于网格型数值天气预报的风电集群日前功率预测方法 [J]. 南方电网技术 , 2024 , 18 ( 6 ): 51 - 57,78 .
Deng Weisi , Che Jianfeng , Wang Mingqing , et al . Day-ahead power forecasting method of wind cluster based on grid nume-rical weather prediction [J]. Southern Power System Technology , 2024 , 18 ( 6 ): 51 - 57,78 .
战文华 , 车建峰 , 王勃 , 等 . 基于网格化数值天气预报的区域光伏发电多输出功率预测方法 [J]. 中国电力 , 2024 , 57 ( 3 ): 144 - 151 .
Zhan Wenhua , Che Jianfeng , Wang Bo , et al . A grid-based numerical weather prediction method for multi-output prediction of regional photovoltaic power [J]. Electric Power , 2024 , 57 ( 3 ): 144 - 151 .
Allenspach S , Hiss J A , Schneider G . Neural multi-task lear-ning in drug design [J]. Nature Machine Intelligence , 2024 , 6 ( 2 ): 124 - 137 .
Yang M , Huang Y T , Xu C Y , et al . Review of several key processes in wind power forecasting:mathematical formulations,scientific problems,and logical relations [J]. Applied Energy , 2025 , 377 : 124631 .
Yang M , Guo Y F , Huang T , et al . Power prediction conside-ring NWP wind speed error tolerability:a strategy to improve the accuracy of short-term wind power prediction under wind speed offset scenarios [J]. Applied Energy , 2025 , 377 : 124720 .
Peng X S , Cheng K , Lang J X , et al . Short-term wind power prediction for wind farm clusters based on SFFS feature selection and BLSTM deep learning [J]. Energies , 2021 , 14 ( 7 ): 1894 .
Qu Z J , Hou X X , Li J , et al . Short-term wind farm cluster power prediction based on dual feature extraction and quadra-tic decomposition aggregation [J]. Energy , 2024 , 290 : 130155 .
杜明山 , 张海清 , 李代伟 , 等 . 基于多任务学习的短期风能发电功率预测研究 [J]. 软件导刊 , 2025 , 24 ( 4 ): 32 - 41 .
Du Mingshan , Zhang Haiqing , Li Daiwei , et al . Research on short-term wind power prediction based on multi-task learning [J]. Software Guide , 2025 , 24 ( 4 ): 32 - 41 .
陈殿昊 , 臧海祥 , 刘璟璇 , 等 . 基于多视角特征提取与多任务学习的光伏功率多步预测 [J]. 高电压技术 , 2024 , 50 ( 9 ): 3924 - 3933 .
Chen Dianhao , Zang Haixiang , Liu Jingxuan , et al . Multi-step prediction of photovoltaic power based on multi-view features extraction and multi-task learning [J]. High Voltage Enginee-ring , 2024 , 50 ( 9 ): 3924 - 3933 .
庞森深 . 基于数据驱动和多任务学习的短期光伏发电功率预测方法 [D]. 南宁 : 广西大学 , 2023 .
Pang Senshen . A short term photovoltaic power prediction method based on data-driven and multi-task learning [D]. Nanning : Guangxi University , 2023 .
Niño-Adan I , Manjarres D , Landa-Torres I , et al . Feature weigh-ting methods:a review [J]. Expert Systems with Applications , 2021 , 184 : 115424 .
Wang S N , Li B Z , Khabsa M , et al . Linformer:self-attention with linear complexity [PP/OL]. V3. arXiv ( 2020-06-14 )[ 2025-05-10 ]. https:∥doi.org/10.48550/arXiv.2006.04768 https://doi.org/10.48550/arXiv.2006.04768 .
Nemirko A P , Dulá J H . Machine learning algorithm based on convex hull analysis [J]. Procedia Computer Science , 2021 , 186 : 381 - 386 .
Veličković P , Cucurull G , Casanova A , et al . Graph attention networks [PP/OL]. V3. arXiv ( 2018-02-04 )[ 2025-05-10 ]. https:∥doi.org/10.48550/arXiv.1710.10903 https://doi.org/10.48550/arXiv.1710.10903 .
冯双 , 杨浩 , 崔昊 , 等 . 基于Copula传递熵的设备级和网络级宽频振荡传播路径分析及振荡源定位方法 [J]. 电工技术学报 , 2024 , 39 ( 16 ): 4996 - 5010 .
Feng Shuang , Yang Hao , Cui Hao , et al . Device and network level wideband oscillations propagation path analysis and source localization method based on Copula transfer entropy [J]. Transactions of China Electrotechnical Society , 2024 , 39 ( 16 ): 4996 - 5010 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621