[1]蒋建东,刘明宇,王昱龙,等.基于风场空间与气象融合的风电集群短期功率预测[J].郑州大学学报(工学版),2027,48(XX):1-9.[doi:10. 13705 / j. issn. 1671-6833. 2026. 02. 005]
　WEI Zhenzhu,LIU Mingyu,WANG Yulong,et al.Short-term Power Prediction of Wind Power Clusters Based on Wind Field Spatial and Meteorological Fusion[J].Journal of Zhengzhou University (Engineering Science),2027,48(XX):1-9.[doi:10. 13705 / j. issn. 1671-6833. 2026. 02. 005]
点击复制

基于风场空间与气象融合的风电集群短期功率预测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
48
期数:
2027年XX
页码:
1-9
栏目:
出版日期:
2027-12-10

文章信息/Info

Title:
Short-term Power Prediction of Wind Power Clusters Based on Wind Field Spatial and Meteorological Fusion
作者:
蒋建东' target="_blank" rel="external">蒋建东1，刘明宇1，王昱龙1，周 燕2，蒋建东' target="_blank" rel="external">蒋建东1
1. 郑州大学 电气与信息工程学院,河南 郑州 450001;2. 国网河南省电力公司洛阳供电公司,河南 洛阳 471000
Author(s):
WEI Zhenzhu1, LIU Mingyu1, WANG Yulong1, ZHOU Yan2, JIANG Jiandong1
1. School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China; 2. Luoyang Power Supply Company of State Grid Henan Electric Power Company, Luoyang 471000, China
关键词:
风电集群功率预测; 时空图卷积神经网络; 多头自注意力机制; 图数据结构; 深度学习
Keywords:
wind power cluster forecasting;  spatio-temporal graph convolutional neural network;  multi-head self-attention mechanism;  graph data structure;  deep learning
分类号:
TM614TP183
DOI:
10. 13705 / j. issn. 1671-6833. 2026. 02. 005
文献标志码:
A
摘要:
针对传统风电集群功率预测方法在空间上未有效考虑场站间气象关联特性,难以基于单场预测高效推演集群整体功率的问题,为充分挖掘离散型数值气象预报(NWP) 异构气象信息的时空耦合复杂特性嵌入表征,提出一种基于注意力时空嵌入机制的多维度场站时空信息融合框架。 首先,利用多头自注意力机制( Multi-Head Self-Attention)直接融合空间特征,增强模型对多场站空间功率关联的捕捉能力。 其次,基于最大信息系数解构集群位置信息,构建反映气象关联的非欧几里得图数据结构,并结合时空注意力机制实现场站及其邻域时空特征的交叉融合,动态调整场站间影响权重以捕捉时空动态相关性。 并通过编-解码器架构将空间与时空特征集成至统一语义空间,捕获序列时间连续性。 最后,基于中国西北某地区实际风电场运行数据对所提模型进行验证。 实验结果表明:所提方法在对比其余 6 种预测模型时,RMSE 与 MAE 两项误差评价指标均显著降低,有效验证其先进性与适应性。
Abstract:
Given that traditional wind power cluster prediction methods fail to effectively account for the spatial meteorological correlations among stations and struggle to efficiently deduce the overall cluster power based on single-station predictions, this paper proposes a multi-dimensional spatiotemporal information fusion framework for stations based on an attention-based spatiotemporal embedding mechanism. This framework aims to fully exploit the complex spatiotemporally coupled characteristics embedded within discrete Numerical Weather Prediction (NWP) heterogeneous meteorological information. Firstly, a Multi-Head Self-Attention mechanism is employed to directly fuse spatial features, enhancing the model’s ability to capture spatial power correlations across multiple stations. Secondly, cluster location information is deconstructed using the Maximal Information Coefficient (MIC) to construct a non-Euclidean graph data structure reflecting meteorological correlations. This is combined with a Spatial-Temporal Attention mechanism to achieve cross-fusion of spatiotemporal features between stations and their neighborhoods, dynamically adjusting the influence weights among stations to capture spatiotemporal dynamic dependencies. Furthermore, an encoder-decoder architecture integrates spatial and spatiotemporal features into a unified semantic space to capture temporal continuity within sequences. Finally, the proposed model is verified based on the actual wind farm operation data of a certain region in Northwest China.Experimental results show that when the proposed method is compared with the other 6 prediction models, the reduction amplitudes of theERMSE error index are 15.32, 13.55, 17.80, 16.13, 6.90, and 2.64 percentage points respectively. The decrease amplitudes of theEMAE error index are 20.56, 16.15, 18.67, 12.59, 8.38, and 3.02 percentage points respectively, which effectively verify its advancement and adaptability

参考文献/References:

[1]. 邵桂萍,许洪华. 可再生能源综合系统现状与未来发展趋势研究[J]. 太阳能,2024(7):127-132.
[2]. SHAO G P, XU H H. Research on present situation and future development trend of renewable energy integeated system[J]. Solar Energy, 2024(7): 129-134.
[3]. SOLÉ J, GARCÍA-OLIVARES A, TURIEL A, et al. Renewable transitions and the net energy from oil liquids: a scenarios study[J]. Renewable Energy, 2018, 116: 258-271.
[4]. 张文煜，马可可，郭振海，等. 基于灰狼算法和极限学习机的风速多步预测[J]. 郑州大学学报（工学版）,2024,45(2):89-96.
[5]. ZHANG W Y, MA K K, GUO Z H, et al. Multistep prediction of wind speed based on grey wolf algorithm and extreme learning machine [J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(2): 89-96.
[6]. 涂青宇,苗世洪,林毓军,等. 基于动态R藤Copula模型的区域风电集群超短期功率区间预测方法[J]. 高电压技术,2022,48(2):456-466.
[7]. TU Q Y, MIAO S H, LIN Y J, et al. Ultra-short-term interval forecasting method for regional wind farms based on dynamic r-vine copula model[J]. High Voltage Engineering, 2022,48(2):456-466.
[8]. 朱梓彬,孟安波,欧祖宏,等. 基于多元模态分解与多目标算法优化的深度集成学习模型的超短期风电功率预测[J]. 现代电力,2024,41(3):458-469.
[9]. ZHU Z B, MENG A B, OU Z H, et al. Ultra-short-term wind power prediction based on deep ensemble learning model using multivariate mode decomposition and multi-objective optimization[J]. Modern Electric Power, 2024,41(3):458-469.
[10]. 吴霓. 基于集成模型的风电功率预测方法研究[D]. 湖北:湖北工业大学,2023.
[11]. WU N. Research on wind power prediction method based on ensemble model[D]. Hubei: Hubei University of Technology, 2023.
[12]. 向阳.基于CNN-LSTM模型的风电场集群短期功率预测方法研究[D]. 华北电力大学(北京),2024.
[13]. XIANG Y. Research on short term power method of wind farm cluster based on CNN-LSTM variant model[D]. North China Electric Power University (Beijing), 2024.
[14]. 李超峰,原升耀,王灵梅,等.基于Informer的风电场超短期功率预测[J].山西大学学报(自然科学版),2024,47(06):1201-1210.
[15]. LI C F, YUAN S Y, WANG L M, et al. U ltra-short-term power prediction for wind farms based on Informer[J]. Journal of Shanxi University (Natural Science Edition), 2024, 47(6): 1201-1210.
[16]. 顾婷婷,黄亦露,王亚男,等.基于多头注意力机制的ResNet-UNet短期风电功率预测[J/OL].太阳能学报,1-6.
[17]. GU T T, HUANG Y L, WANG Y N, et al. ResNet-UNet short-term wind power prediction with introduction of multi-head attention mechanism[J/OL]. Acta Energiae Solaris Sinica, 1-6.
[18]. 周丽娜,刘旭东.基于CNN-LSTM的短期风电功率预测方法研究[J].黑龙江工程学院学报,2024,38(06):44-50.
[19]. ZHOU L N, LIU X D. Research on short term wind power prediction method based on CNN-LSTM[J]. Journal of Heilongjiang Institute of Technology, 2024, 38(6): 44-50.
[20]. CHEN G，SHAN J N，LI D Y，et al. Research on wind power prediction method based on convolutional neural network and genetic algorithm[C]//2019 IEEE Innovative Smart Grid Technologies- Asia （ISGT Asia）. Chengdu，China，2019: 3573-3578.
[21]. 刘勇,杨熙卉,燕林滋,等. CEEMD双层分解和Granger因果变量选择风电功率预测[J]. 中国测试,2023,49(4):98-105.
[22]. LIU Y, YANG X H, YAN L Z, et al. Wind power prediction based on CEEMD and Granger causality variable selection[J]. China Measurement, 2023, 49(4): 98-105.
[23]. 郑颖颖,李鑫,陈延旭,等. 基于Stacking多模型融合的极端天气短期风电功率预测方法[J]. 高电压技术,2024,50(9):3871-3882.
[24]. ZHENG Y Y, LI X, CHEN Y X, et al. Short-term wind power forecasting method in extreme weather based on Stacking multi-model fusion[J]. High Voltage Engineering, 2024, 50(9): 3871-3882.
[25]. 张浩田,温蜜,李晋国,等. 数据驱动的时间注意力卷积风电功率预测模型[J]. 太阳能学报,2022,43(10):167-176.
[26]. ZHANG H T, WEN M, LI J G, et al. Data-driven time attention convolution wind power prediction model[J]. Acta Energiae Solaris Sinica, 2022, 43(10): 167-176.
[27]. RAO R M, LIU J, VERKUIL R, etal. MSA transformer [C]//Proceedingsof the 38th International Conference on Machine Learning. Singapore: PMLR, 2021: 8844-8856.
[28]. ZHANG G, LIU H C, ZHANG J B, et al. Wind power prediction based on variational mode decomposition multifrequency combinations[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7(2): 281-288.
[29]. BAI J D, ZHU J W, SONG Y J, et al. A3T- GCN: attention temporal graph convolutional network for traffic forecasting [J]. ISPRS International Journal of Geo-Information, 2021, 10(7): 485.
[30]. 叶林,李奕霖,裴铭,等. 寒潮天气小样本条件下的短期风电功率组合预测[J]. 中国电机工程学报,2023,43(2):543-555.
[31]. YE L, LI Y L, PEI M, et al. Combined approach for short - term wind power forecasting under cold weather with small sample[J]. Proceedings of The CSEE, 2023, 43(2): 543 - 555.
[32]. 徐武,范鑫豪,沈智方,等. 多尺度特征提取的Transformer短期风电功率预测[J]. 太阳能学报,2025,46(2):640-648.
[33]. XU W, FAN X H, SHEN Z F, et al.Short-term wind power prediction using Transformer with multi-scale feature extraction[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 640-648.
[34]. 刘腾飞,陈李越,房江祎,等. SCFNet:一种面向时空预测的外部空间特征融合框架[J]. 计算机科学,2025,52(4):110-118.
[35]. LIU T F, CHEN L Y, FANG J Y, et al. SCFNet:fusion framework of external spatial features for spatio-temporal prediction[J]. Computer Science, 2025, 52(4): 110-118.
[36]. 王晓东,栗杉杉,刘颖明,等. 基于特征变权的超短期风电功率预测[J]. 太阳能学报,2023,44(2):52-58.
[37]. WANG X D, LI S S, LIU Y M, et al. Ultra-short-term wind power prediction based on variable feature weight[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 52-58.
[38]. 蒲晓云,杨靖,杨兴,等. 基于分解技术的IZOA-Transformer-BiGRU短期风电功率预测[J]. 电子测量技术,2025,48(2):39-48.
[39]. PU X Y, YANG J, YANG X, et al. IZOA-Transformer-BiGRU short-term wind power prediction based on decomposition technique[J]. Electronic Measurement Technology, 2025, 48(2): 39-48.

备注/Memo

备注/Memo:
收稿日期:2026-01-26;修订日期:2026-03-29基金项目:河南省高等学校重点科研项目(24A470009)作者简介:魏臻珠(1977— ) ,女,青海西宁人,郑州大学讲师,主要从事电力系统电能质量分析与控制研究,E-mail: jdjiang@ zzu. edu. cn。通信作者:蒋建东(1975— ) ,男,河南南阳人,郑州大学教授,博士,主要从事电力系统电能质量分析与控制、新能源技术等研究,E-mail:zzwei@ zzu. edu. cn。
更新日期/Last Update: 2026-05-26