太阳能学报

融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测

PDF下载

太阳能学报 | 2026,47(6): 296-305

收起

太阳能学报 2026 , 47 (6) : 296 -305

融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测

全屏

余勇祥, 匡相宇, 韩建, 高波, 曾晗, 李泽文

作者信息

MAMBA-TRANSFORMER ULTRA-SHORT-TERM WIND POWER PREDICTION BY INTEGRATING PHYSICAL CONSTRAINTS AND MULTISCALE FEATURES

Yu Yongxiang, Kuang Xiangyu, Han Jian, Gao Bo, Zeng Han, Li Zewen

Affiliations

doi: 10.19912/j.0254-0096.tynxb.2025-0079

文章导航

摘要

收起

提出一种融合物理约束与多尺度特征的Mamba-Transformer模型,用于超短期风电功率预测。该模型通过自适应噪声完备经验模态分解风电功率数据,提取不同频率下的非线性与非平稳特征,并将分解后的模态函数与风电场气象数据输入Mamba模型,挖掘局部时变特性。再利用Transformer模型的自注意力机制捕捉多尺度特征间的长距离依赖关系。最后,结合一维Jensen尾流模型构建物理约束,通过自适应加权机制整合物理模型与数据驱动模型预测结果。实验结果表明,该文提出的模型与Transformer相比,均方根误差（RMSE）和平均绝对误差（MAE）分别降低41.29%和50.26%。该模型在提高风电功率预测精度的同时,展现出较高的泛化能力。

关键词

风电功率预测 / 物理约束 / 自适应噪声完备经验模态分解 / Mamba / Transformer / 一维Jensen尾流模型

Abstract

收起

We propose a Mamba-Transformer model integrating physical constraints and multi-scale features for ultra-short-term wind power forecasting. The proposed model employs complete ensemble empirical mode decomposition with adaptive noise to capture nonlinear and nonstationary patterns in wind power data across multiple frequency components. The decomposed modal functions are then fed into the Mamba model alongside meteorological data from the wind farm to uncover local time-varying properties. The self-attention mechanism of the Transformer model is then employed to capture long-range dependencies among multi-scale features. Finally, a one-dimensional Jensen wake model is integrated to establish physical constraints, integrating the prediction results of physical models and data-driven models through an adaptive weighting mechanism. Experimental results demonstrate that compared to the Transformer model, the proposed model reduces root mean square error （RMSE） and mean absolute error （MAE） by 41.29% and 50.26%, respectively. This model enhances wind power forecasting accuracy while exhibiting strong generalization capabilities.

Key words

wind power forecasting / physical constraint / CEEMDAN / Mamba / Transformer / one-dimensional Jensen wake model

引用本文

余勇祥, 匡相宇, 韩建, 高波, 曾晗, 李泽文. 融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测. 太阳能学报, 2026 , 47 (6) : 296 -305 . DOI: 10.19912/j.0254-0096.tynxb.2025-0079

Yu Yongxiang, Kuang Xiangyu, Han Jian, Gao Bo, Zeng Han, Li Zewen. MAMBA-TRANSFORMER ULTRA-SHORT-TERM WIND POWER PREDICTION BY INTEGRATING PHYSICAL CONSTRAINTS AND MULTISCALE FEATURES[J]. Acta Energiae Solaris Sinica, 2026 , 47 (6) : 296 -305 . DOI: 10.19912/j.0254-0096.tynxb.2025-0079

基金

收起

国家自然科学基金（52367015; 52277148）; 中国博士后科学基金（2024M750897）; 江西省自然科学基金（20232BAB214061）

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1] 舒印彪, 赵勇, 赵良, 等. “双碳”目标下我国能源电力低碳转型路径[J]. 中国电机工程学报, 2023, 43(5): 1663-1671.
SHU Y B, ZHAO Y, ZHAO L, et al.Study on low carbon energy transition path toward carbon peak and carbon neutrality[J]. Proceedings of the CSEE, 2023, 43(5): 1663-1671.
[2] LIU M D, DING L, BAI Y L.Application of hybrid model based on empirical mode decomposition, novel recurrent neural networks and the ARIMA to wind speed prediction[J]. Energy conversion and management, 2021, 233: 113917.
[3] YUAN X H, TAN Q X, LEI X H, et al.Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine[J]. Energy, 2017, 129: 122-137.
[4] XIANG L, FU X, YAO Q T, et al.A novel model for ultra-short term wind power prediction based on Vision Transformer[J]. Energy, 2024, 294: 130854.
[5] LI Y, WANG R N, LI Y Z, et al.Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach[J]. Applied energy, 2023, 329: 120291.
[6] LI Y H, WANG H, YAN J, et al.Ultra-short-term wind power forecasting based on the strategy of “dynamic matching and online modeling”[J]. IEEE transactions on sustainable energy, 2025, 16(1): 107-123.
[7] 王颉, 刘兴杰, 梁英, 等. 一种基于MGWO-Informer的超短期风电功率预测方法[J]. 太阳能学报, 2024, 45(11): 477-485.
WANG J, LIU X J, LIANG Y, et al.An ultra-short-term wind power prediction method based on MGWO-Informer[J]. Acta energiae solaris sinica, 2024, 45(11): 477-485.
[8] 邬永, 王冰, 陈玉全, 等. 融合精细化气象因素与物理约束的深度学习模型在短期风电功率预测中的应用[J]. 电网技术, 2024, 48(4): 1455-1465, I0022, I0023, I0024.
WU Y, WANG B, CHEN Y Q, et al. Application of deep learning model integrating refined meteorological factors and physical constraints in short-term wind power prediction[J]. Power system technology, 2024, 48(4): 1455-1465, I0022, I0023, I0024.
[9] 刘凡, 李捍东, 覃涛. 基于CEEMDAN-AsyHyperBand-MultiTCN的短期风电功率预测[J]. 太阳能学报, 2024, 45(1): 151-158.
LIU F, LI H D, QIN T.Short-term wind power prediction based on CEEMDAN-AsyHyperBand-MultiTCN[J]. Acta energiae solaris sinica, 2024, 45(1): 151-158.
[10] 郭喜峰, 王凯泽, 单丹, 等. 多角度基于CEEMDAN-CNN-BiLSTM模型的锂离子电池RUL预测[J]. 太阳能学报, 2024, 45(7): 181-189.
GUO X F, WANG K Z, SHAN D, et al.RUL prediction for lithium ion batteries based on CEEMDAN-CNN-BiLSTM model from multiple perspectives[J]. Acta energiae solaris sinica, 2024, 45(7): 181-189.
[11] GU A, DAO T, ERMON S, et al.Hippo: recurrent memory with optimal polynomial projections[J]. Advances in neural information processing systems, 2020, 33: 1474-1487.
[12] GU A, GOEL K, RÉ C.Efficiently modeling long sequences with structured state spaces[C]//International Conference on Learning Representations (ICLR). 2022.
[13] GU A, JOHNSON I, GOEL K, et al.Combining recurrent, convolutional, and continuous-time models with linear state-space layers[J]. Advances in neural information processing systems, 2021, 34: 572-585.
[14] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[PP/OL]. V2. arXiv (2024-05-31). https://doi.org/10.48550/arXiv.2312.00752.
[15] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, California, USA, 2017: 6000-6010.
[16] 杨伟峰, 文云峰, 李立, 等. 考虑疲劳载荷的风电场分散式频率响应策略[J]. 电力自动化设备, 2022, 42(4): 55-62.
YANG W F, WEN Y F, LI L, et al.Decentralized frequency response strategy for wind farm considering fatigue load[J]. Electric power automation equipment, 2022, 42(4): 55-62.
[17] 胡阳, 张冲, 房方, 等. 基于主动尾流控制的风电机群协同优化调度[J]. 动力工程学报, 2024, 44(4): 566-574.
HU Y, ZHANG C, FANG F, et al.Cooperative and optimal scheduling of wind turbine groups based on active wake control[J]. Journal of Chinese Society of Power Engineering, 2024, 44(4): 566-574.
[18] 李练兵, 高国强, 吴伟强, 等. 考虑特征重组与改进Transformer的风电功率短期日前预测方法[J]. 电网技术, 2024, 48(4): 1466-1476, I0025, I0027-I0029.
LI L B, GAO G Q, WU W Q, et al. Short-term day-ahead wind power prediction considering feature recombination and improved transformer[J]. Power system technology, 2024, 48(4): 1466-1476, I0025, I0027-I0029.
[19] GUAN S J, WANG Y S, LIU L M, et al.Ultra-short-term wind power prediction method based on FTI-VACA-XGB model[J]. Expert systems with applications, 2024, 235: 121185.

2026年第47卷第6期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.19912/j.0254-0096.tynxb.2025-0079

接收时间：2025-01-14
首发时间：2026-07-17

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-01-14

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/tynxb/CN/10.19912/j.0254-0096.tynxb.2025-0079

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT