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

余勇祥; 匡相宇; 韩建; 高波; 曾晗; 李泽文

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

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2026-07-22

- 融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测
- Vol. 47, Issue 6, Pages: 296-305(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19912/j.0254-0096.tynxb.2025-0079
  CLC： TM614
- Online First：08 July 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
余勇祥, 匡相宇, 韩建, et al. 融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测[J]. 2026, 47(6): 296-305.
DOI：

余勇祥, 匡相宇, 韩建, et al. 融合物理约束与多尺度特征的Mamba-Transformer超短期风电功率预测[J]. 2026, 47(6): 296-305. DOI： 10.19912/j.0254-0096.tynxb.2025-0079.

摘要

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。

Abstract

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.

关键词

Keywords

references

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

GU A, GOEL K, RÉ C.Efficiently modeling long sequences with structured state spaces[C]//International Conference on Learning Representations (ICLR). 2022.

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.

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.

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.

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.

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.

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.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于改进SVR-SSA-BiLSTM误差修正的短期风电功率混合预测模型研究

基于DGAT-Transformer组合算法的区域光伏出力数据质量增强与超短期功率预测方法

基于MODWT-BiLSTM-BiGRU的风电功率预测

基于BiTCN-Informer的新型超短期风电功率组合预测方法

基于PXGBoost-GAE-GMM-GRU多风力机功率预测

Related Author

葛伟

顾彬

吴子辰

胡皓

王莘然

常喜强

甄钊

任惠

Related Institution

Energy Development Research Institute, China Southern Power Grid

School of Electrical Engineering, Guangxi University

Beihai Power Supply Bureau, Guangxi Power Grid

Guangxi Power Grid Dispatching Control Center

Chian Electric Power Research Institute

AI问答

⁰