考虑来流风速特征的风电机组超短期功率预测方法

卢鸿坤; 高晓霞; 张焕强; 麻宏宇; 朱霄珣; 王瑜

doi:10.7638/kqdlxxb-2025.0173

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

考虑来流风速特征的风电机组超短期功率预测方法

研究专栏——新一代风电空气动力学 | 更新时间：2026-07-11

- 考虑来流风速特征的风电机组超短期功率预测方法
- An ultra-short-term power prediction method for wind turbines considering inflow wind speed characteristics
- 空气动力学学报 2026年44卷第6期页码：146-156
- 作者机构：
  
  1. 华北电力大学动力工程系,保定,071003
  2. 华北电力大学燕赵电力实验室,保定,071003
  3. 河北省低碳高效发电技术重点实验室,保定,071003
  4. 保定市低碳高效发电技术重点实验室,保定,071003
- 作者简介：
  
  卢鸿坤，研究方向：风电机组功率预测. E-mail：hongkunlu@hotmail.com
  高晓霞*，研究方向：风能应用. E-mail：okspringgao@hotmail.com
- 基金信息：
  
  国家自然科学基金（52576204）
- DOI：10.7638/kqdlxxb-2025.0173
  中图分类号： TK89
- 纸质出版：2026
- 稿件说明：
移动端阅览
卢鸿坤, 高晓霞, 张焕强, 等. 考虑来流风速特征的风电机组超短期功率预测方法[J]. 空气动力学学报, 2026, 44(6): 146−156.

Lu Hongkun, Gao Xiaoxia, Zhang Huanqiang, et al. An ultra-short-term power prediction method for wind turbines considering inflow wind speed characteristics[J]. 2026, 44(6): 146-156.
卢鸿坤, 高晓霞, 张焕强, 等. 考虑来流风速特征的风电机组超短期功率预测方法[J]. 空气动力学学报, 2026, 44(6): 146−156. DOI： 10.7638/kqdlxxb-2025.0173

Lu Hongkun, Gao Xiaoxia, Zhang Huanqiang, et al. An ultra-short-term power prediction method for wind turbines considering inflow wind speed characteristics[J]. 2026, 44(6): 146-156. DOI： 10.7638/kqdlxxb-2025.0173.

摘要

针对风电超短期功率预测中风速表征失真与模型动态响应不足的问题，本文提出一种融合高精度来流风速特征与TimeMixer模型的预测方法。首先，考虑风电场地形特性、机组间布局与尾流干扰，构建空间修正风速场并计算机组轮毂高度处未受扰动的真实来流风速；其次，以来流风速为输入特征，改进TimeMixer模型，在其中引入趋势性-高频波动性双通道特征分离机制，通过多尺度特征融合策略，强化模型对机组功率演化中高频波动与低频趋势的协同捕捉能力；最后，将本文预测方法与机舱风速模型进行对比，并利用云南曲靖山地风电场实测数据开展模型验证。结果表明：本文以来流风速为输入的改进TimeMixer模型在均方根误差

rmse

、平均绝对误差

mae

、相关系数

和合格率

4项指标上较机舱风速模型分别提升18.75%、25%、7.69%、6.37%；相较传统时间卷积网络（temporal convolutional network

TCN）与长短期记忆网络（long short-term memory

LSTM），改进TimeMixer模型在趋势跟踪与波动响应捕捉方面表现更优，相关系数

分别提升2.46%与5.04%。本文方法有效提升了超短期功率预测精度，可为高比例新能源电力系统稳定运行提供一定技术支撑。

Abstract

To address the challenges of wind speed representation distortion and insufficient dynamic response in ultra-short-term wind power prediction

this paper proposes a prediction method integrating high-fidelity inflow wind speed features with the TimeMixer model. First

considering the wind farm's terrain characteristic

turbine layout

and wake interference effects

a spatially corrected wind field is constructed to calculate the undisturbed inflow wind speed at hub height for each turbine. Second

using the incoming wind speed as the input feature

an improved TimeMixer model is developed

incorporating a dual-channel decomposition mechanism for trend and high-frequency fluctuation components. Through a multi-scale feature fusion strategy

the model's ability to jointly capture high-frequency fluctuations and low-frequency trends in turbine power evolution is enhanced. Finally

the proposed method is compared with the nacelle wind speed model

and validation is conducted using measured data from a mountainous wind farm in Qujing

Yunnan. The results show that the improved TimeMixer model with incoming wind speed input achieves improvements of 18.75%

25%

7.69% and 6.37% over the nacelle wind speed model in terms of root mean square error (

rmse

)

mean absolute error (

mae

)

and

respectively. Compared with the traditional temporal convolutional network (TCN) and long short-term memory (LSTM) network

the improved TimeMixer model exhibits superior performance in trend tracking and fluctuation response capture

with the correlation coefficient

improved by 2.46% and 5.04%

respectively. The proposed method effectively enhances ultra-short-term prediction accuracy and can provide technical support for the stable operation of power systems with a high penetration of renewable energy.

关键词

Keywords

references

金轩. “四个革命、一个合作”指引我国能源高质量发展[N]. 人民日报, 2025-04-09(6).

Lyu X, Groß D. Grid forming fast frequency response for PMSG-based wind turbines[J]. IEEE Transactions on Sustainable Energy, 2024, 15(1): 23−38. doi: 10.1109/TSTE.2023.3263858

Liu S Y, Li Q S, Lu B, et al. Prediction of offshore wind turbine wake and output power using large eddy simulation and convolutional neural network[J]. Energy Conversion and Management, 2025, 324: 119326. doi: 10.1016/j.enconman.2024.119326

Zhang Lan, Zhang Yong. Short-term wind power forecast based on Bayesian dynamic linear model error compensation[J]. Information Technology Informatization, 2022(9): 96−99(in Chinese). doi: 10.3969/j.issn.1672-9528.2022.09.024

Tao Tianyou, Deng Peng, Wang Hao, et al. Research progress and considerations on short-term prediction of extreme wind fields based on machine learning[J]. Acta Aerodynamica Sinica, 2025, 43(5): 78−91(in Chinese). doi: 10.7638/kqdlxxb-2025.0041

Zhang G, Liu H C, Zhang J B, et al. Wind power prediction based on variational mode decomposition multi-frequency combinations[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7(2): 281−288. doi: 10.1007/s40565-018-0471-8

Jiang Guoqian, Xu Xiangdong, Bai Jiarong, et al. Ultra-short-term wind power prediction based on multi-granularity temporal convolution network[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 104−111(in Chinese). doi: 10.19912/j.0254-0096.tynxb.2023-0006

Xiang L, Liu J N, Yang X, et al. Ultra-short term wind power prediction applying a novel model named SATCN-LSTM[J]. Energy Conversion and Management, 2022, 252: 115036. doi: 10.1016/j.enconman.2021.115036

Sun Y, Zhou Q B, Sun L, et al. CNN-LSTM-AM: a power prediction model for offshore wind turbines[J]. Ocean Engineering, 2024, 301: 117598. doi: 10.1016/j.oceaneng.2024.117598

Gong M J, Yan C C, Xu W, et al. Short-term wind power forecasting model based on temporal convolutional network and Informer[J]. Energy, 2023, 283: 129171. doi: 10.1016/j.energy.2023.129171

Wang L, He Y G, Li L, et al. A novel approach to ultra-short-term multi-step wind power predictions based on encoder-decoder architecture in natural language processing[J]. Journal of Cleaner Production, 2022, 354: 131723. doi: 10.1016/j.jclepro.2022.131723

Lin S M, Wang S, Xu X F, et al. GAOformer: an adaptive spatiotemporal feature fusion transformer utilizing GAT and optimizable graph matrixes for offshore wind speed prediction[J]. Energy, 2024, 292: 130404. doi: 10.1016/j.energy.2024.130404

Chen H, Wei S B, Yang W, et al. Input wind speed forecasting for wind turbines based on spatio-temporal correlation[J]. Renewable Energy, 2023, 216: 119075. doi: 10.1016/j.renene.2023.119075

Li S P, Li X, Jiang Y, et al. A novel frequency-domain physics-informed neural network for accurate prediction of 3D spatio-temporal wind fields in wind turbine applications[J]. Applied Energy, 2025, 386: 125526. doi: 10.1016/j.apenergy.2025.125526

Zhang Y G, Kong X, Wang J C, et al. A comprehensive wind speed prediction system based on intelligent optimized deep neural network and error analysis[J]. Engineering Applications of Artificial Intelligence, 2024, 128: 107479. doi: 10.1016/j.engappai.2023.107479

Wang Dongfeng, Ma Jinjie, Hu Yiran, et al. iTransformer short-term wind speed prediction based on VMD-FFCM feature enhancement[J]. Electric Power Science and Engineering, 2025, 41(8): 39−47(in Chinese). doi: 10.3969/j.ISSN.1672-0792.2025.08.005

Xiang Ling, Chen Jinpeng, Fu Xiaomengting, et al. Multi-step wind speed forecasting based on ViT and LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(9): 525−533(in Chinese). doi: 10.19912/j.0254-0096.tynxb.2023-0797

Yin Yuanya, Pan Wenhu, Zhao Wenguang, et al. Ultra-short-term wind speed prediction method based on CEEMDAN and BiLSTM-AM[J]. Electrical Measurement Instrumentation, 2024, 61(9): 77−84(in Chinese). doi: 10.19753/j.issn1001-1390.2024.09.010

Wang S Y, Wu H X, Shi X M, et al. TimeMixer: decomposable multiscale mixing for time series forecasting[C]//International Conference on Learning Representations (ICLR), 2024. doi: 10.48550/arXiv.2405.14616

Ramasamy P, Chandel S S, Yadav A K. Wind speed prediction in the mountainous region of India using an artificial neural network model[J]. Renewable Energy, 2015, 80: 338−347. doi: 10.1016/j.renene.2015.02.034

Wang Hao, Lyu Zhitong, Xin Zhiqiang, et al. Wind speed field of 15 MW offshore wind turbines considering typhoon spatiotemporal variability[J]. Journal of Vibration and Shock, 2024, 43(22): 253−260(in Chinese). doi: 10.13465/j.cnki.jvs.2024.22.028

Lu H K, Gao X X, Yu J X, et al. Analysis and prediction of incoming wind speed for turbines in complex wind farm: accounting for meteorological factors and spatiotemporal characteristics of wind farm[J]. Applied Energy, 2025, 381: 125135. doi: 10.1016/j.apenergy.2024.125135

Lu H K, Gao X X, Xu Z Y, et al. Wind direction prediction combined with wind speed in a wind farm[J]. Energy, 2025, 333: 137334. doi: 10.1016/j.energy.2025.137334

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

合成双射流的相干结构演化与卷吸效应：工作频率的影响

考虑海气耦合的海洋风环境中-微尺度数值模拟

基于CFD-CSD耦合仿真的风力机气弹稳定性及载荷分析

基于CFD仿真的漂浮式风力机尾流模型研究

差分格式应用于非均匀网格的精度保持算法