基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测

栾福明; 张衡; 陈海平

doi:10.19805/j.cnki.jcspe.2026.240699

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 >

基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测

新能源与储能 | 更新时间：2026-10-10

- 基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测
- Short-term Wind Power Output Prediction Based on FeatureSimilarity Day and CNN-BiLSTM-Attention Model
- 动力工程学报 2026年46卷第2期页码：80-88
- 作者机构：
  
  1. 华北电力大学能源动力与机械工程学院,北京,102206
  2. 中国大唐集团科学技术研究总院有限公司华北电力试验研究院,北京,100040
- 作者简介：
  
  栾福明(1981-),男,新疆乌鲁木齐人,博士研究生,研究方向为清洁能源利用理论与技术,E-mail:28155819@qq.com
- 基金信息：
  
  华北电力大学中央高校基本科研业务费专项资金(2023MS028);国家重点研发计划资助项目(2022YFB2403200)
- DOI：10.19805/j.cnki.jcspe.2026.240699
  中图分类号：
- 网络首发：2026-02-10，
  
  纸质出版：2026-02-10
- 稿件说明：
移动端阅览
栾福明,张衡,陈海平. 基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测动力工程学报, 2026, 46(2): 80-88 https://doi.

org/10.19805/j.cnki.jcspe.2026.240699
栾福明,张衡,陈海平. 基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测动力工程学报, 2026, 46(2): 80-88 https://doi. DOI： 10.19805/j.cnki.jcspe.2026.240699.

org/10.19805/j.cnki.jcspe.2026.240699 DOI：

摘要

短期风电功率预测对电力系统的实时调度至关重要

可靠的风电预测不仅能够保障电力系统的安全运行

还能提升电网的运行效率。为了获得更加准确、可靠的风电功率预测结果

针对风电功率数据的非线性和时序性特征

提出了一种将特征相似日和CNN-BiLSTM-Attention相结合的短期风电功率预测方法。首先

充分考虑气象因素对风电输出功率数据的影响

利用 Spearman相关系数筛选出与风电输出功率最相关的气象因子作为模型的输入参数。其次

采用高斯混合模型(GMM)对风电数据进行聚类分析

通过手肘法确定最佳的聚类簇数

并结合特征相似度和余弦相似熵方法

确定待测日与历史数据中最相关的聚类类型。最后

使用 CNN-BiLSTM-Attention模型进行训练

深度挖掘风电功率的时序特征

获得更加精准的风电功率预测结果。以新疆地区的实际风电功率数据为例进行了仿真分析

验证结果表明该方法的预测精度较高

能够为电力系统的规划与稳定运行提供有力支持。

Abstract

Short-term wind power forecasting is crucial for real-time dispatch of power systems. Reliable wind power forecasts not only ensure the safe operation of power system but also enhance the operational efficiency of power grid.To obtain more accurate and reliable wind power forecasting results

considering the nonlinear and time-series characteristics of wind power data

a short-term wind power forecasting method based on feature similarity day combined with CNN-BiLSTM-Attention was proposed. Firstly

the impact of meteorological factors on wind power output was fully considered

and the Spearman correlation coefficient was used to select the meteorological factors most correlated with wind power output as model input parameters. Next

the Gaussian mixture model (GMM) was used to conduct cluster analysis on the wind power data. The elbow method was used to determine the optimal number of clusters

and in combination with the feature similarity and cosine similarity entropy methods

the most relevant cluster type for the day under test was determined among the historical data. Finally

the CNN-BiLSTM-Attention model was used for training to deeply extract the temporal features of wind power and obtain more accurate wind power prediction results. Taking the actual wind power data of Xinjiang region as an example

a simulation analysis was conducted. The verification results show that the prediction accuracy of the method is high

and it can provide strong support for the planning and stable operation of the power system.

关键词

Keywords

references

魏泓屹, 卓振宇, 张宁, 等. 中国电力系统碳达峰碳中和转型路径优化与影响因素分析[J]. 电力系统自动化, 2022, 46(19):1-12.WEI Hongyi, ZHUO Zhenyu, ZHANG Ning, et al. Transition path optimization and influencing factor analysis of carbon emission peak and carbon neutrality for power system of China[J]. Automation of Electric Power Systems, 2022, 46(19):1-12.

滕伟, 许庆祥, 王亚军, 等. 平滑风电波动的飞轮协同电池混合储能系统经济性配置[J]. 动力工程学报, 2024, 44(7):1101-1108.TENG Wei, XU Qingxiang, WANG Yajun, et al. Economic configuration of flywheel collaborative battery hybrid energy storage system for smoothing wind power fluctuations[J]. Journal of Chinese Society of Power Engineering, 2024, 44(7):1101-1108.

武煜昊, 王永生, 徐昊, 等. 风电输出功率预测技术研究综述[J]. 计算机科学与探索, 2022, 16(12):2653-2677.WU Yuhao, WANG Yongsheng, XU Hao, et al. Survey of wind power output power forecasting technology[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(12):2653-2677.

黄飞. 基于风速变化特性的短期风电功率预测方法研究[D]. 南京:南京信息工程大学, 2019.

杨锡运, 孙翰墨. 基于时间序列模型的风电场风速预测研究[J]. 动力工程学报, 2011, 31(3):203-208.YANG Xiyun, SUN Hanmo. Wind speed prediction in wind farms based on time series model[J]. Journal of Chinese Society of Power Engineering, 2011, 31(3):203-208.

陈中慧, 王海云, 王维庆, 等. 基于数据挖掘与小波去噪的短期风电功率预测[J]. 计算机仿真, 2021, 38(9):90-94, 133.CHEN Zhonghui, WANG Haiyun, WANG Weiqing, et al. Short-term wind power prediction based on data mining and wavelet denoising[J]. Computer Simulation, 2021, 38(9):90-94, 133.

曹俊波, 周任军, 邓学华, 等. 考虑优化ARIMA模型差分次数的风功率预测[J]. 电力系统及其自动化学报, 2019, 31(1):105-111.CAO Junbo, ZHOU Renjun, DENG Xuehua,et al. Wind power forecast considering differential times of optimal ARIMA model[J]. Proceedings of the CSU-EPSA, 2019, 31(1):105-111.

付炳喆, 王玮, 任国瑞, 等. 考虑增强特征选择的深度卷积-时序网络短期风功率预测[J]. 动力工程学报, 2024, 44(10):1565-1573.FU Bingzhe, WANG Wei, REN Guorui,et al. Short-term wind power prediction with deep convolutional-temporal networks considering enhanced feature selection[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10):1565-1573.

刘忠, 周泽华, 邹淑云, 等. 基于迁移学习和CNN-LSTM的水轮机空化状态识别方法[J]. 动力工程学报, 2024, 44(10):1533-1540.LIU Zhong, ZHOU Zehua, ZOU Shuyun, et al. Cavitation state recognition method of hydraulic turbine based on transfer learning and CNN-LSTM[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10):1533-1540.

胡阳, 胡耀宗, 程逸, 等. 基于FD-AT-LSTM的大型风电机组变频器温度状态监测[J]. 动力工程学报, 2023, 43(9):1207-1215.HU Yang, HU Yaozong, CHENG Yi, et al. Temperature monitoring of heavy wind power unit inverters based on FD-AT-LSTM[J]. Journal of Chinese Society of Power Engineering, 2023, 43(9):1207-1215.

周建新, 王鸿滔. 基于相似日理论和改进PSO-LSTM模型的风电短期出力预测[J]. 中国工程机械学报, 2024, 22(4):447-451, 457.ZHOU Jianxin, WANG Hongtao. Short-term wind power prediction based on similar day theory and improved PSO-LSTM model[J]. Chinese Journal of Construction Machinery, 2024, 22(4):447-451, 457.

唐清苇, 向月, 代佳琨, 等. 基于CNN-LSTM的风电场发电功率迁移预测方法[J]. 工程科学与技术, 2024, 56(2):91-99.TANG Qingwei, XIANG Yue, DAI Jiakun, et al. Wind farm power transfer forecasting method based on CNN-LSTM[J]. Advanced Engineering Sciences, 2024, 56(2):91-99.

王渝红, 史云翔, 周旭, 等. 基于时间模式注意力机制的BiLSTM多风电机组超短期功率预测[J]. 高电压技术, 2022, 48(5):1884-1892.WANG Yuhong, SHI Yunxiang, ZHOU Xu, et al. Ultra-short-term power prediction for BiLSTM multi wind turbines based on temporal pattern attention[J]. High Voltage Engineering, 2022, 48(5):1884-1892.

吴向明, 宋楠, 李晓军, 等. 基于二次模态分解和卷积双向长短期记忆神经网络的高比例光伏配电网线损预测[J]. 电网技术, 2025, 49(9):3891-3899.WU Xiangming, SONG Nan, LI Xiaojun, et al. Line loss prediction of high proportion photovoltaic distribution network based on quadratic mode decomposition and CNN-BiLSTM neural network[J]. Power System Technology, 2025, 49(9):3891-3899.

徐睿麟, 郑建勇, 梅飞, 等. 基于谱聚类和多元变分模态分解的风电机组功率预测[J]. 电网技术, 2024, 48(5):2043-2053.XU Ruilin, ZHENG Jianyong, MEI Fei, et al. Power prediction of wind turbine units based on spectral clustering and multivariate variational mode decomposition[J]. Power System Technology, 2024, 48(5):2043-2053.

郭琦, 闫军, 郝乾鹏, 等. 基于闭环聚类和多目标优化的风电短期功率预测方法[J/OL]. 上海交通大学学报, 1-20(2024-07-03)[2024-10-19]. https://doi.org/10.16183/j.cnki.jsjtu.2024.079.GUO Qi, YAN Jun, HAO Qianpeng, et al. Short-term wind power prediction method based on closed-loop clustering and multi-objective optimization[J]. Journal of Shanghai Jiao Tong University, 1-20(2024-07-03)[2024-10-19]. https://doi.org/10.16183/j.cnki.jsjtu.2024.079.

高明裕, 蔡林辉, 孙长城, 等. 一种基于斯皮尔曼秩相关结合神经网络的电池组内部短路故障检测算法[J]. 电子与信息学报, 2022, 44(11):3734-3747.GAO Mingyu, CAI Linhui, SUN Changcheng, et al. An internal short circuit fault detecting of battery pack based on Spearman rank correlation combined with neural network[J]. Journal of Electronics & Information Technology, 2022, 44(11):3734-3747.

肖碧涛, 赖晓路, 郭鹏, 等. 高斯混合模型风电机组异常数据识别方法研究[J]. 可再生能源, 2023, 41(8):1051-1056.XIAO Bitao, LAI Xiaolu, GUO Peng, et al. Abnormal data identification for wind turbine based on Gaussian mixture model[J]. Renewable Energy Resources, 2023, 41(8):1051-1056.

苏丰睿, 穆伟伟, 赵宣茗, 等. 一种划分聚类k值与中心初始化的改进方法[J]. 计算机工程, 2023, 49(11):85-93.SU Fengrui, MU Weiwei, ZHAO Xuanming, et al. Improved method for partitioning clustering k-values and center initialization[J]. Computer Engineering, 2023, 49(11):85-93.

徐从云, 郑近德, 潘海洋, 等. 基于余弦相似熵的滚动轴承状态表征方法[J]. 噪声与振动控制, 2019, 39(5):167-172.XU Congyun, ZHENG Jinde, PAN Haiyang, et al. A state characterization method for rolling bearings based on cosine similarity entropy[J]. Noise and Vibration Control, 2019, 39(5):167-172.

张红颖, 贾一超, 汪江志, 等. 考虑注意力机制的CNN-LSTM高渗透风电并网暂态电压稳定性研究[J]. 可再生能源, 2024, 42(3):398-406.ZHANG Hongying, JIA Yichao, WANG Jiangzhi, et al. Study on high penetration wind power integration and transient voltage stability in power grid using CNN-LSTM with attention mechanism[J]. Renewable Energy Resources, 2024, 42(3):398-406.

吴家葆, 曾国辉, 张振华, 等. 基于K-means分层聚类的TCN-GRU和LSTM动态组合光伏短期功率预测[J]. 可再生能源, 2023, 41(8):1015-1022.WU Jiabao, ZENG Guohui, ZHANG Zhenhua, et al. Dynamic combination of TCN-GRU and LSTM photovoltaic short-term power prediction based on K-means hierarchical clustering[J]. Renewable Energy Resources, 2023, 41(8):1015-1022.

张越, 臧海祥, 韩海腾, 等. 基于FSN-MCCN-SA-BiLSTM的短期风速预测[J]. 太阳能学报, 2024, 45(8):529-536.ZHANG Yue, ZANG Haixiang, HAN Haiteng, et al. Short-term wind speed forecasting based on FSN-MCCN-SA-BiLSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(8):529-536.

刘玉娟, 刘颜达, 闫振, 等. 注意力机制的混合卷积高光谱图像分类方法[J]. 光谱学与光谱分析, 2024, 44(10):2916-2922.LIU Yujuan, LIU Yanda, YAN Zhen, et al. Classification of hybrid convolution hyperspectral images based on attention mechanism[J]. Spectroscopy and Spectral Analysis, 2024, 44(10):2916-2922.

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

基于CNN-BiLSTM-SSA的锅炉再热器壁温预测模型

融合时空特性的改进Informer风电功率短期预测

新型电力系统下熔盐储热技术的研究进展

基于改进LSTM与注意力机制的SCR入口NOx生成浓度预测

基于多尺度注意力域适应网络的跨域转子故障迁移诊断方法