基于时空混合注意力机制的超短时风电功率预测方法

黄贤明; 郝雨辰; 霍雪松; 柴赟; 彭程

doi:10.19725/j.cnki.1007-2322.2023.0246

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于时空混合注意力机制的超短时风电功率预测方法

新能源电力系统 | 更新时间：2025-10-22

- 基于时空混合注意力机制的超短时风电功率预测方法
- An Ultra-short Term Wind Power Prediction Method Based on Spatio-temporal Hybrid Attention Mechanism
- 现代电力 2025年42卷第5期页码：928-936
- 作者机构：
  
  1. 常熟理工学院电气与自动化工程学院,江苏省,苏州市,215500
  2. 国网江苏省电力有限公司,江苏省,南京市,210017
  3. 电子科技大学中山学院计算机学院,广东省,中山市,528400
- 作者简介：
  
  [ "黄贤明(1972)，男，博士，高级工程师，研究方向为新能源发电与控制技术，E-mail：2668440765@qq.com" ]
  [ "郝雨辰(1985)，男，博士，高级工程师，研究方向为新能源并网调度运行与管理，E-mail：hao_yuchen@126.com" ]
  [ "霍雪松(1974)，男，硕士，高级工程师，研究方向为新能源并网调度运行与管理， E-mail：huoxuesong@jsepc.com.cn" ]
  [ "柴赟(1992)，男，硕士，工程师，研究方向为新能源及分布式电源运行分析， E-mail：chaiyun17@163.com" ]
  [ "彭程(1990)，男，博士，讲师，研究方向为人工智能，E-mail：hyfen2009@126.com" ]
- 基金信息：
  
  国网江苏省电力有限公司科技项目(J2021065)。
- DOI：10.19725/j.cnki.1007-2322.2023.0246
  中图分类号： 5
- 纸质出版：2025
- 稿件说明：
移动端阅览
黄贤明, 郝雨辰, 霍雪松, 等. 基于时空混合注意力机制的超短时风电功率预测方法[J]. 现代电力, 2025,42(5):928-936.

HUANG Xianming, HAO Yuchen, HUO Xuesong, et al. An Ultra-short Term Wind Power Prediction Method Based on Spatio-temporal Hybrid Attention Mechanism[J]. 2025, 42(5): 928-936.
黄贤明, 郝雨辰, 霍雪松, 等. 基于时空混合注意力机制的超短时风电功率预测方法[J]. 现代电力, 2025,42(5):928-936. DOI： 10.19725/j.cnki.1007-2322.2023.0246.

HUANG Xianming, HAO Yuchen, HUO Xuesong, et al. An Ultra-short Term Wind Power Prediction Method Based on Spatio-temporal Hybrid Attention Mechanism[J]. 2025, 42(5): 928-936. DOI： 10.19725/j.cnki.1007-2322.2023.0246.

摘要

针对风电功率预测精度差以及一些风电场没有气象传感器的问题，提出不依赖气象数据的风力发电预测模型算法。首先，使用基于滑动窗口的方法对数据进行切分，构造时序数据。然后，通过采用一维卷积网络和长短期记忆网络(long short-term memory neural network

LSTM)对具有长期依赖性的时间序列数据进行空间和时间维度上的特征提取。之后，采用时空混合注意力机制对特征进行融合，并进行功率预测。通过对华东某风电场的3年数据进行算例分析，结果表明上述预测模型比卷积神经网络-长短期记忆网络(convolutional neural network-long short-term memory，CNN-LSTM)模型、CNN模型和LSTM模型更加准确，证明了所提预测方法的有效性和实用性。该研究为在实际场景中对功率预测的可靠性分析，提供了有力的支持。

Abstract

In response to the challenges posed by poor forecasting accuracy of wind power and inadequate meteorological sensors in certain wind farms

a wind power prediction model algorithm independent of meteorological data is proposed. Firstly

the sliding window based method is utilized to split the data and construct the time sequence data. The one-dimensional convolution network and long short-term memory network (LSTM) are subsequently employed to extract spatial and time dimension features from time series data with long term dependence. Finally

a spatio-temporal hybrid attention mechanism is employed to fuse features and predict power. Through the case analysis of three-year data from a wind farm in eastern China

the practicability of the above prediction model is proved and the results are more accurate than those of convolutional neural network-long short-term memory (CNN-LSTM) model

CNN model and LSTM model. Both validity and practicability of the proposed prediction method are proved

providing substantial support for reliability analysis of power prediction in actual scenarios.

关键词

Keywords

references

MA Weizhe, CHENG Renli , SHI Jun, et al. Affine arithmetic-based interval power flow calculation considering wind farm model[J]. Guangdong Electric Power, 2019, 32(11): 28−37(in Chinese).

马伟哲, 程韧俐, 史军, 等. 考虑风电场模型的仿射区间潮流计算[J]. 广东电力, 2019, 32(11): 28−37.

HAN Zifen, JING Qianming, ZHANG Yankai, et al. Review of wind power forecasting methods and new trends[J]. Power System Protection and Control, 2019, 47(24): 178-187(in Chinese).

韩自奋, 景乾明, 张彦凯, 等. 风电预测方法与新趋势综述[J]. 电力系统保护与控制, 2019, 47 (24): 178-187.

TAN Minge, JIANG Bo, WANG Jianyuan, et al. Research on short-term wind power prediction method based on deep learning model with bidirectional long short-term memory[J]. Power System and Clean Energy, 2020, 36(6): 85−91(in Chinese).

谭敏戈, 蒋勃, 王建渊, 等. 基于双向长短期记忆深度学习模型的短期风功率预测方法研究[J]. 电网与清洁能源, 2020, 36(6): 85−91.

YANG Zimin, PENG Xiaosheng, LANG Jianxun, et al. Short-term wind power prediction based on dynamic cluster division and BLSTM deep learning method[J]. High Voltage Engineering, 2021, 47(4): 1195−1203(in Chinese).

杨子民, 彭小圣, 郎建勋, 等. 基于集群动态划分与BLSTM 深度学习的风电集群短期功率预测[J]. 高电压技术, 2021, 47(4): 1195−1203.

QIAN Zheng, PEI Yan, CAO Lixiao, et al. Review of wind power forecasting method[J]. High Voltage Engineering, 2016, 42(4): 1047−1060(in Chinese).

钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047−1060.

XU Yannong, WANG Yifan, WANG Haochun, et al. Wind power prediction method based on primary/secondary exponential smoothing method[J]. South Agricultural Machinery, 2021, 52(21): 26−28(in Chinese).

徐彦农, 王一帆, 王浩淳, 等. 基于一次 / 二次指数平滑法的风功率预测方法[J]. 南方农机, 2021, 52(21): 26−28.

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(09): 90−94,133(in Chinese).

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(09): 90−94,133.

WANG Chunmei. Research on wind power forecasting method based on combined model[J]. Journal of State Grid Technology College, 2021, 24(5): 23−26(in Chinese).

王春梅. 基于组合模型的风电功率预测方法研究[J]. 山东电力高等专科学校学报, 2021, 24(5): 23−26.

DENG Yaping, DUAN Jiandong, JIA Hao, et al. Ultra-short-term wind power prediction based on deep learning with independent recurrent neural network via cuckoo algorithm optimized[J]. Power System and Clean Energy, 2021, 37(09): 18−26(in Chinese).

邓亚平, 段建东, 贾颢, 等. 基于布谷鸟算法优化独立循环神经网络深度学习的超短期风电功率预测[J]. 电网与清洁能源, 2021, 37(09): 18−26.

ZHANG Tao, SUN Xiaowei, SHI Suyi, et al. Ultra-short-term wind power forecasting based on QPSO-LSSVM[J]. Electric Power, 2016, 49(3): 183−187(in Chinese).

张涛, 孙晓伟, 史苏怡, 等. 基于QPSO-LSSVM的风电场超短期功率预测[J]. 中国电力, 2016, 49(3): 183−187.

WANG Yimei, LIU Hui, SONG Peng, et al. Short-term power forecasof wind farm based on gaussian mixture model clustering[J]. Automation of Electric Power Systems, 2021, 45(7): 37−43(in Chinese).

王一妹, 刘辉, 宋鹏, 等. 基于高斯混合模型聚类的风电场短期功率预测方法[J]. 电力系统自动化, 2021, 45(7): 37−43.

HU Tianyu, WU Wenchuan, GUO Qinglai, et al. Very short-term spatial and temporal wind power forecasting: A deep learning approach[J]. CSEE Journal of Power and Energy Systems, 2020, 6(2): 434−443.

ZHOU Niancheng, LIAO Jianquan, WANG Qianggang, et al. Analysis and prospect of deep learning application in smart grid[J]. Automation of Electric Power Systems, 2019, 43(4): 180−191(in Chinese).

周念成, 廖建权, 王强钢, 等. 深度学习在智能电网中的应用现状分析与展望[J]. 电力系统自动化, 2019, 43(4): 180−191.

ZHU Qiaomu, LI Hongyi, WANG Ziqi, et al. Short-term wind power forecasting based on LSTM[J]. Power System Technology, 2017, 41(12): 3797−3802(in Chinese).

朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797−3802.

WANG Yalan, TIAN Ye, YANG Lihua. Ultra-short-term wind farm power prediction method based on DA-CNNGRU hybrid neural network[J]. Hubei Electric Power, 2021, 45(3): 23−28(in Chinese).

王雅兰, 田野, 杨丽华. 基于DA-CNNGRU混合神经网络的超短期风电场功率预测方法[J]. 湖北电力, 2021, 45(3): 23−28.

LI Dan, WANG Qi, YANG Baohua, et al. Ultra-short-term power prediction of multiple wind farms based on independent sparse SAE[J]. Proceedings of the CSU-EPSA, 2022, 34(2): 23−30(in Chinese).

李丹, 王奇, 杨保华, 等. 基于独立稀疏SAE的多风电场超短期功率预测[J]. 电力系统及其自动化学报, 2022, 34(2): 23−30.

YAO Yue, LIU Da. Short-term wind power forecasting based on attention mechanism of CNN-LSTM[J]. Modern Electric Power, 2022, 39(2): 212−218(in Chinese).

姚越, 刘达. 基于注意力机制的卷积神经网络-长短期记忆网络的短期风电功率预测[J]. 现代电力, 2022, 39(2): 212−218.

ZHANG Huan, ZHANG Qing, YU Jiyan. Overview of the development of activation function and its nature analysis[J]. Journal of Xihua University (Natural Science Edition), 2021, 40(4): 1−10(in Chinese).

张焕, 张庆, 于纪言. 激活函数的发展综述及其性质分析[J]. 西华大学学报(自然科学版), 2021, 40(4): 1−10.

YANG Li, WU Yuxi, WANG Junli, et al. Research on recurrent neural network[J]. Journal of Computer Applications, 2018, 38(S2): 1−6, 26(in Chinese).

杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38(S2): 1−6, 26.

LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43(08): 131−137(in Chinese).

陆继翔, 张琪培, 杨志宏, 等. 基于 CNN-LSTM 混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(08): 131−137.

LIU Fang, WANG Zhen, LIU Ruidi, et al. Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of Zhejiang University (Engineering Edition), 2021, 55(03): 594−600(in Chinese).

刘芳, 汪震, 刘睿迪, 等. 基于组合损失函数的 BP 神经网络风力发电短期预测方法[J]. 浙江大学学报(工学版), 2021, 55(03): 594−600.

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

基于随差遗忘长短期记忆的风电功率实时预测

基于自组织映射−前馈神经网络和先知混合模型的短期负荷预测

基于密度聚类模态分解的卷积神经网络和长短期记忆网络短期风电功率预测

基于变分模态分解的卷积长短时记忆网络短期电力负荷预测方法

基于长短期记忆网络数字孪生体的短期光伏发电预测