1×1卷积层对不同尺度的时空特征赋权、融合和降维。最后,将融合特征输入门控循环网络挖掘时序关联,输出多风电场风电功率的预测结果,以真实数据集验证了所提模型的有效性。;Mining the causal correlation between wind power and wind energy, as well as the spatio-temporal correlation among multiple wind farms from multi-source, multi-dimensional, and multi-modal wind power data, is an effective way to improve the accuracy of wind power prediction. A data-driven hybrid deep-learning model is proposed. First, in the data preprocessing stage, the scene of the wind farm operating at full power output and wind speed overflowing is regarded as the abnormal and fault state of wind power prediction, and the corresponding data-cleaning method is proposed to enhance the correlation between the wind speed and wind power. Then, aiming at the causal correlation between meteorological data and wind power, multi-channel convolution is designed to mine the coupling relationship; aiming at the spatio-temporal correlation between adjacent wind farms,the multi-scale convolution is designed to mine wind power characteristics with different spatio-temporal scales, and these spatio-temporal characteristics are weighted, fused, and reduced through the 1×1 convolution layer. Finally, the fusion characteristics are input into the gated recurrent network to mine the time correlation and output the prediction results of wind power for multiple wind farms. The effectiveness of the proposed model is verified by real datasets."/>

半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于数据驱动和深度学习的超短期风电功率预测
作者:
作者单位:

中国矿业大学电气与动力工程学院,江苏省徐州市 221116

摘要:

从多源、多维、多模态的风电数据中挖掘风能、风电的因果关联,以及多风电场间的时空关联,是提高风电功率预测精度的有效途径。文中提出了一种基于数据驱动的混合深度学习模型。首先,在数据预处理环节,将风电场满功率输出、风速溢出的场景,视为风电功率预测的异常、故障状态,并提出数据清洗方法以加强风速和风电的相关性。然后,针对气象信息与风电的因果关联,设计多通道卷积挖掘其耦合关系;针对相邻风电场间的时空关联,设计多尺度卷积挖掘不同时空尺度下的风电特征,并通过1×1卷积层对不同尺度的时空特征赋权、融合和降维。最后,将融合特征输入门控循环网络挖掘时序关联,输出多风电场风电功率的预测结果,以真实数据集验证了所提模型的有效性。

关键词:

基金项目:

国家自然科学基金资助项目(61703404)。

通信作者:

作者简介:

苗长新(1976—) ,男,通信作者,博士,副教授,主要研究方向:人工智能技术在电力系统中的应用、无功补偿与谐波治理、电能质量与控制。E-mail:miaochangxin@163.com
李昊(1994—) ,男,硕士研究生,主要研究方向:人工智能技术在电力系统中的应用、新能源发电。E-mail:297415047@qq.com
王霞(1994—) ,女,硕士研究生,主要研究方向:人工智能技术在电力系统中的应用、新能源发电。E-mail:1023326616@qq.com


Data-driven and Deep-learning-based Ultra-short-term Wind Power Prediction
Author:
Affiliation:

School of Electrical and Power Engineering, China University of Mining and Technology, Xuzhou 221116, China

Abstract:

Mining the causal correlation between wind power and wind energy, as well as the spatio-temporal correlation among multiple wind farms from multi-source, multi-dimensional, and multi-modal wind power data, is an effective way to improve the accuracy of wind power prediction. A data-driven hybrid deep-learning model is proposed. First, in the data preprocessing stage, the scene of the wind farm operating at full power output and wind speed overflowing is regarded as the abnormal and fault state of wind power prediction, and the corresponding data-cleaning method is proposed to enhance the correlation between the wind speed and wind power. Then, aiming at the causal correlation between meteorological data and wind power, multi-channel convolution is designed to mine the coupling relationship; aiming at the spatio-temporal correlation between adjacent wind farms,the multi-scale convolution is designed to mine wind power characteristics with different spatio-temporal scales, and these spatio-temporal characteristics are weighted, fused, and reduced through the 1×1 convolution layer. Finally, the fusion characteristics are input into the gated recurrent network to mine the time correlation and output the prediction results of wind power for multiple wind farms. The effectiveness of the proposed model is verified by real datasets.

Keywords:

Foundation:
This work is supported by National Natural Science Foundation of China (No. 61703404).
引用本文
[1]苗长新,李昊,王霞,等.基于数据驱动和深度学习的超短期风电功率预测[J].电力系统自动化,2021,45(14):22-29. DOI:10.7500/AEPS20201127004.
MIAO Changxin, LI Hao, WANG Xia, et al. Data-driven and Deep-learning-based Ultra-short-term Wind Power Prediction[J]. Automation of Electric Power Systems, 2021, 45(14):22-29. DOI:10.7500/AEPS20201127004.
复制
分享
历史
  • 收稿日期:2020-11-27
  • 最后修改日期:2021-04-12
  • 录用日期:
  • 在线发布日期: 2021-07-21
  • 出版日期:
相关附件