基于物理信息的时间卷积神经网络风电功率预测  

Temporal Convolutional Neural Network for Wind Power Prediction Based on Physical Information

在线阅读下载全文

作  者:张维通 闫正兵[1] 张正江[1] 黄世沛 戴瑜兴[1] ZHANG Weitong;YAN Zhengbing;ZHANG Zhengjiang;HUANG Shipei;DAI Yuxing(National and Local Joint Engineering Research Center for Digital Electrical Design Technology,Wenzhou University,Wenzhou 325035,China)

机构地区:[1]温州大学电气数字化设计技术国家地方联合工程研究中心,浙江温州325035

出  处:《计算机测量与控制》2024年第11期101-108,117,共9页Computer Measurement &Control

基  金:温州市科研项目(ZF2022003);工业控制技术国家重点实验室开放课题(ICT2022B65);温州市高水平创新团队项目(温委人[2020]3号):电气数字化设计技术国家地方联合工程。

摘  要:由于风力的不确定性和随机性,风电功率预测对电力系统的稳定运行至关重要;为提高风电功率模型的预测精度;对风力发电机的数学模型进行研究后,将物理建模和数据驱动建模相结合,提出一种基于物理信息的时间卷积神经网络模型用于风力发电机的功率预测;采用将风力发电机的转子运动方程嵌入时间卷积神经网络的损失函数,从而提高模型的预测能力,泛化性和物理可解释性;并在Simulink仿真软件中搭建风力发电机物理模型以获取实验数据样本,经同工况实验和外推实验表明,基于物理信息的时间卷积神经网络模型相较于原时间卷积神经网络模型的同工况实验均方根误差下降50.8%,外推实验的均方根误差下降55.2%,显著提高了风力功率预测的准确性。Due to the uncertainty and randomness of wind power,it is very important to predict wind power in the stable operation of power system.To improve the prediction accuracy of wind power model;After studying the mathematical model of wind turbine,combining physical modeling and data-driven modeling,a temporal convolutional neural network model based on physical information is proposed to predict the power of wind turbine.The rotor motion equation of the wind turbine is embedded into the loss function of the temporal convolutional neural network,so as to improve the prediction ability,generalization and physical interpretability of the model.The physical model of the wind turbine is built in Simulink simulation software to obtain experimental data samples.Through experiments under the same working conditions and extrapolation experiments,the results show that compared with the original temporal convolutional neural network model,the temporal convolutional neural network model based on physical information reduces the root mean square error by 50.8%,and the root mean square error of the extrapolation experiment is reduced by 55.2%,significantly improving the accuracy of wind power prediction.

关 键 词:风力发电机 功率预测 物理信息 时间卷积神经网络 数据驱动建模 

分 类 号:TM614[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象