基于数字孪生及神经网络的电压扰动定位方法  

Voltage Disturbance Localization Method Based on Digital Twin and Neural Network

作　　者：冯志远 李琼林 蒋建东[1] 郑晨 赵鹏祥 FENG Zhiyuan;LI Qionglin;JIANG Jiandong;ZHENG Chen;ZHAO Pengxiang(School of Electrical Engineering,Zhengzhou University,Zhengzhou 450001,Henan Province,China;Electric Power Research Institute of State Grid Henan Electric Power Company,Zhengzhou 450052,Henan Province,China)

机构地区：[1]郑州大学电气工程学院,河南省郑州市450001 [2]国网河南省电力公司电力科学研究院,河南省郑州市450052

出　　处：《全球能源互联网》2023年第3期275-281,共7页Journal of Global Energy Interconnection

基　　金：国家电网有限公司科技项目(5400-202124153A-0-0-00)。

摘　　要：提出一种基于数字孪生及神经网络的电压扰动定位方法。首先根据配电网中大量的监测点信息以及网架结构参数构建配电网数字镜像模型,然后采用人工神经网络对数字镜像模型的历史数据进行学习训练,得到反映节点电压与暂降发生位置之间映射关系的神经网络模型。该模型可以根据暂降后各节点的电压数据得到反映各节点故障特征的信息,进而实现对暂降源的定位。以河南某县30节点的配电网为例,对所提方法的有效性进行验证,结果表明该方法能够实现对电压暂降源的准确定位。A voltage disturbance localization method based on digital twin and neural network is proposed.Firstly,a digital mirror model of the distribution network is constructed according to a large number of monitoring point information in the distribution network and the structural parameters of the distributed grid.Then an artificial neural network is used to analyze the digital mirror model.The historical data is used for learning and training to obtain the neural network model that reflects the mapping relationship between the node voltage and the sag occurrence position.Through this model,the information reflecting the fault characteristics of each node can be obtained according to the voltage data of each node after the sag,and then the location of the sag source can be realized.The effectiveness of the proposed method is verified by taking a 30-node distribution network in a county of Henan Province as an example.The results show that the method can accurately locate the voltage sag source.

关 键 词：电压暂降 数字孪生 神经网络 定位 

分 类 号：TM769[电气工程—电力系统及自动化]