An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning

As a measure for internal overvoltage identification of distribution network, the data driving method is limited in practical applications due to the small number of overvoltage samples. A transfer-learning-based deep convolutional neural network (D-CNN) algorithm is thus proposed to identify the in...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao XU, Liqiang LIU, Chao LV
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2021-08-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202006274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030066080153600
author Hao XU
Liqiang LIU
Chao LV
author_facet Hao XU
Liqiang LIU
Chao LV
author_sort Hao XU
collection DOAJ
description As a measure for internal overvoltage identification of distribution network, the data driving method is limited in practical applications due to the small number of overvoltage samples. A transfer-learning-based deep convolutional neural network (D-CNN) algorithm is thus proposed to identify the internal overvoltage of distribution network. Firstly, 6 types of two-dimension time-frequency maps of 10 kV distribution network internal overvoltage are constructed by simulation and continuous wavelet transform (CWT). Then, the transfer-learning-based D-CNN network models are built using four network models, including Alexnet, Vgg-16, Googlenet and Resnet50. Finally, the two-dimension time-frequency maps are introduced into the transformed D-CNN for training. By comparing and analyzing the experimental results, it is found that the newly constructed VGG-16 network model has the highest identification accuracy, reaching 99.07%, which realizes the accurate classification of overvoltage faults in the case of scarce data.
format Article
id doaj-art-e28df35effb2493bbd5a4ced8d3e38c2
institution DOAJ
issn 1004-9649
language zho
publishDate 2021-08-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-e28df35effb2493bbd5a4ced8d3e38c22025-08-20T02:59:19ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492021-08-01548525910.11930/j.issn.1004-9649.202006274zgdl-54-8-xuhaoAn Internal Overvoltage Identification Method for Distribution Network Based on Transfer LearningHao XU0Liqiang LIU1Chao LV2College of Electric Power, Inner Mongolia University of Technology, Hohhot 010080, ChinaCollege of Electric Power, Inner Mongolia University of Technology, Hohhot 010080, ChinaInner Mongolia Electric Power Research Institute, Hohhot 010020, ChinaAs a measure for internal overvoltage identification of distribution network, the data driving method is limited in practical applications due to the small number of overvoltage samples. A transfer-learning-based deep convolutional neural network (D-CNN) algorithm is thus proposed to identify the internal overvoltage of distribution network. Firstly, 6 types of two-dimension time-frequency maps of 10 kV distribution network internal overvoltage are constructed by simulation and continuous wavelet transform (CWT). Then, the transfer-learning-based D-CNN network models are built using four network models, including Alexnet, Vgg-16, Googlenet and Resnet50. Finally, the two-dimension time-frequency maps are introduced into the transformed D-CNN for training. By comparing and analyzing the experimental results, it is found that the newly constructed VGG-16 network model has the highest identification accuracy, reaching 99.07%, which realizes the accurate classification of overvoltage faults in the case of scarce data.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202006274internal overvoltage of distribution networkcontinuous wavelet transformtransfer learningdeep convolutional neural networkpattern recognition
spellingShingle Hao XU
Liqiang LIU
Chao LV
An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
Zhongguo dianli
internal overvoltage of distribution network
continuous wavelet transform
transfer learning
deep convolutional neural network
pattern recognition
title An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
title_full An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
title_fullStr An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
title_full_unstemmed An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
title_short An Internal Overvoltage Identification Method for Distribution Network Based on Transfer Learning
title_sort internal overvoltage identification method for distribution network based on transfer learning
topic internal overvoltage of distribution network
continuous wavelet transform
transfer learning
deep convolutional neural network
pattern recognition
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202006274
work_keys_str_mv AT haoxu aninternalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning
AT liqiangliu aninternalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning
AT chaolv aninternalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning
AT haoxu internalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning
AT liqiangliu internalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning
AT chaolv internalovervoltageidentificationmethodfordistributionnetworkbasedontransferlearning