A simple gated recurrent network for detection of power quality disturbances

Abstract This paper presents a new concise deep learning–based sequence model to detect the power quality disturbances (PQD), which only uses original signals and does not require pre‐processing and complex artificial feature extraction process. A simple gated recurrent network (SGRN) with a new rec...

Full description

Bibliographic Details
Main Authors: Xiangrong Zu, Kai Wei
Format: Article
Language:English
Published: Wiley 2021-02-01
Series:IET Generation, Transmission & Distribution
Online Access:https://doi.org/10.1049/gtd2.12056
id doaj-ac7bcc8fdbdf48dab6c72ba5a3be7200
record_format Article
spelling doaj-ac7bcc8fdbdf48dab6c72ba5a3be72002021-07-14T13:26:00ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952021-02-0115475176110.1049/gtd2.12056A simple gated recurrent network for detection of power quality disturbancesXiangrong Zu0Kai Wei1School of Control and Computer Engineering North China Electric Power University Beijing ChinaSchool of Control and Computer Engineering North China Electric Power University Beijing ChinaAbstract This paper presents a new concise deep learning–based sequence model to detect the power quality disturbances (PQD), which only uses original signals and does not require pre‐processing and complex artificial feature extraction process. A simple gated recurrent network (SGRN) with a new recurrent cell structure is developed, which consists of only two gates: forget gate and input gate, and two weight matrices. Compared with the standard Recurrent Neural Network (RNN) model, the training process of the proposed method is more stable and the prediction accuracy is higher. In addition, this special structure retains basic non‐linearity and long‐term memory, while enabling the simple gated recurrent network model to be superior to Long Short‐Term Memory (LSTM) Network and Gated Recurrent Unit (GRU) Network in terms of the number of parameters (i.e. memory cost) and detection speed. In the light of the experimental results, the simple gated recurrent network algorithm can achieve 99.07% detection accuracy, and contains only 18,959 parameters, which indicates that our proposed method is easier to deploy in resource‐constrained internet of things (IoT) micro‐controllers.https://doi.org/10.1049/gtd2.12056
collection DOAJ
language English
format Article
sources DOAJ
author Xiangrong Zu
Kai Wei
spellingShingle Xiangrong Zu
Kai Wei
A simple gated recurrent network for detection of power quality disturbances
IET Generation, Transmission & Distribution
author_facet Xiangrong Zu
Kai Wei
author_sort Xiangrong Zu
title A simple gated recurrent network for detection of power quality disturbances
title_short A simple gated recurrent network for detection of power quality disturbances
title_full A simple gated recurrent network for detection of power quality disturbances
title_fullStr A simple gated recurrent network for detection of power quality disturbances
title_full_unstemmed A simple gated recurrent network for detection of power quality disturbances
title_sort simple gated recurrent network for detection of power quality disturbances
publisher Wiley
series IET Generation, Transmission & Distribution
issn 1751-8687
1751-8695
publishDate 2021-02-01
description Abstract This paper presents a new concise deep learning–based sequence model to detect the power quality disturbances (PQD), which only uses original signals and does not require pre‐processing and complex artificial feature extraction process. A simple gated recurrent network (SGRN) with a new recurrent cell structure is developed, which consists of only two gates: forget gate and input gate, and two weight matrices. Compared with the standard Recurrent Neural Network (RNN) model, the training process of the proposed method is more stable and the prediction accuracy is higher. In addition, this special structure retains basic non‐linearity and long‐term memory, while enabling the simple gated recurrent network model to be superior to Long Short‐Term Memory (LSTM) Network and Gated Recurrent Unit (GRU) Network in terms of the number of parameters (i.e. memory cost) and detection speed. In the light of the experimental results, the simple gated recurrent network algorithm can achieve 99.07% detection accuracy, and contains only 18,959 parameters, which indicates that our proposed method is easier to deploy in resource‐constrained internet of things (IoT) micro‐controllers.
url https://doi.org/10.1049/gtd2.12056
work_keys_str_mv AT xiangrongzu asimplegatedrecurrentnetworkfordetectionofpowerqualitydisturbances
AT kaiwei asimplegatedrecurrentnetworkfordetectionofpowerqualitydisturbances
AT xiangrongzu simplegatedrecurrentnetworkfordetectionofpowerqualitydisturbances
AT kaiwei simplegatedrecurrentnetworkfordetectionofpowerqualitydisturbances
_version_ 1721302735044739072