Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation

In traditional data-driven power system transient stability assessment methods, the impact of noise in the collected data and the information missing problems are rarely considered for the transient stability prediction. To deal with these problems, this paper presents a method for transient stabili...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanzhen ZHOU, Xianyu ZHA, Jian LAN, Qinglai GUO, Hongbin SUN, Feng XUE, Shengming WANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2020-01-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201912113
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053184683245568
author Yanzhen ZHOU
Xianyu ZHA
Jian LAN
Qinglai GUO
Hongbin SUN
Feng XUE
Shengming WANG
author_facet Yanzhen ZHOU
Xianyu ZHA
Jian LAN
Qinglai GUO
Hongbin SUN
Feng XUE
Shengming WANG
author_sort Yanzhen ZHOU
collection DOAJ
description In traditional data-driven power system transient stability assessment methods, the impact of noise in the collected data and the information missing problems are rarely considered for the transient stability prediction. To deal with these problems, this paper presents a method for transient stability prediction based on data augmentation and deep residual network (ResNet). Firstly, the original training data is extended with consideration of the noise data and data-missing conditions. Then, the real-time data of the disturbed generator is used as input features. Considering the similarity between high-dimensional time series data and images, the deep residual network, which is an improved algorithm based on convolutional neural networks, is used to build transient stability assessment model. The case studies show that the proposed method can improve the generalization ability of the model, and has better robustness in dealing with noise data or data missing problems.
format Article
id doaj-art-1b72d165913c4b1ebbb3a23f3afaeac1
institution DOAJ
issn 1004-9649
language zho
publishDate 2020-01-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-1b72d165913c4b1ebbb3a23f3afaeac12025-08-20T02:52:37ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492020-01-01531223110.11930/j.issn.1004-9649.201912113zgdl-53-1-zhouyanzhenTransient Stability Prediction of Power Systems Based on Deep Residual Network and Data AugmentationYanzhen ZHOU0Xianyu ZHA1Jian LAN2Qinglai GUO3Hongbin SUN4Feng XUE5Shengming WANG6Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing 211106, ChinaDepartment of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing 211106, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing 211106, ChinaIn traditional data-driven power system transient stability assessment methods, the impact of noise in the collected data and the information missing problems are rarely considered for the transient stability prediction. To deal with these problems, this paper presents a method for transient stability prediction based on data augmentation and deep residual network (ResNet). Firstly, the original training data is extended with consideration of the noise data and data-missing conditions. Then, the real-time data of the disturbed generator is used as input features. Considering the similarity between high-dimensional time series data and images, the deep residual network, which is an improved algorithm based on convolutional neural networks, is used to build transient stability assessment model. The case studies show that the proposed method can improve the generalization ability of the model, and has better robustness in dealing with noise data or data missing problems.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201912113transient stabilitydeep learningdeep residual networkdata augmentationpower systemnoiseinformation missing
spellingShingle Yanzhen ZHOU
Xianyu ZHA
Jian LAN
Qinglai GUO
Hongbin SUN
Feng XUE
Shengming WANG
Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
Zhongguo dianli
transient stability
deep learning
deep residual network
data augmentation
power system
noise
information missing
title Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
title_full Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
title_fullStr Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
title_full_unstemmed Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
title_short Transient Stability Prediction of Power Systems Based on Deep Residual Network and Data Augmentation
title_sort transient stability prediction of power systems based on deep residual network and data augmentation
topic transient stability
deep learning
deep residual network
data augmentation
power system
noise
information missing
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201912113
work_keys_str_mv AT yanzhenzhou transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT xianyuzha transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT jianlan transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT qinglaiguo transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT hongbinsun transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT fengxue transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation
AT shengmingwang transientstabilitypredictionofpowersystemsbasedondeepresidualnetworkanddataaugmentation