A hierarchical power system transient stability assessment method considering sample imbalance

In order to make full use of the dynamic information contained in the electrical quantity response trajectories, improve the reliability of critical sample prediction results, and correct the bias problem caused by sample imbalance to model prediction, a transient stability assessment (TSA) method b...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yixing Du, Zhijian Hu, Fangzhou Wang
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Transient stability assessment Deep learning Power systems BiLSTM Sample imbalance Loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/63259d483d404d459121ae4f1651c634
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:63259d483d404d459121ae4f1651c634
record_format	dspace
spelling	oai:doaj.org-article:63259d483d404d459121ae4f1651c6342021-11-26T04:33:29ZA hierarchical power system transient stability assessment method considering sample imbalance2352-484710.1016/j.egyr.2021.08.052https://doaj.org/article/63259d483d404d459121ae4f1651c6342021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721006533https://doaj.org/toc/2352-4847In order to make full use of the dynamic information contained in the electrical quantity response trajectories, improve the reliability of critical sample prediction results, and correct the bias problem caused by sample imbalance to model prediction, a transient stability assessment (TSA) method based on bidirectional long short-term memory (BiLSTM) network is proposed. The method takes the dynamic trajectories of the underlying measurement data as the inputs, abstracts the features step by step from the multivariate time series through the multilayered neural network, and then establishes the nonlinear mapping relationship between the input feature and the stability category. In this paper, BiLSTM is improved by introducing truncation threshold and penalty coefficient into the loss function to give higher weights to hard samples and unstable samples, thus optimizing the gradient descent direction. Furthermore, this method enables sustainable hierarchical prediction and effectively reduces uncertain samples. The experimental results on the New England 39-bus system integrated with wind farm show that the proposed method significantly reduces the missing alarm rate of unstable samples and the false alarm rate of stable samples, and improves the credibility of the prediction results of critical samples.Yixing DuZhijian HuFangzhou WangElsevierarticleTransient stability assessmentDeep learningPower systemsBiLSTMSample imbalanceLoss functionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 7, Iss , Pp 224-232 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Transient stability assessment Deep learning Power systems BiLSTM Sample imbalance Loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Transient stability assessment Deep learning Power systems BiLSTM Sample imbalance Loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yixing Du Zhijian Hu Fangzhou Wang A hierarchical power system transient stability assessment method considering sample imbalance
description	In order to make full use of the dynamic information contained in the electrical quantity response trajectories, improve the reliability of critical sample prediction results, and correct the bias problem caused by sample imbalance to model prediction, a transient stability assessment (TSA) method based on bidirectional long short-term memory (BiLSTM) network is proposed. The method takes the dynamic trajectories of the underlying measurement data as the inputs, abstracts the features step by step from the multivariate time series through the multilayered neural network, and then establishes the nonlinear mapping relationship between the input feature and the stability category. In this paper, BiLSTM is improved by introducing truncation threshold and penalty coefficient into the loss function to give higher weights to hard samples and unstable samples, thus optimizing the gradient descent direction. Furthermore, this method enables sustainable hierarchical prediction and effectively reduces uncertain samples. The experimental results on the New England 39-bus system integrated with wind farm show that the proposed method significantly reduces the missing alarm rate of unstable samples and the false alarm rate of stable samples, and improves the credibility of the prediction results of critical samples.
format	article
author	Yixing Du Zhijian Hu Fangzhou Wang
author_facet	Yixing Du Zhijian Hu Fangzhou Wang
author_sort	Yixing Du
title	A hierarchical power system transient stability assessment method considering sample imbalance
title_short	A hierarchical power system transient stability assessment method considering sample imbalance
title_full	A hierarchical power system transient stability assessment method considering sample imbalance
title_fullStr	A hierarchical power system transient stability assessment method considering sample imbalance
title_full_unstemmed	A hierarchical power system transient stability assessment method considering sample imbalance
title_sort	hierarchical power system transient stability assessment method considering sample imbalance
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/63259d483d404d459121ae4f1651c634
work_keys_str_mv	AT yixingdu ahierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance AT zhijianhu ahierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance AT fangzhouwang ahierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance AT yixingdu hierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance AT zhijianhu hierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance AT fangzhouwang hierarchicalpowersystemtransientstabilityassessmentmethodconsideringsampleimbalance
_version_	1718409843992166400

A hierarchical power system transient stability assessment method considering sample imbalance

Ejemplares similares