Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network

In response to the demand for identification of distribution network topology with a high percentage of renewable energy penetration, a distribution network topology analysis method based on decision trees and deep learning methods is proposed. First, the decision tree model is constructed to analyz...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Juhua Hong, Linyao Zhang, Yufei Yan, Zeqi Wang, Pengzhe Ren
Formato: article
Lenguaje:EN
Publicado: Hindawi Limited 2021
Materias:
Acceso en línea:https://doaj.org/article/65642770684b4d58accd371e5770ae6b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:65642770684b4d58accd371e5770ae6b
record_format dspace
spelling oai:doaj.org-article:65642770684b4d58accd371e5770ae6b2021-11-29T00:56:27ZDeep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network1563-514710.1155/2021/8942733https://doaj.org/article/65642770684b4d58accd371e5770ae6b2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/8942733https://doaj.org/toc/1563-5147In response to the demand for identification of distribution network topology with a high percentage of renewable energy penetration, a distribution network topology analysis method based on decision trees and deep learning methods is proposed. First, the decision tree model is constructed to analyze the importance of each node’s characteristics to the observability of the distribution network topology. Next, we arrange the node feature importance from large to small and select the node measurement data with high importance as the training sample set. Then, the principal component analysis (PCA)-deep belief network (DBN) model is used to analyze the changes in the observability of the distribution network topology, and the nodes are selected as the optimal location for the measurement device when the distribution network is completely observable. Finally, the IEEE-33 bus system with a high proportion of renewable energy is used to verify that the method proposed has a good effect in the identification of the distribution network topology.Juhua HongLinyao ZhangYufei YanZeqi WangPengzhe RenHindawi LimitedarticleEngineering (General). Civil engineering (General)TA1-2040MathematicsQA1-939ENMathematical Problems in Engineering, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Engineering (General). Civil engineering (General)
TA1-2040
Mathematics
QA1-939
spellingShingle Engineering (General). Civil engineering (General)
TA1-2040
Mathematics
QA1-939
Juhua Hong
Linyao Zhang
Yufei Yan
Zeqi Wang
Pengzhe Ren
Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
description In response to the demand for identification of distribution network topology with a high percentage of renewable energy penetration, a distribution network topology analysis method based on decision trees and deep learning methods is proposed. First, the decision tree model is constructed to analyze the importance of each node’s characteristics to the observability of the distribution network topology. Next, we arrange the node feature importance from large to small and select the node measurement data with high importance as the training sample set. Then, the principal component analysis (PCA)-deep belief network (DBN) model is used to analyze the changes in the observability of the distribution network topology, and the nodes are selected as the optimal location for the measurement device when the distribution network is completely observable. Finally, the IEEE-33 bus system with a high proportion of renewable energy is used to verify that the method proposed has a good effect in the identification of the distribution network topology.
format article
author Juhua Hong
Linyao Zhang
Yufei Yan
Zeqi Wang
Pengzhe Ren
author_facet Juhua Hong
Linyao Zhang
Yufei Yan
Zeqi Wang
Pengzhe Ren
author_sort Juhua Hong
title Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
title_short Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
title_full Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
title_fullStr Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
title_full_unstemmed Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
title_sort deep-learning-assisted topology identification and sensor placement for active distribution network
publisher Hindawi Limited
publishDate 2021
url https://doaj.org/article/65642770684b4d58accd371e5770ae6b
work_keys_str_mv AT juhuahong deeplearningassistedtopologyidentificationandsensorplacementforactivedistributionnetwork
AT linyaozhang deeplearningassistedtopologyidentificationandsensorplacementforactivedistributionnetwork
AT yufeiyan deeplearningassistedtopologyidentificationandsensorplacementforactivedistributionnetwork
AT zeqiwang deeplearningassistedtopologyidentificationandsensorplacementforactivedistributionnetwork
AT pengzheren deeplearningassistedtopologyidentificationandsensorplacementforactivedistributionnetwork
_version_ 1718407711420317696