A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network

Accurate topological connectivity is critical for the safe operation and management of low-voltage distribution grids (LVDGs). However, due to the complexity of the structure and the lack of measurement equipment, obtaining and maintaining these topological connections has become a challenge. This p...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Lei, Fan Yang, Yanjun Feng, Wei Hu, Yinzhang Cheng
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/11/2821
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850130797450756096
author Yang Lei
Fan Yang
Yanjun Feng
Wei Hu
Yinzhang Cheng
author_facet Yang Lei
Fan Yang
Yanjun Feng
Wei Hu
Yinzhang Cheng
author_sort Yang Lei
collection DOAJ
description Accurate topological connectivity is critical for the safe operation and management of low-voltage distribution grids (LVDGs). However, due to the complexity of the structure and the lack of measurement equipment, obtaining and maintaining these topological connections has become a challenge. This paper proposes a topology identification strategy for LVDGs based on a feature-enhanced graph attention network (F-GAT). First, the topology of the LVDG is represented as a graph structure using measurement data collected from intelligent terminals, with a feature matrix encoding the basic information of each entity. Secondly, the meta-path form of the heterogeneous graph is designed according to the connection characteristics of the LVDG, and the walking sequence is enhanced using a heterogeneous skip-gram model to obtain an embedded representation of the structural characteristics of each node. Then, the F-GAT model is used to learn potential association patterns and structural information in the graph topology, achieving a joint low-dimensional representation of electrical attributes and graph semantics. Finally, case studies on five urban LVDGs in the Wuhan region are conducted to validate the effectiveness and practicality of the proposed F-GAT model.
format Article
id doaj-art-e70d07f845f946aa989d101fb85fec0b
institution OA Journals
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-e70d07f845f946aa989d101fb85fec0b2025-08-20T02:32:37ZengMDPI AGEnergies1996-10732025-05-011811282110.3390/en18112821A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention NetworkYang Lei0Fan Yang1Yanjun Feng2Wei Hu3Yinzhang Cheng4Power Science Research Institute of State Grid Hubei Electric Power Co., Wuhan 430048, ChinaPower Science Research Institute of State Grid Hubei Electric Power Co., Wuhan 430048, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 211102, ChinaPower Science Research Institute of State Grid Hubei Electric Power Co., Wuhan 430048, ChinaPower Science Research Institute of State Grid Shanxi Electric Power Co., Taiyuan 030021, ChinaAccurate topological connectivity is critical for the safe operation and management of low-voltage distribution grids (LVDGs). However, due to the complexity of the structure and the lack of measurement equipment, obtaining and maintaining these topological connections has become a challenge. This paper proposes a topology identification strategy for LVDGs based on a feature-enhanced graph attention network (F-GAT). First, the topology of the LVDG is represented as a graph structure using measurement data collected from intelligent terminals, with a feature matrix encoding the basic information of each entity. Secondly, the meta-path form of the heterogeneous graph is designed according to the connection characteristics of the LVDG, and the walking sequence is enhanced using a heterogeneous skip-gram model to obtain an embedded representation of the structural characteristics of each node. Then, the F-GAT model is used to learn potential association patterns and structural information in the graph topology, achieving a joint low-dimensional representation of electrical attributes and graph semantics. Finally, case studies on five urban LVDGs in the Wuhan region are conducted to validate the effectiveness and practicality of the proposed F-GAT model.https://www.mdpi.com/1996-1073/18/11/2821low-voltage distribution gridtopology identificationfeature-enhanced graph attention networkmeta-path formheterogeneous skip-gram
spellingShingle Yang Lei
Fan Yang
Yanjun Feng
Wei Hu
Yinzhang Cheng
A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
Energies
low-voltage distribution grid
topology identification
feature-enhanced graph attention network
meta-path form
heterogeneous skip-gram
title A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
title_full A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
title_fullStr A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
title_full_unstemmed A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
title_short A Topology Identification Strategy of Low-Voltage Distribution Grids Based on Feature-Enhanced Graph Attention Network
title_sort topology identification strategy of low voltage distribution grids based on feature enhanced graph attention network
topic low-voltage distribution grid
topology identification
feature-enhanced graph attention network
meta-path form
heterogeneous skip-gram
url https://www.mdpi.com/1996-1073/18/11/2821
work_keys_str_mv AT yanglei atopologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT fanyang atopologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT yanjunfeng atopologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT weihu atopologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT yinzhangcheng atopologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT yanglei topologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT fanyang topologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT yanjunfeng topologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT weihu topologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork
AT yinzhangcheng topologyidentificationstrategyoflowvoltagedistributiongridsbasedonfeatureenhancedgraphattentionnetwork