Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network
With the rapid development of power grid infrastructure, especially the increasing number of ultra-high voltage (UHV) projects, knowledge extracted from historical engineering data is collected and can be potentially used to assist in the review of power transmission and transformation projects. How...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1339416/full |
| _version_ | 1797356941947699200 |
|---|---|
| author | Jie Hu Gang Xu Lizhong Qi Xin Qie |
| author_facet | Jie Hu Gang Xu Lizhong Qi Xin Qie |
| author_sort | Jie Hu |
| collection | DOAJ |
| description | With the rapid development of power grid infrastructure, especially the increasing number of ultra-high voltage (UHV) projects, knowledge extracted from historical engineering data is collected and can be potentially used to assist in the review of power transmission and transformation projects. However, conventional knowledge modeling and knowledge reasoning methods cannot meet the current needs of power grid construction. In this paper, considering the more supernumerary and distinctive information brought by multi-view data which could be beneficial for feature representation and knowledge reasoning from the constructed knowledge base, a multi-view graph convolutional network (GCN) based on knowledge graph is proposed to make classification for power grid infrastructure projects. Specifically, several views are constructed based on attribute information of a knowledge graph. In addition, a Haar convolution-based pooling mechanism is employed to capture the structural features represented by a chain of subgraphs. And then an aggregator that combines both attribute and structural information is used to classify UHV projects. Results from both UHV and NCI-1 datasets indicate that our proposed method is more has higher accuracy and generalization ability. |
| first_indexed | 2024-03-08T14:37:05Z |
| format | Article |
| id | doaj.art-3d68df2194e74facbd118d8b808c85ba |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-03-08T14:37:05Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-3d68df2194e74facbd118d8b808c85ba2024-01-12T04:20:41ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2024-01-011110.3389/fenrg.2023.13394161339416Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional networkJie Hu0Gang Xu1Lizhong Qi2Xin Qie3School of Electrical and Electronic Engineering, North China Electric Power University, Beijing, ChinaSchool of Electrical and Electronic Engineering, North China Electric Power University, Beijing, ChinaState Grid Economic and Technological Research Institute Co Ltd., Beijing, ChinaSchool of Electrical and Electronic Engineering, North China Electric Power University, Beijing, ChinaWith the rapid development of power grid infrastructure, especially the increasing number of ultra-high voltage (UHV) projects, knowledge extracted from historical engineering data is collected and can be potentially used to assist in the review of power transmission and transformation projects. However, conventional knowledge modeling and knowledge reasoning methods cannot meet the current needs of power grid construction. In this paper, considering the more supernumerary and distinctive information brought by multi-view data which could be beneficial for feature representation and knowledge reasoning from the constructed knowledge base, a multi-view graph convolutional network (GCN) based on knowledge graph is proposed to make classification for power grid infrastructure projects. Specifically, several views are constructed based on attribute information of a knowledge graph. In addition, a Haar convolution-based pooling mechanism is employed to capture the structural features represented by a chain of subgraphs. And then an aggregator that combines both attribute and structural information is used to classify UHV projects. Results from both UHV and NCI-1 datasets indicate that our proposed method is more has higher accuracy and generalization ability.https://www.frontiersin.org/articles/10.3389/fenrg.2023.1339416/fullreview of power transmission and transformationknowledge graphgraph classificationgraph convolutional networkknowledge reasoning |
| spellingShingle | Jie Hu Gang Xu Lizhong Qi Xin Qie Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network Frontiers in Energy Research review of power transmission and transformation knowledge graph graph classification graph convolutional network knowledge reasoning |
| title | Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network |
| title_full | Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network |
| title_fullStr | Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network |
| title_full_unstemmed | Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network |
| title_short | Knowledge reasoning in power grid infrastructure projects based on deep multi-view graph convolutional network |
| title_sort | knowledge reasoning in power grid infrastructure projects based on deep multi view graph convolutional network |
| topic | review of power transmission and transformation knowledge graph graph classification graph convolutional network knowledge reasoning |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1339416/full |
| work_keys_str_mv | AT jiehu knowledgereasoninginpowergridinfrastructureprojectsbasedondeepmultiviewgraphconvolutionalnetwork AT gangxu knowledgereasoninginpowergridinfrastructureprojectsbasedondeepmultiviewgraphconvolutionalnetwork AT lizhongqi knowledgereasoninginpowergridinfrastructureprojectsbasedondeepmultiviewgraphconvolutionalnetwork AT xinqie knowledgereasoninginpowergridinfrastructureprojectsbasedondeepmultiviewgraphconvolutionalnetwork |