Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability

Highlights A fast TSA scheme for pre-failure scanning. A physical mechanism-based attention structure for dynamic graph pooling. A node regression model that responds to key physical mechanisms. Generator label for richer output information. Top performance and post-hoc interpretation.

Bibliographic Details
Main Authors: Liukai Chen, Lin Guan
Format: Article
Language:English
Published: SpringerOpen 2023-01-01
Series:Protection and Control of Modern Power Systems
Subjects:
Online Access:https://doi.org/10.1186/s41601-023-00278-x
_version_ 1811171663120695296
author Liukai Chen
Lin Guan
author_facet Liukai Chen
Lin Guan
author_sort Liukai Chen
collection DOAJ
description Highlights A fast TSA scheme for pre-failure scanning. A physical mechanism-based attention structure for dynamic graph pooling. A node regression model that responds to key physical mechanisms. Generator label for richer output information. Top performance and post-hoc interpretation.
first_indexed 2024-04-10T17:18:47Z
format Article
id doaj.art-d7286e62482f473d93ca778bf5c10298
institution Directory Open Access Journal
issn 2367-2617
2367-0983
language English
last_indexed 2024-04-10T17:18:47Z
publishDate 2023-01-01
publisher SpringerOpen
record_format Article
series Protection and Control of Modern Power Systems
spelling doaj.art-d7286e62482f473d93ca778bf5c102982023-02-05T12:16:06ZengSpringerOpenProtection and Control of Modern Power Systems2367-26172367-09832023-01-018111610.1186/s41601-023-00278-xStatic information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretabilityLiukai Chen0Lin Guan1School of Electric Power, South China University of TechnologySchool of Electric Power, South China University of TechnologyHighlights A fast TSA scheme for pre-failure scanning. A physical mechanism-based attention structure for dynamic graph pooling. A node regression model that responds to key physical mechanisms. Generator label for richer output information. Top performance and post-hoc interpretation.https://doi.org/10.1186/s41601-023-00278-xTransient stability assessment (TSA)Data-drivenExplainableGraph neural network (GNN)Self-attention
spellingShingle Liukai Chen
Lin Guan
Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
Protection and Control of Modern Power Systems
Transient stability assessment (TSA)
Data-driven
Explainable
Graph neural network (GNN)
Self-attention
title Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
title_full Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
title_fullStr Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
title_full_unstemmed Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
title_short Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
title_sort static information k neighbor and self attention aggregated scheme a transient stability prediction model with enhanced interpretability
topic Transient stability assessment (TSA)
Data-driven
Explainable
Graph neural network (GNN)
Self-attention
url https://doi.org/10.1186/s41601-023-00278-x
work_keys_str_mv AT liukaichen staticinformationkneighborandselfattentionaggregatedschemeatransientstabilitypredictionmodelwithenhancedinterpretability
AT linguan staticinformationkneighborandselfattentionaggregatedschemeatransientstabilitypredictionmodelwithenhancedinterpretability