A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems

Transient stability assessments and state prediction are critical tasks for power system security. The increasing integration of renewable energy sources has introduced significant uncertainties into these tasks. While AI has shown great potential, most existing AI-based approaches focus on single t...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuaibo Wang, Xinyuan Xiang, Jie Zhang, Zhuohang Liang, Shufang Li, Peilin Zhong, Jie Zeng, Chenguang Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/6/1531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204220138979328
author Shuaibo Wang
Xinyuan Xiang
Jie Zhang
Zhuohang Liang
Shufang Li
Peilin Zhong
Jie Zeng
Chenguang Wang
author_facet Shuaibo Wang
Xinyuan Xiang
Jie Zhang
Zhuohang Liang
Shufang Li
Peilin Zhong
Jie Zeng
Chenguang Wang
author_sort Shuaibo Wang
collection DOAJ
description Transient stability assessments and state prediction are critical tasks for power system security. The increasing integration of renewable energy sources has introduced significant uncertainties into these tasks. While AI has shown great potential, most existing AI-based approaches focus on single tasks, such as either stability assessments or state prediction, limiting their practical applicability. In power system operations, these two tasks are inherently coupled, as system states directly influence stability conditions. To address these challenges, this paper presents a multi-task learning framework based on spatiotemporal graph convolutional networks that efficiently performs both tasks. The proposed framework employs a spatiotemporal graph convolutional encoder to capture system topology features and integrates a self-attention U-shaped residual decoder to enhance prediction accuracy. Additionally, a Multi-Exit Network branch with confidence-based exit points enables efficient and reliable transient stability assessments. Experimental results on IEEE standard test systems and real-world power grids demonstrate the framework’s superiority as compared to state-of-the-art AI models, achieving a 48.1% reduction in prediction error, a 6.3% improvement in the classification F1 score, and a 52.1% decrease in inference time, offering a robust solution for modern power system monitoring and safety assessments.
format Article
id doaj-art-0d74a01253be42cdb6860c33399c85db
institution OA Journals
issn 1996-1073
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-0d74a01253be42cdb6860c33399c85db2025-08-20T02:11:19ZengMDPI AGEnergies1996-10732025-03-01186153110.3390/en18061531A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power SystemsShuaibo Wang0Xinyuan Xiang1Jie Zhang2Zhuohang Liang3Shufang Li4Peilin Zhong5Jie Zeng6Chenguang Wang7School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaState Key Laboratory of HVDC, Electric Power Research Institute, China Southern Power Grid, Guangzhou 510663, ChinaGuangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System, Guangzhou 510663, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaTransient stability assessments and state prediction are critical tasks for power system security. The increasing integration of renewable energy sources has introduced significant uncertainties into these tasks. While AI has shown great potential, most existing AI-based approaches focus on single tasks, such as either stability assessments or state prediction, limiting their practical applicability. In power system operations, these two tasks are inherently coupled, as system states directly influence stability conditions. To address these challenges, this paper presents a multi-task learning framework based on spatiotemporal graph convolutional networks that efficiently performs both tasks. The proposed framework employs a spatiotemporal graph convolutional encoder to capture system topology features and integrates a self-attention U-shaped residual decoder to enhance prediction accuracy. Additionally, a Multi-Exit Network branch with confidence-based exit points enables efficient and reliable transient stability assessments. Experimental results on IEEE standard test systems and real-world power grids demonstrate the framework’s superiority as compared to state-of-the-art AI models, achieving a 48.1% reduction in prediction error, a 6.3% improvement in the classification F1 score, and a 52.1% decrease in inference time, offering a robust solution for modern power system monitoring and safety assessments.https://www.mdpi.com/1996-1073/18/6/1531power system transient stability assessmentstate predictionmulti-task learning
spellingShingle Shuaibo Wang
Xinyuan Xiang
Jie Zhang
Zhuohang Liang
Shufang Li
Peilin Zhong
Jie Zeng
Chenguang Wang
A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
Energies
power system transient stability assessment
state prediction
multi-task learning
title A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
title_full A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
title_fullStr A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
title_full_unstemmed A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
title_short A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems
title_sort multi task spatiotemporal graph neural network for transient stability and state prediction in power systems
topic power system transient stability assessment
state prediction
multi-task learning
url https://www.mdpi.com/1996-1073/18/6/1531
work_keys_str_mv AT shuaibowang amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT xinyuanxiang amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT jiezhang amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT zhuohangliang amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT shufangli amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT peilinzhong amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT jiezeng amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT chenguangwang amultitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT shuaibowang multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT xinyuanxiang multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT jiezhang multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT zhuohangliang multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT shufangli multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT peilinzhong multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT jiezeng multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems
AT chenguangwang multitaskspatiotemporalgraphneuralnetworkfortransientstabilityandstatepredictioninpowersystems