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

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:
Transient stability assessment (TSA)
Data-driven
Explainable
Graph neural network (GNN)
Self-attention
Online Access:https://doi.org/10.1186/s41601-023-00278-x

Internet

https://doi.org/10.1186/s41601-023-00278-x

Similar Items