System-Scale-Free Transient Contingency Screening Scheme Based on Steady-State Information: A Pooling-Ensemble Multi-Graph Learning Approach

Data-driven transient stability assessment (TSA) models are usually sensitive to system scale changes and require dynamic information from time-domain simulation (TDS) as inputs. We propose a
S
ystem-sc
A
le-
F
re
E

T
ransient
C
ontingency
S
creening (SAFE-TCS) scheme based on only the steady-state measurements. An analytical model is set up to estimate the state variation at fault occurrence (
$t_{0+}$
) snapshot, which forms multi-graph inputs together with the steady-state information. A novel pooling-ensemble multi-attention graph convolutional network (PE-MAGCN) realizes the spatio-temporal graph embedding, in which an inter-graph convolution link works for the temporal abstraction. Following a pooling-ensemble mechanism, PE-MAGCN derives a fixed-size expressive vector for task-specific networks. This promotes the robustness of the model against system extension. The advantages of SAFE-TCS also benefit from the coordination of various training tricks, including channel attention, category-balanced sampling and joint-decoupling learning, etc. Test results on IEEE 39 Bus system and IEEE 300 Bus system indicate the superiority of the proposed scheme over existing models and its adaptability under various scenarios.