Deep-Learning-Based Short-Term Voltage Stability Assessment with Topology-Adaptive Voltage Dynamic Feature and Domain Transfer

Abstract

Short-term voltage stability (STVS) assessment is a critical monitoring technology in modern power systems. During daily operations, transmission lines may switch on or off due to scheduled maintenance or unexpected faults, which poses challenges to the STVS assessment under varying topology change conditions. To adapt the STVS assessment to the system topology changes, we propose a deep-learning-based STVS assessment model with the topology-adaptive voltage dynamic feature and the fine-tuning domain transfer for power systems with changing system topologies. The topology-adaptive voltage dynamic feature, extracted from streaming time-series data of phasor measurement units (PMUs), is used to characterize transient voltage stability. The voltage dynamic features depend on the balance of reactive power flow and system topology, effectively revealing both spatiotemporal patterns of post-disturbance system dynamics. The simulation results based on large disturbances in the New England 39-bus power system demonstrate that the proposed model achieves superior STVS assessment performance, with an accuracy of 99.65% in predicting voltage stability compared with the existing deep learning methods. The proposed model also performs well when applied to the larger IEEE 145-bus power system. The fine-tuning domain transfer of the proposed model adapts very well to system topology changes in power systems. It achieves an accuracy of 99.50% in predicting the STVS for the New England 39-bus power system with the transmission line alternation. Further-more, the proposed model demonstrates strong robustness to noisy and missing data.