Chao Shen, Ke Zuo, Mingyang Sun
Existing dynamics prediction frameworks for transient stability analysis (TSA) fail to achieve multi-scenario "universality"--the inherent ability of a single, pre-trained architecture to generalize across diverse operating conditions, unseen faults, and heterogeneous systems. To address this, this paper proposes TSA-LLM, a large language model (LLM)-based universal framework that models multi-variate transient dynamics prediction as a univariate generative task with three key innovations: First, a novel data processing pipeline featuring channel independence decomposition to resolve dimensional heterogeneity, sample-wise normalization to eliminate separate stable or unstable pipelines, and temporal patching for efficient long-sequence modeling; Second, a parameter-efficient freeze-and-finetune strategy that augments the LLM's architecture with dedicated input embedding and output projection layers while freezing core transformer blocks to preserve generic feature extraction capabilities; Third, a two-stage fine-tuning scheme that combines teacher forcing, which feeds the model ground-truth data during initial training, with scheduled sampling, which gradually shifts to leveraging model-generated predictions, to mitigate cumulative errors in long-horizon iterative prediction. Comprehensive testing demonstrates the framework's universality, as TSA-LLM trained solely on the New England 39-bus system achieves zero-shot generalization to mixed stability conditions and unseen faults, and matches expert performance on the larger Iceland 189-bus system with only 5% fine-tuning data. This multi-scenario versatility validates a universal framework that eliminates scenario-specific retraining and achieves scalability via large-scale parameters and cross-scenario training data.