Revisiting data-driven dynamic security assessment with a tabular foundation model

2026-07-17

AI Summary

This work proposes a novel approach to dynamic security assessment in power systems by introducing tabular foundation models (TFMs), which overcome the limitations of conventional data-driven methods that require separate model training for each contingency and rely heavily on large labeled datasets with limited generalization. By integrating electrical distance-based coordinate encoding and in-context learning, the proposed method enables multi-contingency assessment without retraining or hyperparameter tuning. It drastically reduces dependence on labeled data: on the IEEE 68-bus system, it achieves an average Macro F1 score of 90% with only 120 samples per contingency, and for unseen contingencies, just 10 samples suffice to match the performance of idealized transfer learning—thereby breaking through the generalization bottleneck inherent in traditional models.

Abstract

Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning. Existing approaches face two limitations. First, they require a large labelled database for training, with a separate model trained, tuned, and maintained for each contingency in a potentially long list of credible contingencies. Second, the trained models generalize poorly to unseen contingencies. This work addresses the limitations by using a tabular foundation model (TFM) that assesses stability through in-context learning, requiring no retraining or hyperparameter optimization. A single TFM can assess many contingencies at once, removing the need for one model per classifier. We also characterize when the use of electrical distance coordinates (EDC) as continuous features enables generalization of TFM to unseen contingencies and when they do not, demonstrating how a few labelled samples can reliably improve generalization. Through comprehensive case studies on the IEEE 68-bus system, we show that a single TFM attains an average Macro F1 score of about 90% with only 120 labelled samples per contingency, roughly two orders of magnitude fewer than conventionally assumed, without any model retraining or hyperparameter tuning. For new/unseen contingencies, we show that using just 10 labelled samples of the new contingency with EDC encoding matches the best achievable transfer learning oracle model, which requires fully labelled data and is not deployable in practice. Overall, this initial study paves the way towards developing and deploying foundation models for power system operations, with possible applications across multiple operational tasks.

Problem

• dynamic security assessment
• power system
• contingency generalization
• labelled data scarcity
• machine learning

Innovation

• tabular foundation model
• in-context learning
• dynamic security assessment
• electrical distance coordinates
• few-shot generalization