Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement
This addresses the need for scalable and physics-consistent predictions in power system analysis, representing an incremental improvement over existing ML methods.
The paper tackled the problem of machine learning-based power flow surrogates lacking physical consistency by introducing a physics-informed test-time training framework, which reduced power flow residuals and constraint violations by one to two orders of magnitude on IEEE and PEGASE bus systems while maintaining computational efficiency.
Power Flow (PF) calculation based on machine learning (ML) techniques offer significant computational advantages over traditional numerical methods but often struggle to maintain full physical consistency. This paper introduces a physics-informed test-time training (PI-TTT) framework that enhances the accuracy and feasibility of ML-based PF surrogates by enforcing AC power flow equalities and operational constraints directly at inference time. The proposed method performs a lightweight self-supervised refinement of the surrogate outputs through few gradient-based updates, enabling local adaptation to unseen operating conditions without requiring labeled data. Extensive experiments on the IEEE 14-, 118-, and 300-bus systems and the PEGASE 1354-bus network show that PI-TTT reduces power flow residuals and operational constraint violations by one to two orders of magnitude compared with purely ML-based models, while preserving their computational advantage. The results demonstrate that PI-TTT provides fast, accurate, and physically reliable predictions, representing a promising direction for scalable and physics-consistent learning in power system analysis.