Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement

TL;DR

This paper presents a physics-informed test-time training framework that improves the accuracy and physical consistency of machine learning-based power flow surrogates by enforcing constraints during inference, without needing labeled data.

Contribution

The proposed PI-TTT method enables local, self-supervised refinement of power flow surrogates at inference time, significantly enhancing their physical accuracy and operational feasibility.

Findings

Reduces power flow residuals by up to two orders of magnitude.

Decreases operational constraint violations substantially.

Maintains computational efficiency of ML models.

Abstract

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.