Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement
By: Panteleimon Dogoulis , Mohammad Iman Alizadeh , Sylvain Kubler and more
Potential Business Impact:
Makes power grids predict electricity flow accurately.
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.
Similar Papers
Study Design and Demystification of Physics Informed Neural Networks for Power Flow Simulation
Machine Learning (CS)
Makes power grids safer and more reliable.
Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee
Machine Learning (CS)
Makes power grids run faster and cheaper.
Machine Learning for Physical Simulation Challenge Results and Retrospective Analysis: Power Grid Use Case
Machine Learning (CS)
Makes power grids safer with faster computer checks.