Physics-Informed GNN for Medium-High Voltage AC Power Flow With Edge-Aware Attention and Line Search Correction Operator

Kim C, Conrad T, Karim R, Oelhaf J, Riebesel D, Arias Vergara T, Maier A, Jäger J, Bayer S (2026)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Publisher: IEEE

Series: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

City/Town: Barcelona, Spain

Conference Proceedings Title: 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Event location: Barcelona, Spain

URI: https://ieeexplore.ieee.org/document/11463241

DOI: 10.1109/ICASSP55912.2026.11463241

Abstract

Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic Newton–Raphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the soft constraint on the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases to form a fully differentiable known-operator layer inside the computation graph, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4–32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08° in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2–5× faster batched inference than NR on 4–1024-bus grids.

Authors with CRIS profile

Related research project(s)

How to cite

APA:

Kim, C., Conrad, T., Karim, R., Oelhaf, J., Riebesel, D., Arias Vergara, T.,... Bayer, S. (2026). Physics-Informed GNN for Medium-High Voltage AC Power Flow With Edge-Aware Attention and Line Search Correction Operator. In 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona, Spain, ES: IEEE.

MLA:

Kim, Changhun, et al. "Physics-Informed GNN for Medium-High Voltage AC Power Flow With Edge-Aware Attention and Line Search Correction Operator." Proceedings of the 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain IEEE, 2026.

BibTeX: Download