Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
Not on the map. Why?
Abstract (arXiv)
Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (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 knownoperator 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 deg in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively. With streaming micro-batches, it delivers 2-5x faster batched inference than NR on 4-1024-bus grids.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 36 references that are in the map. First posted on arXiv 26 Sep 2025.
Builds on
14 of 36 references.
References · 14
- 2017Attention Is All You Needcited by 60,361
- 2017Graph Attention Networkscited by 8,923
- 2017Deep Setscited by 1,421
- 2021Characterizing possible failure modes in physics-informed neural networkscited by 643
- 2019Optimal Power Flow Using Graph Neural Networkscited by 63
- 2020Physics-Guided Deep Neural Networks for Power Flow Analysiscited by 33
- 2024Foundation Models for the Electric Power Gridcited by 28
- 2024OPFData: Large-scale datasets for AC optimal power flow with topological perturbationscited by 24
- 2023PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networkscited by 21
- 2021Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Futurecited by 18
- 2022Solving AC Power Flow with Graph Neural Networks under Realistic Constraintscited by 11
- 2023Physics-Guided Graph Neural Networks for Real-time AC/DC Power Flow Analysiscited by 2
2 more
Built on by
Citing papers per year: 2026: 2.
2 papers.