← Back to all news
arXiv Machine Learning By Anna Varbella, Damien Briens, Blazhe Gjorgiev, Giuseppe Alessio D'Inverno, Priya L. Donti, Giovanni Sansavini

Physics-Informed Graph Neural Networks for Robust AC-Optimal Power Flow

Read the original on arXiv Machine Learning →

arXiv:2410. 04818v2 Announce Type: replace-cross Abstract: We present PINCO, an unsupervised learning framework that integrates Graph Neural Networks with physics-informed neural networks for AC optimal power flow (AC-OPF) solutions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 25

GridSFM: A Foundation Model for Solving AC Optimal Power Flow

GridSFM is a 15‑million‑parameter physics‑inspired graph neural network that serves as a foundation model for solving AC Optimal Power Flow (AC‑OPF) across diverse grid topologies. Pretrained on 54 topologies ranging from 500 to 4,000 buses, it achieves a 2.45 % zero‑shot generation‑cost error on a held‑out 10,000‑bus case and adapts to unseen grids with only 100 solved instances using a physics‑informed fine‑tuning scheme based on Newton’s method. The authors address the disconnected feasible set of AC‑OPF by lifting and relaxing constraints with logarithmically penalized slacks, proving the resulting elastic feasible set is contractible and that solutions can be projected back onto the original feasible set.

By Luke Bhan, Weiwei Yang, Margaret Capetz, Baosen Zhang
fine-tuning
More like this →
arXiv Machine Learning
Aug 27

Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration

The paper introduces Penalty + Sequential Linearized Feasibility Seeking (SLFS), a self‑supervised learning framework for solving multiphase AC optimal power flow (AC‑OPF) in distribution systems with topology reconfiguration. SLFS trains directly from the AC‑OPF objective and constraints using a differentiable fixed‑point power flow solver, avoiding the need for labeled optimal solutions. It achieves negligible optimality gaps and near‑zero constraint violations on IEEE feeders up to 8,500 nodes, delivering up to three orders of magnitude speedups over IPOPT while maintaining robustness to large distributional shifts.

By Hoang T. Nguyen, Shaohui Liu, Reetam Sen Biswas, Varsha Pendyala, Nurali Virani, Deepjyoti Deka, Priya L. Donti
More like this →
arXiv AI
Aug 18

Graph Machine Learning: An Opportunity for Power Systems

arXiv:2608. 16494v1 Announce Type: cross Abstract: Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for real-time decision-making across a wide range of timescales.

By Martin Sadric, Sebastian P\"utz, Christian Nauck, Veit Hagenmeyer, Frank Hellmann, Dirk Witthaut, Benjamin Sch\"afer
benchmarkssafety
More like this →