The paper presents a physics‑aware distillation of a large Grid Foundation Model (GridFM) for real‑time edge inference. A 20.1 M‑parameter, 12‑layer teacher is compressed into a 0.62 M‑parameter, 6‑layer student, achieving a 32.5× reduction in parameters and halving message‑passing depth while improving accuracy on active‑power dispatch by up to 48 % and always outperforming the teacher on reactive‑power dispatch. The distillation objective combines masked power‑flow loss with output, physics‑residual, latent‑state, and attention transfer, though the physics‑residual term proved detrimental in this setting.
Grid foundation models (GridFMs) are graph transformers pretrained on a masked power-flow objective, and evaluate power flow orders of magnitude faster than an iterative solver. Their size, however, t...
arXiv:2605.23194v2 Announce Type: replace-cross Abstract: Fast and reliable optimal power flow (OPF) approximation is important for power system operation, yet heterogeneous OPF graph models are ofte...
arXiv:2608. 09921v1 Announce Type: new Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis, where strict physical consistency must be enforced.
arXiv:2608.21719v1 Announce Type: cross Abstract: AI inference clusters are increasingly constrained by instantaneous power, not just energy: grid operators condition new capacity on demand response,...
arXiv:2610.20462v1 Announce Type: new Abstract: Foundation models have shown strong generalization across scientific domains, but their use in power systems remains largely task-specific. We investig...
The paper presents a hierarchical graph neural network (GNN) approach for power‑flow modeling that leverages physics‑informed graph reductions. By exchanging information through two reduced graphs within the corrective network of GENCO, the model achieves superior generalization across three grid topologies and new operating scenarios, outperforming both the flat baseline and a Quotient construction. Training required only about 200 epochs and fewer than 1,900 scenarios per grid, yet the hierarchical models achieved a macro family‑balanced voltage error of 0.851±0.110, a 51.3% improvement over the per‑bus mean fitted on training solutions.
Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode relational structure particular to the training topologies rather than the underlying physics, causing models to fail on unseen grids despite strong in-distribution performance.
arXiv:2607. 12241v1 Announce Type: cross Abstract: Machine-learned surrogates for the AC power flow (ACPF) problem amortize the cost of repeated solves on a fixed network, but lose one to two orders of magnitude of accuracy when a line outage changes the topology.
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.
arXiv:2510. 22048v4 Announce Type: replace Abstract: Power flow (PF) calculations are the backbone of real-time grid operations, across workflows such as contingency analysis (where repeated PF evaluations assess grid security under outages) and topology optimization (which involves PF-based searches over combinatorially large action spaces).
Spectral-Guided Diffusion introduces a method to accelerate diffusion inference by identifying and reusing residual branches that need not be recomputed during the trajectory. The approach uses a Spectral Concentration Ratio (SCR) combined with Frobenius magnitude to create an offline sensitivity proxy and deterministic lifetime for each scheduled unit, eliminating the need for routers or input-dependent searches. Experiments on models such as LLaDA-8B, DiT-XL/2, U-ViT-L, and SDXL show that this scheduling preserves quality better than several baselines and achieves up to a 3.0× wall‑clock speedup over eager inference.
arXiv:2607. 13763v1 Announce Type: cross Abstract: Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift.