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...
The paper extends the neural network verification framework to graph neural networks by introducing GraphStar sets, which model uncertainty over both node and edge features. This allows sound propagation of linear message‑passing operations and ReLU nonlinearities for GCN and GINE layers. Experiments on power system tasks (PF, OPF, CFA) and graph classification benchmarks (ENZYMES, PROTEINS) show that the method, called GNNV, yields tighter robustness guarantees than CORA and provides, for the first time, edge‑aware guarantees for GINE‑based models under joint node and edge perturbations.
The paper presents a unified benchmark of graph neural network (GNN) architectures for predicting AC power flow (ACPF) on IEEE 14‑bus and 118‑bus systems. It isolates the effects of message‑passing mechanisms and inductive biases by using identical preprocessing, training procedures, and comparable parameter budgets. The study finds that anisotropic message‑passing, explicit edge features for line impedances, and global context aggregation yield the best trade‑off between predictive accuracy and physical consistency, while two or three message‑passing layers are generally optimal under a fixed parameter budget.
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.
arXiv:2607. 09122v1 Announce Type: new Abstract: Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention has been paid to the solution feasibility, which can be obtained by traditional solvers.
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.
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: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.
arXiv:2602. 17975v2 Announce Type: replace Abstract: This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations.
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.
The paper introduces a method that uses a single deep neural network, trained only on basecase AC power flow data, to predict post-contingency operating states for any single-line outage. It frames this prediction as a fixed-point iteration and provides sufficient convergence conditions, certifying them via semidefinite programming. Numerical experiments on the IEEE 118-bus system show that the certified conditions hold for all tested contingencies and that accurate state estimates are achieved in only a few iterations.
The paper introduces Multi-Channel Physics-Aware Random Walk Fingerprints (MC-PA-RWF), a lightweight graph-level representation that incorporates physical edge states into random-walk propagation for power grid graphs. By constructing multiple edge-weighted channels from domain-relevant attributes and concatenating channel-specific fingerprints, the method achieves high balanced accuracy on PowerGraph benchmarks, outperforming topology-only RWF and matching or surpassing several graph neural network baselines. Experiments on three benchmark systems show statistically significant improvements, with the node-edge extension reaching up to 99.32% balanced accuracy and boosting failure-class F1 scores by 1.60–5.84 percentage points.