analiza aiqbench
This research introduces a unified heterogeneous graph neural network capable of solving multiple power system analysis tasks—power flow, optimal power flow, and state estimation—with a single shared backbone. By training jointly across diverse topologies, the model achieves accuracy comparable to task-specific solvers while offering robustness to unseen conditions, marking a significant step toward foundation models for grid operations. The work demonstrates how advanced machine learning architectures can generalize complex physical system behaviors without requiring separate models for each analytical problem.
Unified Heterogeneous Graph Neural Network solver for Power Flow, Optimal Power Flow and State Estimation
arXiv:2609.16738v1 Announce Type: cross Abstract: Power Flow (PF), Optimal Power Flow (OPF), and State Estimation (SE) are fundamental problems in power system analysis, but solving them is computationally expensive. Graph Neural Networks (GNNs) have been proposed as fast surrogates, yet existing solvers are trained for a single problem at a time, producing narrow models that must be rebuilt for each new task. We propose a more general approach: a single Heterogeneous Residual Gated Graph Convolutional Network that solves all three problems with one shared backbone. Rather than learning one mapping, the model learns a reusable representation of how the network behaves, from which PF, OPF, and SE can each be estimated. Trained jointly on the three problems across diverse topologies and loading conditions, and evaluated on the IEEE 14-bus and 118-bus systems, the shared model matches the accuracy of task-specific GNN solvers and stays robust on unseen loading levels and topologies. These results show that a single model can capture the basic operation of a power network and serve several analysis tasks at once, a first step toward a foundation model for power systems.
Abstract:Power Flow (PF), Optimal Power Flow (OPF), and State Estimation (SE) are fundamental problems in power system analysis, but solving them is computationally expensive. Graph Neural Networks (GNNs) have been proposed as fast surrogates, yet existing solvers are trained for a single problem at a time, producing narrow models that must be rebuilt for each new task. We propose a more general approach: a single Heterogeneous Residual Gated Graph Convolutional Network that solves all three problems with one shared backbone. Rather than learning one mapping, the model learns a reusable representation of how the network behaves, from which PF, OPF, and SE can each be estimated. Trained jointly on the three problems across diverse topologies and loading conditions, and evaluated on the IEEE 14-bus and 118-bus systems, the shared model matches the accuracy of task-specific GNN solvers and stays robust on unseen loading levels and topologies. These results show that a single model can capture the basic operation of a power network and serve several analysis tasks at once, a first step toward a foundation model for power systems.
Systems and Control (eess.SY); Machine Learning (cs.LG)
arXiv:2609.16738 [eess.SY]
(or arXiv:2609.16738v1 [eess.SY] for this version)
https://doi.org/10.48550/arXiv.2609.16738 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 277 cuvinte
Subiecte conexe
IBM’s quantum GENCO neural solver unifies three grid tasks
Quantum Zeitgeist · 12 aug. 2026
News
Quantum Computing Report · 25 iul. 2026
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · 15 iul. 2026
Physics-Informed Graph Neural Networks for Robust AC-Optimal Power Flow
arXiv · 30 iul. 2026