Accelerating gas-network feasibility screening with a physics-informed graph neural network surrogate

2026-07-15

AI Summary

This work addresses the high computational cost of steady-state simulation in large-scale gas networks, where traditional nonlinear solvers suffer from low efficiency and purely data-driven models often yield physically infeasible solutions. The authors propose a physics-informed graph neural network surrogate model that employs an edge-centric architecture to predict pressure drops and flow rates across pipeline segments. Physical consistency is enforced through a differentiable projection layer that guarantees nodal mass conservation, complemented by a Laplacian-based pressure reconstruction to ensure topologically coherent pressure fields. Evaluated on the GasLib-582 benchmark, the model achieves a mean absolute error of 1.05 bar (1.3% of the pressure range) and an R² of 0.981 for pressure prediction, with inference times under 40 milliseconds and mass imbalance residuals as low as 10⁻⁵–10⁻⁴ Nm³/s, demonstrating an exceptional balance among accuracy, physical fidelity, and computational efficiency.

Abstract

Large-scale gas-network scenario evaluation is a computational bottleneck in integrated energy-system planning, particularly when gas infrastructure interacts with power, heat, hydrogen, and sector-coupling pathways. Conventional nonlinear hydraulic solvers provide reliable feasibility assessment but are costly for stochastic screening, whereas unconstrained learning-based surrogates may produce hydraulically infeasible states. This study develops a physics-informed graph neural network surrogate for steady-state gas-network simulation and feasibility screening. The model uses an edge-centric architecture to predict pipe-level squared-pressure differences and flows. A differentiable projection layer enforces nodal mass conservation on predicted flows, while a Laplacian reconstruction maps edge pressure differences to topologically consistent nodal pressures. The framework is evaluated on GasLib-134, GasLib-135, and GasLib-582 using stochastically generated operating scenarios. On the meshed 582-node benchmark trained with 5000 scenarios, the surrogate achieves a pressure mean absolute error of 1.05~bar, corresponding to 1.3\% of the realized pressure range, with $R^2 = 0.981$. Projected-flow predictions reach $R^2 = 0.972$, and mass-balance residuals are reduced to numerical precision, on the order of $10^{-5}$--$10^{-4}$~Nm$^3$/s. Compared with the MYNTS reference solver, inference is reduced from seconds to milliseconds, with the largest benchmark evaluated in less than 40~ms. Loadability and out-of-distribution stress-test evaluations demonstrate robust feasibility screening under high-load conditions, while strongly localized demand concentrations are identified as cases requiring solver-based verification near feasibility limits. The framework provides a physically constrained planning accelerator for high-volume scenario screening and prioritization.

Problem

• gas-network feasibility
• integrated energy systems
• scenario screening
• computational bottleneck
• hydraulic simulation

Innovation

• physics-informed graph neural network
• gas-network feasibility screening
• differentiable projection
• Laplacian pressure reconstruction
• surrogate modeling