Emission-Aware Optimization of Gas Networks: Input-Convex Neural Network Approach

2022/09/18 by Vladimir Dvorkin, Dvorkin, Vladimir, Samuel Chevalier +3
Engineering · #Advanced Control Systems Optimization #Enhanced Oil Recovery Techniques #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Process Optimization and Integration

paper · pdf · doi:10.48550/arxiv.2209.08645

openalex publication_date 2022/09/18 · openalex created_date 2022/09/21 · openalex updated_date 2026/07/28

Abstract

Gas network planning optimization under emission constraints prioritizes gas supply with the least CO₂ intensity. As this problem includes complex physical laws of gas flow, standard optimization solvers cannot guarantee convergence to a feasible solution. To address this issue, we develop an input-convex neural network (ICNN) aided optimization routine which incorporates a set of trained ICNNs approximating the gas flow equations with high precision. Numerical tests on the Belgium gas network demonstrate that the ICNN-aided optimization dominates non-convex and relaxation-based solvers, with larger optimality gains pertaining to stricter emission targets. Moreover, whenever the non-convex solver fails, the ICNN-aided optimization provides a feasible solution to network planning.

Related

• Machine Learning for Improved Gas Network Models in Coordinated Energy Systems
• Improved Mixing and Pressure Loss Formulations for Gas Network Optimization
• A Data-Driven Warm Start Approach for Convex Relaxation in Optimal Gas Flow
• Natural Gas Flow Solvers using Convex Relaxation
• Natural Gas Flow Equations: Uniqueness and an MI-SOCP Solver