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

Vladimir Dvorkin, Samuel Chevalier, Spyros Chatzivasileiadis

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Planning optimization of gas networks under emission constraints prioritizes gas supply with the smallest emission footprint. As this problem includes complex gas flow physical laws, standard optimization solvers cannot guarantee convergence to a feasible solution, especially under strict emission constraints. 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.
Original languageEnglish
Title of host publicationProceedings of 2023 62nd IEEE Conference on Decision and Control (CDC)
Number of pages5
PublisherIEEE
Publication date2024
Pages1575-1579
ISBN (Electronic)979-8-3503-0124-3
DOIs
Publication statusPublished - 2024
Event62nd IEEE Conference on Decision and Control - Marina Bay Sands, Singapore
Duration: 13 Dec 202315 Dec 2023

Conference

Conference62nd IEEE Conference on Decision and Control
Country/TerritorySingapore
CityMarina Bay Sands
Period13/12/202315/12/2023
SeriesProceedings of the IEEE Conference on Decision and Control
ISSN0743-1546

Fingerprint

Dive into the research topics of 'Emission-Constrained Optimization of Gas Networks: Input-Convex Neural Network Approach'. Together they form a unique fingerprint.

Cite this