Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-15834
For citation please use:
Main Title: Generative deep learning for decision making in gas networks
Author(s): Anderson, Lovis
Turner, Mark
Koch, Thorsten
Type: Article
URI: https://depositonce.tu-berlin.de/handle/11303/17055
http://dx.doi.org/10.14279/depositonce-15834
License: https://creativecommons.org/licenses/by/4.0/
Abstract: A decision support system relies on frequent re-solving of similar problem instances. While the general structure remains the same in corresponding applications, the input parameters are updated on a regular basis. We propose a generative neural network design for learning integer decision variables of mixed-integer linear programming (MILP) formulations of these problems. We utilise a deep neural network discriminator and a MILP solver as our oracle to train our generative neural network. In this article, we present the results of our design applied to the transient gas optimisation problem. The trained generative neural network produces a feasible solution in 2.5s, and when used as a warm start solution, decreases global optimal solution time by 60.5%.
Subject(s): mixed-integer programming
deep learning
primal heuristic
gas networks
generative modelling
Issue Date: 19-Apr-2022
Date Available: 18-Jul-2022
Language Code: en
DDC Class: 510 Mathematik
Sponsor/Funder: TU Berlin, Open-Access-Mittel – 2022
Journal Title: Mathematical Methods of Operations Research
Publisher: Springer Nature
Volume: 95
Publisher DOI: 10.1007/s00186-022-00777-x
Page Start: 503
Page End: 532
EISSN: 1432-5217
ISSN: 1432-2994
TU Affiliation(s): Fak. 2 Mathematik und Naturwissenschaften » Inst. Mathematik » FG Software und Algorithmen für die diskrete Optimierung
Appears in Collections:Technische Universität Berlin » Publications

Files in This Item:

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons