Generative deep learning for decision making in gas networks
Not on the map. Why?
Abstract (arXiv)
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. With the trained network we produce a feasible solution in 2.5s, use it as a warm-start solution, and thereby decrease global optimal solution solve time by 60.5%.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 54 references that are in the map. First posted on arXiv 3 Feb 2021.
Builds on
19 of 54 references.
References · 19
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
- 2015Cyclical Learning Rates for Training Neural Networkscited by 627
- 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 612
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
- 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
- 2020Solving Mixed Integer Programs Using Neural Networkscited by 178
- 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 108
- 2019MIPaaL: Mixed Integer Program as a Layercited by 93
- 2020Parameterizing Branch-and-Bound Search Trees to Learn Branching Policiescited by 62
7 more
- 2016Connecting Generative Adversarial Networks and Actor-Critic Methodscited by 49
- 2019Online Mixed-Integer Optimization in Millisecondscited by 37
- 2018The Voice of Optimizationcited by 28
- 2020Reinforcement Learning for Variable Selection in a Branch and Bound Algorithmcited by 28
- 2017Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselinescited by 20
- 2019Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Predictioncited by 2
- 2020An Actor-Critic-Based UAV-BSs Deployment Method for Dynamic Environmentscited by 1
Built on by
Citing papers per year: 2023: 2.
2 papers.