Generative deep learning for decision making in gas networks
This work provides an incremental improvement in solving time for transient gas optimisation problems for operators of gas networks.
This paper addresses the problem of frequent re-solving of similar mixed-integer linear programming (MILP) instances in decision support systems, specifically for transient gas optimisation. They propose a generative neural network to learn integer decision variables, which, when used as a warm-start, decreases the global optimal solution solve time by 60.5%.
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%.