Deep-learning-based Early Fixing for Gas-lifted Oil Production Optimization: Supervised and Weakly-supervised Approaches

TL;DR

This paper introduces deep learning heuristics for efficiently solving gas-lifted oil production optimization problems by early fixing of integer variables, significantly reducing computation time with supervised and weakly-supervised methods.

Contribution

It presents a novel deep learning-based heuristic approach for early fixing of integer variables in MILPs, including a weakly-supervised method that does not require optimal solutions.

Findings

Runtime reduced by 71.11% using the proposed methods.

Weakly-supervised model effectively fixed variables without optimal training data.

Deep learning heuristics outperform traditional methods in efficiency.

Abstract

Maximizing oil production from gas-lifted oil wells entails solving Mixed-Integer Linear Programs (MILPs). As the parameters of the wells, such as the basic-sediment-to-water ratio and the gas-oil ratio, are updated, the problems must be repeatedly solved. Instead of relying on costly exact methods or the accuracy of general approximate methods, in this paper, we propose a tailor-made heuristic solution based on deep learning models trained to provide values to all integer variables given varying well parameters, early-fixing the integer variables and, thus, reducing the original problem to a linear program (LP). We propose two approaches for developing the learning-based heuristic: a supervised learning approach, which requires the optimal integer values for several instances of the original problem in the training set, and a weakly-supervised learning approach, which requires only solutions for the early-fixed linear problems with random assignments for the integer variables. Our results show a runtime reduction of 71.11% Furthermore, the weakly-supervised learning model provided significant values for early fixing, despite never seeing the optimal values during training.