A deep learning model for gas storage optimization

TL;DR

This paper introduces a deep learning approach inspired by reinforcement learning to optimize underground natural gas storage operations, addressing high-dimensional and constrained market complexities.

Contribution

It presents a novel deep learning framework for gas storage optimization, offering a theoretical basis and numerical performance assessment against existing methods.

Findings

Deep learning outperforms traditional techniques in complex market scenarios

The proposed method effectively handles high-dimensional data and constraints

Numerical results demonstrate improved optimization accuracy

Abstract

To the best of our knowledge, the application of deep learning in the field of quantitative risk management is still a relatively recent phenomenon. In this article, we utilize techniques inspired by reinforcement learning in order to optimize the operation plans of underground natural gas storage facilities. We provide a theoretical framework and assess the performance of the proposed method numerically in comparison to a state-of-the-art least-squares Monte-Carlo approach. Due to the inherent intricacy originating from the high-dimensional forward market as well as the numerous constraints and frictions, the optimization exercise can hardly be tackled by means of traditional techniques.