A deep learning model for gas storage optimization

DOI10.1007/S10203-021-00363-6MaRDI QIDQ2064630zbMATH OpenOpenAlexFDO

Authors Nicolas Curin, Michael Kettler, Xi Kleisinger-Yu, Vlatka Komaric, Thomas Krabichler, Josef Teichmann, Hanna Wutte

Publication date 6 January 2022

Published in Decisions in Economics and Finance (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2102.01980

zbMATH Keywords

deep hedginggas storageleast-squares Monte-Carlooptimizationquantitative risk management

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Economic models of real-world systems (e.g., electricity markets, etc.) (91B74) Optimal stochastic control (93E20)

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.

Recommendations

• Generative deep learning for decision making in gas networks
• A Semi-Lagrangian Approach for Natural Gas Storage Valuation and Optimal Operation
• Integrated optimization models and problems of gas production, distribution, and storage
• Convolutional -- recurrent neural network proxy for robust optimization and closed-loop reservoir management
• Maximizing the storage capacity of gas networks: a global MINLP approach
• An approximate dynamic programming approach to benchmark practice-based heuristics for natural gas storage valuation
• Physics informed neural networks: a case study for gas transport problems
• High detail stationary optimization models for gas networks

Cites work

• Deep hedging
• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
• Gas storage hedging
• Natural gas storage valuation and optimization under time-inhomogeneous exponential Lévy processes
• Natural gas storage valuation and optimization: A real options application
• Numerical methods for the pricing of swing options: a stochastic control approach
• Reinforcement learning. An introduction
• Smile modeling in commodity markets
• Valuation of Commodity-Based Swing Options
• Valuation of energy storage: an optimal switching approach

Cited in

(2)

• Generative deep learning for decision making in gas networks
• A level-set approach to the control of state-constrained McKean-Vlasov equations: application to renewable energy storage and portfolio selection

This page was built for publication: A deep learning model for gas storage optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2064630)