A deep learning model for gas storage optimization. (English) Zbl 1480.91153
Summary: 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.
MSC:
| 91B74 | Economic models of real-world systems (e.g., electricity markets, etc.) |
| 93E20 | Optimal stochastic control |
| 68T07 | Artificial neural networks and deep learning |
Keywords:
deep hedging; gas storage; least-squares Monte-Carlo; optimization; quantitative risk managementReferences:
| [1] | Bachouch, A.; Huré, C.; Langrené, N.; Pham, H., Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications, SIAM J. Numer. Anal., 59, 525-557 (2020) · Zbl 1466.65007 |
| [2] | Barrera-Esteve, C.; Bergeret, F.; Dossal, CH; Gobet, E.; Meziou, A.; Munos, R.; Reboul-Salze, D., Numerical methods for the pricing of Swing options: a stochastic control approach, Methodol. Comput. Appl. Probab., 8, 4, 517-540 (2006) · Zbl 1142.91502 · doi:10.1007/s11009-006-0427-8 |
| [3] | Bjerksund, P., Rasmussen, H., Stensland, G.: Valuation and risk management in the Norwegian electricity market. In: Bjørndal, E., Bjørndal, M., Pardalos, P., Rönnqvist, M. (Eds.) Energy, Natural Resources and Environmental Economics, pp. 167-185. Springer, Berlin (2010) |
| [4] | Bjerksund, P., Stensland, G., Vagstad, F.: Gas storage valuation: price modelling v. optimization methods. Energy J. 32(1), 203-227 (2011) |
| [5] | Boogert, A.; De Jong, C., Gas storage valuation using a Monte Carlo method, J Deriv., 15, 3, 81-98 (2008) · doi:10.3905/jod.2008.702507 |
| [6] | Boogert, A.; De Jong, C., Gas storage valuation using a multifactor price process, J Energy Mark, 4, 4, 29-52 (2011) · doi:10.21314/JEM.2011.067 |
| [7] | Buehler, H.; Gonon, L.; Teichmann, J.; Wood, B., Deep hedging, Quant. Finance, 19, 8, 1271-1291 (2019) · Zbl 1420.91450 · doi:10.1080/14697688.2019.1571683 |
| [8] | Carmona, R.; Ludkovski, M., Valuation of energy storage: an optimal switching approach, Quant. Finance, 10, 4, 359-374 (2010) · Zbl 1203.91286 · doi:10.1080/14697680902946514 |
| [9] | Cummins, M.; Kiely, G.; Murphy, B., Gas storage valuation under lévy processes using the fast Fourier transform, J. Energy Mark., 10, 4, 43-86 (2017) · doi:10.21314/JEM.2017.169 |
| [10] | Daluiso, R., Nastasi, E., Pallavicini, A., Sartorelli, G.: Pricing commodity swing options (2020) · Zbl 1447.91180 |
| [11] | De Jong, C., Gas storage valuation and optimization, J. Nat. Gas Sci. Eng., 24, 365-378 (2015) · doi:10.1016/j.jngse.2015.03.029 |
| [12] | Fiorenzani, S.; Ravelli, S.; Edoli, E., The Handbook of Energy Trading (2012), Hoboken: Wiley, Hoboken · doi:10.1002/9781118467275 |
| [13] | Geman, H., Commodities and Commodity Derivatives: Modeling and Pricing for Agricultural, Metals and Energy (2009), Hoboken: Wiley, Hoboken |
| [14] | Hénaff, P.; Laachir, I.; Russo, F., Gas storage valuation and hedging: a quantification of model risk, Int. J. Financ. Stud., 6, 1, 27 (2018) · doi:10.3390/ijfs6010027 |
| [15] | Holland, A.: Optimization of injection/withdrawal schedules for natural gas storage facilities. In: International Conference on Innovative Techniques and Applications of Artificial Intelligence, pp. 287-300. Springer (2007) |
| [16] | Holland, A.: A decision support tool for energy storage optimization. In: 2008 20th IEEE International Conference on Tools with Artificial Intelligence, vol. 2, pp. 299-306. IEEE (2008) |
| [17] | Jaillet, P.; Ronn, EI; Tompaidis, S., Valuation of commodity-based swing options, Manag. Sci., 50, 7, 909-921 (2004) · Zbl 1232.90340 · doi:10.1287/mnsc.1040.0240 |
| [18] | Makassikis, C., Vialle, S., Warin, X.: Distribution of a stochastic control algorithm applied to gas storage valuation. In: 2007 IEEE International Symposium on Signal Processing and Information Technology, pp. 485-490 (2007). doi:10.1109/ISSPIT.2007.4458002 |
| [19] | Malyscheff, AM; Trafalis, TB, Natural gas storage valuation via least squares Monte Carlo and support vector regression, Energy Syst., 8, 4, 815-855 (2017) · doi:10.1007/s12667-017-0239-7 |
| [20] | Safarov, N.; Atkinson, C., Natural gas storage valuation and optimization under time-inhomogeneous exponential lévy processes, Int. J. Comput. Math., 94, 11, 2147-2165 (2017) · Zbl 1394.35528 · doi:10.1080/00207160.2016.1168518 |
| [21] | Sutton, RS; Barto, AG, Reinforcement Learning: An Introduction (2018), Cambridge: MIT Press, Cambridge · Zbl 1407.68009 |
| [22] | Thompson, M., Natural gas storage valuation, optimization, market and credit risk management, J. Commod. Mark., 2, 1, 26-44 (2016) · doi:10.1016/j.jcomm.2016.07.004 |
| [23] | Thompson, M.; Davison, M.; Rasmussen, H., Natural gas storage valuation and optimization: a real options application, Naval Res. Logist. (NRL), 56, 3, 226-238 (2009) · Zbl 1158.90428 · doi:10.1002/nav.20327 |
| [24] | Warin, X.: Gas storage hedging. In: Breton, M., Ben-Ameur, H. (Eds.) Numerical Methods in Finance, pp. 421-445. Springer (2012) · Zbl 1247.91203 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
