Abstract
The rising shares of volatile renewable energy supply in the European electricity markets lead to an increased relevance for short-term trading at the EPEX SPOT. In this paper, we propose a holistic modeling approach for a robust prediction of EPEX SPOT day-ahead prices for the bidding zone Germany, Austria and Luxembourg applying three-layer and deep neural networks. In the first step, we describe, why neural networks are well suited for econometric modeling tasks. In the modeling part, we distinguish an optimal set of meta-parameters and then gradually adjust the final model setup. Lastly, we further improve the performance accuracy by applying a quantile-based scaling process. Thus, we obtain accurate and robust predictions even for sharp price peaks in rare events.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
SE, E.S. (2017). Facts and figures. Technical report, EPEX SPOT SE (2017). https://www.epexspot.com/document/36931/2017-01_EPEX_SPOT_Facts.
Aggarwal, S. K., Saini, L. M., & Kumar, A. (2009). Electricity price forecasting in deregulated markets: A review and evaluation. International Journal of Electrical Power & Energy Systems, 31(1), 13–22. https://doi.org/10.1016/j.ijepes.2008.09.003.
Zimmermann, H. & Neuneier, R. (2000). Modeling dynamical systems by recurrent neural networks. Data Mining 2. https://www.witpress.com/Secure/elibrary/papers/DATA00/DATA00054FU.pdf.
Bengio, Y. (2009). Learning deep architectures for ai. Foundations and Trends in Machine Learning, 2(1), 1–127. https://doi.org/10.1561/2200000006. https://www.iro.umontreal.ca/~bengioy/papers/ftml.pdf.
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8.
Zimmermann, H. G. (2016). Analysis of complex dynamical systems with neural networks. https://indico.cern.ch/event/561247/attachments/1382489/2102391/ZimmermannCERN1.pdf.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Hussak, J., Vogl, S., Grothmann, R., Weber, M. (2018). Prognosis of EPEX SPOT Electricity Prices Using Artificial Neural Networks. In: Kliewer, N., Ehmke, J., Borndörfer, R. (eds) Operations Research Proceedings 2017. Operations Research Proceedings. Springer, Cham. https://doi.org/10.1007/978-3-319-89920-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-89920-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-89919-0
Online ISBN: 978-3-319-89920-6
eBook Packages: Business and ManagementBusiness and Management (R0)