Prognosis of EPEX SPOT Electricity Prices Using Artificial Neural Networks

Johannes Hussak (), Stefanie Vogl, Ralph Grothmann and Merlind Weber
Additional contact information
Johannes Hussak: Technical University Munich
Stefanie Vogl: Siemens AG, Corporate Technology
Ralph Grothmann: Siemens AG, Corporate Technology
Merlind Weber: Technical University Munich

A chapter in Operations Research Proceedings 2017, 2018, pp 89-94 from Springer

Abstract: 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.

Keywords: Artificial neural networks; Deep learning; Forecasting; Bias correction (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:oprchp:978-3-319-89920-6_13

Ordering information: This item can be ordered from
http://www.springer.com/9783319899206

DOI: 10.1007/978-3-319-89920-6_13

Access Statistics for this chapter

More chapters in Operations Research Proceedings from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().