A comparison of modern deep neural network architectures for energy spot price forecasting

F. Cordoni ()
Additional contact information
F. Cordoni: University of Verona

Digital Finance, 2020, vol. 2, issue 3, No 2, 189-210

Abstract: Abstract The present paper is devoted to a comparison of modern deep learning architecture to forecast day—ahead electricity spot prices. The analysis focus on performances of four different neural network, namely a multilayer perceptron (MLP), a convolutional neural network (CNN), a long-short time memory (LSTM) network and a stacked CNN-LSTM network. We briefly review state-of-the-art neural networks architectures, highlighting main differences between the proposed methods. We show how the implemented deep learning methods outperforms other machine learning algorithms typically used in energy prices forecasting such as random forest (RF) and lasso. We compare the forecasts with different metrics, analysing also how results change with respect to day of the week and hour of the day.

Keywords: Electricity spot prices forecasting; Deep learning; Neural networks; C22; C45; C53 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1007/s42521-020-00022-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:digfin:v:2:y:2020:i:3:d:10.1007_s42521-020-00022-2

Ordering information: This journal article can be ordered from
https://www.springer.com/finance/journal/42521

DOI: 10.1007/s42521-020-00022-2

Access Statistics for this article

Digital Finance is currently edited by Wolfgang Karl Härdle, Steven Kou and Min Dai

More articles in Digital Finance from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().