• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Scopus
  4. Short- and long-term forecasting of electricity prices using embedding of calendar information in neural networks
 
  • Details
  • Full
Options
2022
Journal Article
Titel

Short- and long-term forecasting of electricity prices using embedding of calendar information in neural networks

Abstract
Electricity prices strongly depend on seasonality of different time scales, therefore any forecasting of electricity prices has to account for it. Neural networks have proven successful in short-term price-forecasting, but complicated architectures like LSTM are used to integrate the seasonal behavior. This paper shows that simple neural network architectures like DNNs with an embedding layer for seasonality information can generate a competitive forecast. The embedding-based processing of calendar information additionally opens up new applications for neural networks in electricity trading, such as the generation of price forward curves. Besides the theoretical foundation, this paper also provides an empirical multi-year study on the German electricity market for both applications and derives economical insights from the embedding layer. The study shows that in short-term price-forecasting the mean absolute error of the proposed neural networks with an embedding layer is better than the LSTM and time-series benchmark models and even slightly better as our best benchmark model with a sophisticated hyperparameter optimization. The results aresupported by a statistical analysis using Friedman and Holm's tests.
Author(s)
Wagner, Andreas
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Ramentol Martinez, Enislay
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Schirra, Florian
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Michaeli, H.
Hochschule Karlsruhe - Technik und Wirtschaft
Zeitschrift
Journal of commodity markets
Project(s)
FlexEuro: Wirtschaftliche Optimierung flexibler stromintensiver Industrieprozesse
ENets: Modellierung und Steuerung zukünftiger Energienetze
Funder
Bundesministerium für Wirtschaft und Energie -BMWI-
Bundesministerium für Bildung und Forschung -BMBF-
Thumbnail Image
DOI
10.1016/j.jcomm.2022.100246
Language
English
google-scholar
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Tags
  • Machine learning

  • Neural networks

  • Embedding

  • Electricity market

  • Spot price

  • Forecasting

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022