Transfer Learning for Day-Ahead Load Forecasting: A Case Study on European National Electricity Demand Time Series

Alexandros Menelaos Tzortzis (), Sotiris Pelekis, Evangelos Spiliotis, Evangelos Karakolis, Spiros Mouzakitis, John Psarras and Dimitris Askounis
Additional contact information
Alexandros Menelaos Tzortzis: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
Sotiris Pelekis: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
Evangelos Spiliotis: Forecasting and Strategy Unit, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
Evangelos Karakolis: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
Spiros Mouzakitis: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
John Psarras: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece
Dimitris Askounis: Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 157 72 Athens, Greece

Mathematics, 2023, vol. 12, issue 1, 1-24

Abstract: Short-term load forecasting (STLF) is crucial for the daily operation of power grids. However, the non-linearity, non-stationarity, and randomness characterizing electricity demand time series renders STLF a challenging task. Various forecasting approaches have been proposed for improving STLF, including neural network (NN) models which are trained using data from multiple electricity demand series that may not necessarily include the target series. In the present study, we investigate the performance of a special case of STLF, namely transfer learning (TL), by considering a set of 27 time series that represent the national day-ahead electricity demand of indicative European countries. We employ a popular and easy-to-implement feed-forward NN model and perform a clustering analysis to identify similar patterns among the load series and enhance TL. In this context, two different TL approaches, with and without the clustering step, are compiled and compared against each other as well as a typical NN training setup. Our results demonstrate that TL can outperform the conventional approach, especially when clustering techniques are considered.

Keywords: short-term load forecasting; multi-layer perceptron; national energy demand; deep learning; transfer learning; time series forecasting; ensembling (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/1/19/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/1/19/ (text/html)

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:gam:jmathe:v:12:y:2023:i:1:p:19-:d:1304656

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().