Watt’s mext? Benchmarking Time Series Models on Romania’s National Electricity Consumption

Cosmin Adrian Proșcanu (), Miruna Elena Proșcanu (), Daniel Traian Pele () and Adrian Costea ()
Additional contact information
Cosmin Adrian Proșcanu: Bucharest University of Economic Studies, Romania, Corresponding author
Miruna Elena Proșcanu: Bucharest University of Economic Studies, Romania
Daniel Traian Pele: Bucharest University of Economic Studies, Romania. Institute for Economic Forecasting, Romanian Academy, Romania
Adrian Costea: Bucharest University of Economic Studies, Romania, adrian.costea@csie.ase.ro

Journal for Economic Forecasting, 2025, issue 3, 146-163

Abstract: Time series forecasting remains a critical area of research across multiple disciplines, particularly in energy demand prediction. Over time, models have evolved from traditional statistical techniques to advanced neural and transformer-based architectures. This study presents a comprehensive benchmarking of univariate forecasting models, ranging from classical approaches such as SARIMA to cutting-edge architectures like Google's Titans. The dataset, representing Romania's national electricity consumption, was compiled from official sources to ensure accuracy and reliability. Model performance is evaluated using multiple error metrics. The results indicate that modern neural models—specifically N-BEATS and Titans—consistently outperform traditional methods. This study aims to provide practical guidance for selecting appropriate forecasting tools to support data-driven decision-making in Romania's energy sector.

Keywords: Energy Load Forecast; Neural Networks; Time Series; Large Language Models; Foundational Models (search for similar items in EconPapers)
JEL-codes: C45 C52 C53 Q41 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ipe.ro/ftp/RePEc/rjef3_2025/rjef3_2025p146-163.pdf

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:rjr:romjef:v::y:2025:i:3:p:146-163

Access Statistics for this article

Journal for Economic Forecasting is currently edited by Lucian Liviu Albu and Corina Saman

More articles in Journal for Economic Forecasting from Institute for Economic Forecasting Contact information at EDIRC.
Bibliographic data for series maintained by Corina Saman ( this e-mail address is bad, please contact ).