An Intra-Day Electricity Price Forecasting Based on a Probabilistic Transformer Neural Network Architecture

Celeita Rodriguez, David Felipe

doi:http://doi.org/10.3390/en16196767

Ítem

Acceso Abierto

An Intra-Day Electricity Price Forecasting Based on a Probabilistic Transformer Neural Network Architecture

Mostrar el registro sencillo de la publicación

dc.creator	Celeita Rodriguez, David Felipe	spa
dc.date.accessioned	2024-01-31T18:34:49Z
dc.date.available	2024-01-31T18:34:49Z
dc.date.created	2023-10-01	spa
dc.date.issued	2023	spa
dc.description	This paper describes the development of a deep neural network architecture based on transformer encoder blocks and Time2Vec layers for the prediction of electricity prices several steps ahead (8 h), from a probabilistic approach, to feed future decision-making tools in the context of the widespread use of intra-day DERs and new market perspectives. The proposed model was tested with hourly wholesale electricity price data from Colombia, and the results were compared with different state-of-the-art forecasting baseline-tuned models such as Holt–Winters, XGBoost, Stacked LSTM, and Attention-LSTM. The findings show that the proposed model outperforms these baselines by effectively incorporating nonlinearity and explicitly modeling the underlying data’s behavior, all of this under four operating scenarios and different performance metrics. This allows it to handle high-, medium-, and low-variability scenarios while maintaining the accuracy and reliability of its predictions. The proposed framework shows potential for significantly improving the accuracy of electricity price forecasts, which can have significant benefits for making informed decisions in the energy sector.	spa
dc.format.mimetype	application/pdf	spa
dc.identifier.doi	http://doi.org/10.3390/en16196767	spa
dc.identifier.issn	1996-1073	spa
dc.identifier.uri	https://repository.urosario.edu.co/handle/10336/42168
dc.language.iso	eng	spa
dc.publisher	Universidad del Rosario	spa
dc.relation.uri	https://www.mdpi.com/1996-1073/16/19/6767	spa
dc.rights	Attribution-NonCommercial-ShareAlike 4.0 International	spa
dc.rights.accesRights	info:eu-repo/semantics/openAccess	spa
dc.rights.acceso	Abierto (Texto Completo)	spa
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/	spa
dc.source	Energies	spa
dc.source.instname	instname:Universidad del Rosario	spa
dc.source.reponame	reponame:Repositorio Institucional EdocUR	spa
dc.subject	Decision making	spa
dc.subject	Deep learning	spa
dc.subject	Electricity price forecasting (EPF)	spa
dc.subject	Probabilistic forecasting	spa
dc.subject	Time series forecasting	spa
dc.title	An Intra-Day Electricity Price Forecasting Based on a Probabilistic Transformer Neural Network Architecture	spa
dc.type	article	spa
dc.type.hasVersion	info:eu-repo/semantics/publishedVersion	spa
dc.type.spa	Artículo	spa