Publicação
Optimized wavelet-denoised temporal convolutional network for multi-step ahead predictions in power systems
| authorProfile.email | biblioteca@isel.pt | |
| datacite.subject.fos | Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática | |
| dc.contributor.author | Buratto, William Gouvea | |
| dc.contributor.author | Gonzalez, Gabriel Villarrubia | |
| dc.contributor.author | Yamaguchi, Cristina Keiko | |
| dc.contributor.author | Nied, Ademir | |
| dc.contributor.author | Yow, Kin-Choong | |
| dc.contributor.author | Stefenon, Stefano Frizzo | |
| dc.date.accessioned | 2026-10-16T12:57:56Z | |
| dc.date.available | 2026-10-16T12:57:56Z | |
| dc.date.issued | 2026-08-17 | |
| dc.description.abstract | Accurate forecasting of power generation is essential for ensuring the reliable and cost-efficient operation of modern electrical grids. This paper introduces an optimized wavelet temporal convolutional network (TCN) designed for multi-step-ahead prediction of thermal power generation in Brazil. The proposed model, called optimized-wavelet-TCN, integrates a discrete wavelet transform denoising stage to effectively filter high-frequency noise from operational data while preserving underlying signal trends, followed by a TCN optimized via a tree-structured Parzen estimator for hyperparameter tuning. Evaluated on real-world hourly data spanning multiple years, the optimized-wavelet-TCN achieves superior forecasting performance with a mean absolute percentage error of 10.2%, 7.24%, and 8.54% for 15, 30, and 60-step ahead predictions, respectively. The model significantly reduces computational time to only 1.54 s for a 30-step forecast, markedly outperforming state-of-the-art transformer-based and recurrent neural network baselines in both accuracy and efficiency. | eng |
| dc.identifier.citation | Buratto, W. G., Gonzalez, G. V., Yamaguchi, C. K., Nied, A., Yow, K. C., & Stefenon, S. F. (2026). Optimized wavelet-denoised temporal convolutional network for multi-step ahead predictions in power systems. IET Generation Transmission & Distribution, 20(1), 1-16. https://doi.org/10.1049/gtd2.70398 | |
| dc.identifier.doi | 10.1049/gtd2.70398 | |
| dc.identifier.eissn | 1751-8695 | |
| dc.identifier.issn | 1751-8687 | |
| dc.identifier.uri | http://hdl.handle.net/10400.21/23228 | |
| dc.language.iso | eng | |
| dc.peerreviewed | yes | |
| dc.publisher | Willey | |
| dc.relation.hasversion | https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/gtd2.70398 | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | Demand forecasting | |
| dc.subject | Discrete wavelet transforms | |
| dc.subject | Time series | |
| dc.subject | Generation | |
| dc.title | Optimized wavelet-denoised temporal convolutional network for multi-step ahead predictions in power systems | eng |
| dc.type | research article | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 16 | |
| oaire.citation.issue | 1 | |
| oaire.citation.startPage | 1 | |
| oaire.citation.title | IET Generation Transmission & Distribution | |
| oaire.citation.volume | 20 | |
| oaire.version | http://purl.org/coar/version/c_be7fb7dd8ff6fe43 | |
| person.affiliation.name | Instituto Politécnico de Lisboa, Instituto Superior de Engenharia de Lisboa | |
| person.familyName | Stefenon | |
| person.givenName | Stefano Frizzo | |
| person.identifier.orcid | https://orcid.org/0000-0002-3723-616X | |
| relation.isAuthorOfPublication | b0383f14-261a-42cf-a223-7c571c84a241 | |
| relation.isAuthorOfPublication.latestForDiscovery | b0383f14-261a-42cf-a223-7c571c84a241 |