Sparse mixture of experts enhanced transformer architecture for short-term hydroelectric reservoir volume prediction.
Saved in:
| Title: | Sparse mixture of experts enhanced transformer architecture for short-term hydroelectric reservoir volume prediction. |
|---|---|
| Authors: | Seman, Laio Oriel1 (AUTHOR) laio.seman@ufsc.br, Yow, Kin-Choong2 (AUTHOR) Kin-Choong.Yow@uregina.ca, Stefenon, Stefano Frizzo2,3 (AUTHOR) stefano.stefefenon@isel.br |
| Source: | Electric Power Systems Research. Jun2026, Vol. 255, pN.PAG-N.PAG. 1p. |
| Subjects: | Transformer models, Forecasting, Deep learning, Electric power system planning, Ensemble learning, Wavelet transforms |
| Geographic Terms: | Brazil |
| Abstract: | • Hybrid Transformer with sparse Mixture of Experts for reservoir forecasting. • Adaptive multi-head preprocessing captures nonstationary temporal patterns. • Empirical Wavelet Transform improves denoising and short-term accuracy. • Tested on 19 interconnected reservoirs using real operational data. • Outperforms 18 state-of-the-art models with lower prediction error. In hydroelectric-based systems, effective energy generation planning relies heavily on precise forecasting of reservoir water levels. This paper proposes a novel hybrid forecasting framework that integrates multiple preprocessing strategies with a sparse Mixture of Experts enhanced Transformer architecture for short-term reservoir volume prediction. When evaluated on 19 interconnected reservoirs across two major river basins in southern Brazil using real operational data from the Brazilian National System Operator, the proposed model achieves a mean squared error of 0.062 and a mean absolute error of 0.145. Comprehensive benchmarking against 18 state-of-the-art deep learning methods demonstrates that the proposed approach significantly outperforms existing methods while maintaining computational efficiency through sparse expert routing. Our results confirm that combining diverse preprocessing strategies with conditional computation mechanisms provides superior forecasting accuracy for reservoir management in hydroelectric power systems. [ABSTRACT FROM AUTHOR] |
| Copyright of Electric Power Systems Research is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191760353 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Sparse mixture of experts enhanced transformer architecture for short-term hydroelectric reservoir volume prediction. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Seman%2C+Laio+Oriel%22">Seman, Laio Oriel</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> laio.seman@ufsc.br</i><br /><searchLink fieldCode="AR" term="%22Yow%2C+Kin-Choong%22">Yow, Kin-Choong</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> Kin-Choong.Yow@uregina.ca</i><br /><searchLink fieldCode="AR" term="%22Stefenon%2C+Stefano+Frizzo%22">Stefenon, Stefano Frizzo</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> stefano.stefefenon@isel.br</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Electric+Power+Systems+Research%22">Electric Power Systems Research</searchLink>. Jun2026, Vol. 255, pN.PAG-N.PAG. 1p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Forecasting%22">Forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Electric+power+system+planning%22">Electric power system planning</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Wavelet+transforms%22">Wavelet transforms</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Brazil%22">Brazil</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: • Hybrid Transformer with sparse Mixture of Experts for reservoir forecasting. • Adaptive multi-head preprocessing captures nonstationary temporal patterns. • Empirical Wavelet Transform improves denoising and short-term accuracy. • Tested on 19 interconnected reservoirs using real operational data. • Outperforms 18 state-of-the-art models with lower prediction error. In hydroelectric-based systems, effective energy generation planning relies heavily on precise forecasting of reservoir water levels. This paper proposes a novel hybrid forecasting framework that integrates multiple preprocessing strategies with a sparse Mixture of Experts enhanced Transformer architecture for short-term reservoir volume prediction. When evaluated on 19 interconnected reservoirs across two major river basins in southern Brazil using real operational data from the Brazilian National System Operator, the proposed model achieves a mean squared error of 0.062 and a mean absolute error of 0.145. Comprehensive benchmarking against 18 state-of-the-art deep learning methods demonstrates that the proposed approach significantly outperforms existing methods while maintaining computational efficiency through sparse expert routing. Our results confirm that combining diverse preprocessing strategies with conditional computation mechanisms provides superior forecasting accuracy for reservoir management in hydroelectric power systems. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Electric Power Systems Research is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191760353 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.epsr.2026.112754 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: N.PAG Subjects: – SubjectFull: Transformer models Type: general – SubjectFull: Forecasting Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Electric power system planning Type: general – SubjectFull: Ensemble learning Type: general – SubjectFull: Wavelet transforms Type: general – SubjectFull: Brazil Type: general Titles: – TitleFull: Sparse mixture of experts enhanced transformer architecture for short-term hydroelectric reservoir volume prediction. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Seman, Laio Oriel – PersonEntity: Name: NameFull: Yow, Kin-Choong – PersonEntity: Name: NameFull: Stefenon, Stefano Frizzo IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 03787796 Numbering: – Type: volume Value: 255 Titles: – TitleFull: Electric Power Systems Research Type: main |
| ResultId | 1 |
