Accéder directement au contenu Accéder directement à la navigation
Pré-publication, Document de travail

Machine learning for assessing variability of the long-term projections of the hydropower generation on a European scale

Abstract : A big challenge of sustainable power systems is the integration of climate variability into the operational and long-term planning processes. In this paper, we focus on the run-of-river based hydropower generation on a European scale. In particular, we deal with the modeling of this form of power production based on climate variables. Translating time series of climate data (precipitation and air temperature) into time series of run-of-river based hydropower generation is not an easy task as it is necessary to capture the complex relationship between the availability of water and the generation of electricity. Indeed, this kind of electricity generation is limited by the flow of the river in which the power plants are located. Moreover, the water flow is a nonlinear function of the climate variables and the geographical characteristics of the river basins. Finally, the impact of the climate variables on the runoff may occur with a certain delay, whose determination depends on physically based phenomena (e.g., melting snow-local temperature). In this work, we first compare well-established machine learning regression algorithms to be used for modeling the run-of-river hydropower generation. Then, the technique showing to have the best performance is used for producing long-term estimates of hydropower capacity factors based on future climate scenarios for each European country.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal-mines-paristech.archives-ouvertes.fr/hal-02507400
Contributeur : Valentina Sessa <>
Soumis le : vendredi 13 mars 2020 - 10:23:52
Dernière modification le : jeudi 8 octobre 2020 - 16:28:06
Archivage à long terme le : : dimanche 14 juin 2020 - 13:17:40

Fichier

2020_applied_energy_draft_HAL....
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02507400, version 1

Citation

Valentina Sessa, Edi Assoumou, Mireille Bossy, Sílvia Carvalho, Sofia Simoes. Machine learning for assessing variability of the long-term projections of the hydropower generation on a European scale. 2020. ⟨hal-02507400⟩

Partager

Métriques

Consultations de la notice

79

Téléchargements de fichiers

85