Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Trade-off between precision and resolution of a solar power forecasting algorithm for micro-grid optimal control

Abstract : With the development of micro-grids including PV production and storage, the need for efficient energy management strategies arises. One of their key components is the forecast of the energy production from very short to long term. The forecast time-step is an important parameter affecting not only its accuracy but also the optimal control time discretization, hence its efficiency and computational burden. To quantify this trade-off, four machine learning forecast models are tested on two geographical locations for time-steps varying from 2 to 60 min and horizons from 10 min to 6 h, on global irradiance horizontal and tilted when data was available. The results are similar for all the models and indicate that the error metric can be reduced up to 0.8% per minute on the time-step for forecasts below one hour and up to 1.7% per ten minutes for forecasts between one and six hours. In addition, it is shown that for short term horizons, it may be advantageous to forecast with a high resolution then average the results at the time-step needed by the energy management system.
Type de document :
Article dans une revue
Liste complète des métadonnées

https://hal-univ-corse.archives-ouvertes.fr/hal-03041890
Contributeur : Gilles Notton Connectez-vous pour contacter le contributeur
Soumis le : samedi 5 décembre 2020 - 16:45:29
Dernière modification le : jeudi 4 novembre 2021 - 03:08:11

Lien texte intégral

Identifiants

Collections

Citation

Jean Laurent Duchaud, Cyril Voyant, Gilles Notton, Alexis Fouilloy, Marie Laure Nivet. Trade-off between precision and resolution of a solar power forecasting algorithm for micro-grid optimal control. Energies, MDPI, 2020, 13 (14), pp.3565. ⟨10.3390/en13143565⟩. ⟨hal-03041890⟩

Partager

Métriques

Les métriques sont temporairement indisponibles