Communication Dans Un Congrès Année : 2025

Unlock Data Sharing in Wind Power Forecasting through Privacy-preserving Federated-Learning: Benchmarking of Mixed and Fully Encrypted Frameworks

Résumé

Federated learning is a technology enabling the privacy-preserving sharing of spatio-temporal data. Most works are only evaluated on a small-scale dataset. We analyse the scaling of a previous model developed by us. Showing that the idea of mixed encryption is able to allow efficient scaling and address this issue.

Fichier principal
Vignette du fichier
9010+STIPPEL++regular+2025-02-01+10-54-05.pdf (160.36 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05135678 , version 1 (30-06-2025)

Licence

Identifiants

  • HAL Id : hal-05135678 , version 1

Citer

Lukas Stippel, Simon Camal, Georges Kariniotakis. Unlock Data Sharing in Wind Power Forecasting through Privacy-preserving Federated-Learning: Benchmarking of Mixed and Fully Encrypted Frameworks. Wind Energy Science Conference 2025 - WESC2025, European Academy of Wind Energy - EAWE, Jun 2025, Nantes, France. ⟨hal-05135678⟩
636 Consultations
178 Téléchargements

Partager

  • More