Reference : Privacy-preserving federated learning for residential short-term load forecasting
Scientific journals : Article
Engineering, computing & technology : Computer science
Engineering, computing & technology : Energy
Business & economic sciences : Management information systems
Security, Reliability and Trust
http://hdl.handle.net/10993/52125
Privacy-preserving federated learning for residential short-term load forecasting
English
[en] Volume 326, 15 November 2022, 119915
Delgado Fernandez, Joaquin mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
Potenciano Menci, Sergio mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
Lee, Chul Min [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
Rieger, Alexander mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
Fridgen, Gilbert mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
15-Nov-2022
Applied Energy
Elsevier
326
Yes
International
0306-2619
1872-9118
London
United Kingdom
[en] Deep neural networks ; Differential privacy ; Federated learning ; Secure aggregation ; Privacy-preserving federated learning ; Short-term load forecasting
[en] With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these forecasts as they provide detailed load data. However, using smart meter data for load forecasting is challenging due to data privacy requirements. This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation. For our analysis, we employ a large set of residential load data and simulate how different federated learning models and privacy preserving techniques affect performance and privacy. Our simulations reveal that combining federated learning and privacy preserving techniques can secure both high forecasting accuracy and near-complete privacy. Specifically, we find that such combinations enable a high level of information sharing while ensuring privacy of both the processed load data and forecasting models. Moreover, we identify and discuss challenges of applying federated learning, differential privacy and secure aggregation for residential short-term load forecasting.
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Digital Financial Services and Cross-organizational Digital Transformations (FINATRAX) ; University of Luxembourg: High Performance Computing - ULHPC
European Commission - EC
Medical Device Obligations Taskforce
Researchers
http://hdl.handle.net/10993/52125
10.1016/j.apenergy.2022.119915
https://www.sciencedirect.com/science/article/pii/S0306261922011722?via%3Dihub
H2020 ; 814654 - MDOT - Medical Device Obligations Taskforce
FnR ; FNR13342933 > Gilbert Fridgen > DFS > Paypal-fnr Pearl Chair In Digital Financial Services > 01/01/2020 > 31/12/2024 > 2019

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
1-s2.0-S0306261922011722-main.pdfPublisher postprint1.15 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.