Reference : Privacy-preserving federated learning for residential short-term load forecasting

	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Computer science Engineering, computing & technology : Energy Business & economic sciences : Management information systems
	Focus Areas :	Security, Reliability and Trust
	To cite this reference:	http://hdl.handle.net/10993/52125

Title :	Privacy-preserving federated learning for residential short-term load forecasting
Language :	English
Translated title :	[en] Volume 326, 15 November 2022, 119915
Author, co-author :	Delgado Fernandez, Joaquin [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
	Potenciano Menci, Sergio [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 [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
	Fridgen, Gilbert [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX >]
Publication date :	15-Nov-2022
Journal title :	Applied Energy
Publisher :	Elsevier
Volume :	326
Peer reviewed :	Yes
Audience :	International
ISSN :	0306-2619
e-ISSN :	1872-9118
City :	London
Country :	United Kingdom
Keywords :	[en] Deep neural networks ; Differential privacy ; Federated learning ; Secure aggregation ; Privacy-preserving federated learning ; Short-term load forecasting
Abstract :	[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.
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Digital Financial Services and Cross-organizational Digital Transformations (FINATRAX) ; University of Luxembourg: High Performance Computing - ULHPC
Funders :	European Commission - EC
Name of the research project :	Medical Device Obligations Taskforce
Target :	Researchers
Permalink :	http://hdl.handle.net/10993/52125
DOI :	10.1016/j.apenergy.2022.119915
Other URL :	https://www.sciencedirect.com/science/article/pii/S0306261922011722?via%3Dihub
Framework Programme / European Project :	H2020 ; 814654 - MDOT - Medical Device Obligations Taskforce
FnR project :	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): File Commentary Version Size Access Open access 1-s2.0-S0306261922011722-main.pdf Publisher postprint 1.15 MB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map