Privacy Preserving Federated Learning for Energy Disaggregation of Smart Homes

Guardat en:
Dades bibliogràfiques
Publicat a:IET Cyber-Physical Systems : Theory & Applications vol. 10, no. 1 (Jan/Dec 2025)
Autor principal: Ali, Mazhar
Altres autors: Kumar, Ajit, Choi, Bong Jun
Publicat:
John Wiley & Sons, Inc.
Matèries:
Accés en línia:Citation/Abstract
Full Text
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3217514519
003 UK-CbPIL
022 |a 2398-3396 
024 7 |a 10.1049/cps2.70013  |2 doi 
035 |a 3217514519 
045 2 |b d20250101  |b d20251231 
100 1 |a Ali, Mazhar  |u School of Computer Science and Engineering, Soongsil University, Seoul, Korea 
245 1 |a Privacy Preserving Federated Learning for Energy Disaggregation of Smart Homes 
260 |b John Wiley & Sons, Inc.  |c Jan/Dec 2025 
513 |a Journal Article 
520 3 |a ABSTRACT Smart advanced metering infrastructure and edge devices show promising solutions in digitalising distributed energy systems. Energy disaggregation of household load consumption provides a better understanding of consumers’ appliance‐level usage patterns. Machine learning approaches enhance the power system's efficiency but this is contingent upon sufficient training samples for efficient and accurate prediction tasks. In a centralised setup, transferring such a substantially high volume of information to the cloud server has a communication bottleneck. Although high‐computing edge devices seek to address such problems, the data scarcity and heterogeneity among clients remain challenges to be addressed. Federated learning offers a compelling solution in such a scenario by leveraging the ML model training at edge devices and aggregating the client's updates at a cloud server. However, FL still faces significant security issues, including the potential eavesdropping by a malicious actor with the intention of stealing clients' information while communicating with an honest‐but‐curious server. The study aims to secure the sensitive information of energy users participating in the nonintrusive load monitoring (NILM) program by integrating differential privacy with a personalised federated learning approach. The Fisher information method was adapted to extract the global model information based on common features, while personalised updates will not be shared with the server for client‐specific features. Similarly, the authors employed an adaptive differential privacy only on the shared local updates (DP‐PFL) while communicating with the server. Experimental results on the Pecan Street and REFIT datasets depict that DP‐PFL exhibits more favourable performance on both the energy prediction and status classification tasks compared to other state‐of‐the‐art DP approaches in federated NILM. 
651 4 |a United Kingdom--UK 
653 |a Collaboration 
653 |a Deep learning 
653 |a Datasets 
653 |a Advanced metering infrastructure 
653 |a Communication 
653 |a Smart buildings 
653 |a Privacy 
653 |a Machine learning 
653 |a Energy consumption 
653 |a Customization 
653 |a Heterogeneity 
653 |a Use statistics 
653 |a Residential energy 
653 |a Appliances 
653 |a Consumers 
653 |a Servers 
653 |a Edge computing 
653 |a Energy industry 
653 |a Cloud computing 
653 |a Neural networks 
653 |a Fisher information 
653 |a Clients 
653 |a Federated learning 
653 |a Digitization 
653 |a Households 
700 1 |a Kumar, Ajit  |u School of Computer Science and Engineering, Soongsil University, Seoul, Korea 
700 1 |a Choi, Bong Jun  |u School of Computer Science and Engineering, Soongsil University, Seoul, Korea 
773 0 |t IET Cyber-Physical Systems : Theory & Applications  |g vol. 10, no. 1 (Jan/Dec 2025) 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3217514519/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3217514519/fulltext/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3217514519/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch