FedNILM: Applying Federated Learning to NILM Applications at the Edge

Zhang，Yu1; Tang，Guoming2; Huang，Qianyi3; Wang，Yi4; Wu，Kui5; Yu，Keping6; Shao，Xun7

2022

10.1109/TGCN.2022.3167392

IEEE Transactions on Green Communications and Networking   影响因子和分区

2473-2400

Non-intrusive load monitoring (NILM) helps disaggregate a household's main electricity consumption to energy usages of individual appliances, greatly cutting down the cost of fine-grained load monitoring towards the green home vision. To address the privacy concern in NILM applications, federated learning (FL) could be leveraged for NILM model training and sharing. When applying the FL paradigm in real-world NILM applications, however, we are faced with the challenges of edge resource restriction, edge model personalization, and edge training data scarcity. We present FedNILM, a practical FL paradigm for NILM applications at the edge client. Specifically, FedNILM delivers privacy-preserving and personalized NILM services to large-scale edge clients, by leveraging i) collaborative data aggregation through federated learning, ii) efficient cloud model compression via filter pruning and multi-task learning, and iii) personalized edge model building with unsupervised transfer learning. Our experiments on real-world energy data show that FedNILM can achieve personalized energy disaggregation with the state-of-the-art accuracy, while preserving the user privacy.

Non-intrusive load monitoring green home federated learning model compression transfer learning.

EI ; SCI

英语

其他

National Key Research and Development Program of China[2020YFB1806400] ; National Natural Science Foundation of China[62002150] ; Peng Cheng Laboratory The Major Key Project of PCL[PCL2021A08] ; Guangdong Basic and Applied Basic Research Foundation[2019B1515120031]

Telecommunications

Telecommunications

WOS:001009931100023

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20221611994228

Electric load management ; Learning systems

Electric Power Systems:706.1 ; Telecommunication; Radar, Radio and Television:716 ; Telephone Systems and Related Technologies; Line Communications:718 ; Data Processing and Image Processing:723.2

IEEE

1.Chinese University of Hong Kong, Hong Kong, China
2.Peng Cheng Laboratory, Shenzhen, Guangdong, China
3.Southern University of Science and Technology, Shenzhen Guangdong, China, and Peng Cheng Laboratory, Shenzhen, Guangdong, China
4.Southern University of Science and Technology, Shenzhen Guangdong, China, Peng Cheng Laboratory, Shenzhen, Guangdong, China, and Heyuan Bay Area Digital Economy Technology Innovation Center, Heyuan, Guangdong, China
5.Department of Computer Science, University of Victoria, Victoria, BC, Canada
6.Global Information and Telecommunication Institute, Waseda University, Shinjuku, Tokyo, Japan
7.School of Regional Innovation and Social Design Engineering, Kitami Institute of Technology, Kitami, Japan

Zhang，Yu,Tang，Guoming,Huang，Qianyi,et al. FedNILM: Applying Federated Learning to NILM Applications at the Edge[J]. IEEE Transactions on Green Communications and Networking,2022,PP(99):1-1.

Zhang，Yu.,Tang，Guoming.,Huang，Qianyi.,Wang，Yi.,Wu，Kui.,...&Shao，Xun.(2022).FedNILM: Applying Federated Learning to NILM Applications at the Edge.IEEE Transactions on Green Communications and Networking,PP(99),1-1.

Zhang，Yu,et al."FedNILM: Applying Federated Learning to NILM Applications at the Edge".IEEE Transactions on Green Communications and Networking PP.99(2022):1-1.