FedNILM: Applying Federated Learning to NILM Applications at the Edge

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.

Automated summary

Non-intrusive load monitoring (NILM) disaggregates a household's main electricity consumption to individual appliance usages, reducing the cost of load monitoring and promoting green homes. Federated learning (FL) can address the privacy concern in NILM applications, but faces challenges of edge resource restriction, model personalization, and training data scarcity. We propose FedNILM, a FL paradigm for edge clients, which utilizes collaborative data aggregation, cloud model compression, and personalized edge model building to provide privacy-preserving and personalized NILM services. Experiments on real-world energy data demonstrate that FedNILM achieves accurate personalized energy disaggregation while protecting user privacy.