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.

I. Introduction

Non-intrusive load monitoring, also known as energy disaggregation, was first introduced by Gorge W. Hart in 1980s [1]. By nature it is a single-channel blind source separation (BSS) problem that aims to decompose the aggregated power readings of a household into appliance-wise power consumption. One of the major purposes of NILM is to reduce energy consumption efficiently and pursue the green home vision. Evidences have shown that the itemized information could encourage householders to use energy in a more sustainable way, achieving about 15% energy saving [2], [3]. Besides, NILM can be leveraged to evaluate conservation programs, improve the quality of load forecasting, and provide references for power grid management [4]. For example, with real-time NILM, utility companies could suggest switching operations on particular appliances (e.g., air conditioners) for load shifting in peak power hours [3].