FederatedNILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring based on Federated Deep Learning

TL;DR

FederatedNILM introduces a privacy-preserving federated deep learning framework for non-intrusive load monitoring, enabling appliance-level energy disaggregation without compromising user data privacy.

Contribution

It is the first to combine federated learning with deep neural networks specifically for NILM, addressing privacy concerns in real-world applications.

Findings

FederatedNILM achieves comparable accuracy to centralized models.

The framework effectively preserves user privacy during appliance classification.

Extensive experiments validate its practicality and robustness.

Abstract

Non-intrusive load monitoring (NILM), which usually utilizes machine learning methods and is effective in disaggregating smart meter readings from the household-level into appliance-level consumptions, can help to analyze electricity consumption behaviours of users and enable practical smart energy and smart grid applications. However, smart meters are privately owned and distributed, which make real-world applications of NILM challenging. To this end, this paper develops a distributed and privacy-preserving federated deep learning framework for NILM (FederatedNILM), which combines federated learning with a state-of-the-art deep learning architecture to conduct NILM for the classification of typical states of household appliances. Through extensive comparative experiments, the effectiveness of the proposed FederatedNILM framework is demonstrated.