Energy Disaggregation using Variational Autoencoders

TL;DR

This paper introduces a variational autoencoder-based method for non-intrusive load monitoring that improves energy disaggregation accuracy and generalization across different houses, especially for multi-state appliances.

Contribution

It proposes a novel VAE framework that enhances load profile modeling and cross-house generalization in NILM systems.

Findings

18% reduction in mean absolute error on average

Over 11% increase in F1-Score for appliance detection

Competitive results on UK-DALE and REFIT datasets

Abstract

Non-intrusive load monitoring (NILM) is a technique that uses a single sensor to measure the total power consumption of a building. Using an energy disaggregation method, the consumption of individual appliances can be estimated from the aggregate measurement. Recent disaggregation algorithms have significantly improved the performance of NILM systems. However, the generalization capability of these methods to different houses as well as the disaggregation of multi-state appliances are still major challenges. In this paper we address these issues and propose an energy disaggregation approach based on the variational autoencoders framework. The probabilistic encoder makes this approach an efficient model for encoding information relevant to the reconstruction of the target appliance consumption. In particular, the proposed model accurately generates more complex load profiles, thus improving the power signal reconstruction of multi-state appliances. Moreover, its regularized latent space improves the generalization capabilities of the model across different houses. The proposed model is compared to state-of-the-art NILM approaches on the UK-DALE and REFIT datasets, and yields competitive results. The mean absolute error reduces by 18% on average across all appliances compared to the state-of-the-art. The F1-Score increases by more than 11%, showing improvements for the detection of the target appliance in the aggregate measurement.