Improving Non-Intrusive Load Disaggregation through an Attention-Based Deep Neural Network

TL;DR

This paper introduces an attention-based deep neural network for non-intrusive load disaggregation, significantly improving appliance power demand inference accuracy and detection of appliance state changes using public datasets.

Contribution

The paper presents a novel neural network architecture with a tailored attention mechanism that enhances generalization and detection capabilities in NILM tasks.

Findings

Outperforms state-of-the-art methods on REDD and UK-DALE datasets.

Attention mechanism improves detection of appliance on/off events.

Model accurately locates high power consumption segments.

Abstract

Energy disaggregation, known in the literature as Non-Intrusive Load Monitoring (NILM), is the task of inferring the power demand of the individual appliances given the aggregate power demand recorded by a single smart meter which monitors multiple appliances. In this paper, we propose a deep neural network that combines a regression subnetwork with a classification subnetwork for solving the NILM problem. Specifically, we improve the generalization capability of the overall architecture by including an encoder-decoder with a tailored attention mechanism in the regression subnetwork. The attention mechanism is inspired by the temporal attention that has been successfully applied in neural machine translation, text summarization, and speech recognition. The experiments conducted on two publicly available datasets--REDD and UK-DALE--show that our proposed deep neural network outperforms the state-of-the-art in all the considered experimental conditions. We also show that modeling attention translates into the network's ability to correctly detect the turning on or off an appliance and to locate signal sections with high power consumption, which are of extreme interest in the field of energy disaggregation.