Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements

TL;DR

This paper introduces a neural network ensemble method for real-time appliance identification using high-resolution electrical measurements, eliminating the need for engineered signatures and demonstrating robustness across various conditions.

Contribution

The study presents a novel neural network ensemble approach trained on raw waveforms for appliance identification, reducing reliance on engineered features and improving robustness.

Findings

Effective identification of appliances from raw waveform data.

Model stability across different datasets and operational variations.

High accuracy achieved on a large residential dataset.

Abstract

The problem of identifying end-use electrical appliances from their individual consumption profiles, known as the appliance identification problem, is a primary stage in both Non-Intrusive Load Monitoring (NILM) and automated plug-wise metering. Therefore, appliance identification has received dedicated studies with various electric appliance signatures, classification models, and evaluation datasets. In this paper, we propose a neural network ensembles approach to address this problem using high resolution measurements. The models are trained on the raw current and voltage waveforms, and thus, eliminating the need for well engineered appliance signatures. We evaluate the proposed model on a publicly available appliance dataset from 55 residential buildings, 11 appliance categories, and over 1000 measurements. We further study the stability of the trained models with respect to training dataset, sampling frequency, and variations in the steady-state operation of appliances.