Signal Processing Implementation for Non-Intrusive Load Monitoring

Abstract

Non-intrusive load monitoring (NILM), or energy disaggregation, aims to estimate individual appliance consumption from a single-point measurement without using dedicated appliance-wise sensors or sub-meters. For around three decades, signal processing, machine learning algorithms, and statistical tools have been used by researchers to propose different approaches to the problem. However, there are still many challenges to achieving a universal approach that can be applied due to the particularities of the electrical distribution network and the electrical appliances of each country. In this paper, an approach for the NILM of residential electrical energy based on digital signal processing is presented. The experimental scenarios were carried out in Argentina where there was no public dataset for the conHouseHold appliancesumption of electrical appliances.