Non-Intrusive Load Monitoring (NILM) using Deep Neural Networks: A Review

TL;DR

This review paper discusses recent deep learning-based NILM methods, highlighting the most accurate approaches for residential load disaggregation, and compares their performance using standard metrics and public datasets.

Contribution

It provides a comprehensive overview of recent deep learning techniques for NILM, identifying the most effective methods and summarizing evaluation benchmarks.

Findings

Deep learning methods improve NILM accuracy.

Public datasets enable standardized comparison.

Most accurate methods achieve high disaggregation performance.

Abstract

Demand-side management now encompasses more residential loads. To efficiently apply demand response strategies, it's essential to periodically observe the contribution of various domestic appliances to total energy consumption. Non-intrusive load monitoring (NILM), also known as load disaggregation, is a method for decomposing the total energy consumption profile into individual appliance load profiles within the household. It has multiple applications in demand-side management, energy consumption monitoring, and analysis. Various methods, including machine learning and deep learning, have been used to implement and improve NILM algorithms. This paper reviews some recent NILM methods based on deep learning and introduces the most accurate methods for residential loads. It summarizes public databases for NILM evaluation and compares methods using standard performance metrics.