Enhancing Non-Intrusive Load Monitoring with Features Extracted by Independent Component Analysis

TL;DR

This paper introduces a neural network architecture that leverages independent component analysis to improve energy disaggregation, especially in complex scenarios with many appliances, demonstrating superior performance over existing methods.

Contribution

The paper presents a novel neural network design using ICA as its core, addressing data scarcity and complexity in non-intrusive load monitoring.

Findings

Model outperforms existing algorithms on real-world data

Less prone to overfitting and has low complexity

Effective in decomposing signals with many components

Abstract

In this paper, a novel neural network architecture is proposed to address the challenges in energy disaggregation algorithms. These challenges include the limited availability of data and the complexity of disaggregating a large number of appliances operating simultaneously. The proposed model utilizes independent component analysis as the backbone of the neural network and is evaluated using the F1-score for varying numbers of appliances working concurrently. Our results demonstrate that the model is less prone to overfitting, exhibits low complexity, and effectively decomposes signals with many individual components. Furthermore, we show that the proposed model outperforms existing algorithms when applied to real-world data.