An Information-Theoretic Analysis of High-Frequency Load Disaggregation

TL;DR

This paper uses information theory to analyze how well different appliances can be identified from combined power signals, showing that mutual information predicts how accurately appliances can be detected.

Contribution

The paper introduces an information-theoretic framework to quantify appliance observability and disaggregation difficulty in high-frequency NILM.

Findings

Appliances with high mutual information, like hair dryers, have lower estimation errors in disaggregation.

Conditional mutual information reveals asymmetric masking effects, with laptop chargers being dominant interferers.

Normalized mutual information strongly correlates with disaggregation error (Spearman rs=−0.81, p=0.015).

Abstract

High-frequency non-intrusive load monitoring provides detailed harmonic information for appliances’ power disaggregation, and machine-learning approaches have demonstrated good performance in this task. However, these methods provide little transparency regarding the information structure of the aggregate signal. To address this, this paper models NILM as a coding-decoding process and applies information-theoretic measures to quantify uncertainty, recoverability, temporal contribution, and inter-appliance masking effects in aggregate signals. In the analyzed dataset, transfer entropy suggests negligible temporal gains, which is consistent with the observed effectiveness of pointwise models such as Random Forest. Moreover, conditional mutual information emphasizes the asymmetric masking relationships between appliances, with the laptop charger acting as a dominant interferer in the considered measurements. These findings are validated through a Random Forest regression model with minimum Redundancy Maximum Relevance feature selection. The results show that the mutual information between an appliance and the aggregate is a good predictor of disaggregation performance in the examined data, as appliances with high mutual information, such as hair dryer and electric water heater, achieve lower estimation errors, while others, such as iron, are difficult to recover despite stable distributions. This relationship is statistically supported by a strong negative monotonic correlation between normalized mutual information and the disaggregation error (Spearman rs=−0.81, p=0.015). Hence, this work demonstrates how information-theoretic analysis can help characterize disaggregation difficulty prior to model training and assess the observability of appliances in high-frequency NILM.

Figures