Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances

TL;DR

This work tackles NILM ON/OFF multi-label classification with a focus on energy efficiency. It introduces CtRNN, a CNN-GRU architecture inspired by VGG that achieves higher accuracy while reducing training and inference energy compared to state-of-the-art DL models. A novel two-group evaluation framework (SE and RE) assesses robustness across varying numbers of active devices using REFIT and UK-DALE data, showing CtRNN yielding roughly 8–12 percentage points higher weighted F1 and over 23% lower energy consumption than baselines. The findings suggest that deep models can be both more accurate and more energy-efficient for practical NILM deployments, with realistic evaluation enabling better readiness for real-world smart-energy applications.

Abstract

Non-intrusive load monitoring (NILM) is the process of obtaining appliance-level data from a single metering point, measuring total electricity consumption of a household or a business. Appliance-level data can be directly used for demand response applications and energy management systems as well as for awareness raising and motivation for improvements in energy efficiency. Recently, classical machine learning and deep learning (DL) techniques became very popular and proved as highly effective for NILM classification, but with the growing complexity these methods are faced with significant computational and energy demands during both their training and operation. In this paper, we introduce a novel DL model aimed at enhanced multi-label classification of NILM with improved computation and energy efficiency. We also propose an evaluation methodology for comparison of different models using data synthesized from the measurement datasets so as to better represent real-world scenarios. Compared to the state-of-the-art, the proposed model has its energy consumption reduced by more than 23% while providing on average approximately 8 percentage points in performance improvement when evaluating on data derived from REFIT and UK-DALE datasets. We also show a 12 percentage point performance advantage of the proposed DL based model over a random forest model and observe performance degradation with the increase of the number of devices in the household, namely with each additional 5 devices, the average performance degrades by approximately 7 percentage points.

Figures (8)

• Figure 1: The proposed evaluation methodology of groups SE and RE of mixed datasets compared to the proposed evaluation methodology.
• Figure 2: Classification of devices as active or inactive based on the household NILM data using classical ML or DL model to obtain $s_i$ for each device; devices with $s_i > 0.5$ are classified as active, the others are classified as inactive.
• Figure 3: Probability distribution of the number of active devices in a 6 hours time window in REFIT and UK-DALE datasets.
• Figure 4: The proposed architecture inspired by the VGG family of architectures is explained within the figure, where "k" signifies the kernel, "f" represents the number of filters, and "s" denotes the stride value.
• Figure 5: Energy used for making predictions with the proposed model in comparison to VGG11, TanoniCRNN and VAE-NILM.