On a training-less solution for non-intrusive appliance load monitoring using graph signal processing

Zhao, Bochao and Stankovic, Lina and Stankovic, Vladimir (2016) On a training-less solution for non-intrusive appliance load monitoring using graph signal processing. IEEE Access, 4. pp. 1784-1799. (https://doi.org/10.1109/ACCESS.2016.2557460)

[thumbnail of Zhao-etal-IA-2016-On-a-training-less-solution-for-non-intrusive-appliance-load-monitoring]
Preview
Text. Filename: Zhao_etal_IA_2016_On_a_training_less_solution_for_non_intrusive_appliance_load_monitoring.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (12MB)| Preview

Abstract

With ongoing large-scale smart energy metering deployments worldwide, disaggregation of a household’s total energy consumption down to individual appliances using analytical tools, aka. non-intrusive appliance load monitoring (NALM), has generated increased research interest lately. NALM can deepen energy feedback, support appliance retrofit advice and support home automation. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges with respect to its practicality and effectiveness at low sampling rates. Indeed, the majority of NALM approaches, supervised or unsupervised, require training to build appliance models, and are sensitive to appliance changes in the house, thus requiring regular re-training. In this paper, we tackle this challenge by proposing a NALM approach that does not require any training. The main idea is to build upon the emerging field of graph signal processing to perform adaptive thresholding, signal clustering and pattern matching. We determine the performance limits of our approach and demonstrate its usefulness in practice. Using two open access datasets - the US REDD dataset with active power measurements downsampled to 1min resolution and the UK REFIT dataset with 8sec resolution, we demonstrate the effectiveness of the proposed method for typical smart meter sampling rate, with state-of-the-art supervised and unsupervised NALM approaches as benchmarks.