Picture water droplets

Developing mathematical theories of the physical world: Open Access research on fluid dynamics from Strathclyde

Strathprints makes available Open Access scholarly outputs by Strathclyde's Department of Mathematics & Statistics, where continuum mechanics and industrial mathematics is a specialism. Such research seeks to understand fluid dynamics, among many other related areas such as liquid crystals and droplet evaporation.

The Department of Mathematics & Statistics also demonstrates expertise in population modelling & epidemiology, stochastic analysis, applied analysis and scientific computing. Access world leading mathematical and statistical Open Access research!

Explore all Strathclyde Open Access research...

Power disaggregation of domestic smart meter readings using dynamic time warping

Elafoudi, Georgia and Stankovic, Lina and Stankovic, Vladimir (2014) Power disaggregation of domestic smart meter readings using dynamic time warping. In: 6th International Symposium on Communications, Control and Signal Processing (ISCCSP), 2014. IEEE.

[img] PDF (Elafoudi-etal-2014-Power-disaggregation-of-domestic-smart-meter-readings)
Elafoudi_etal_2014_Power_disaggregation_of_domestic_smart_meter_readings.pdf
Accepted Author Manuscript

Download (170kB)

Abstract

Non-intrusive appliance load monitoring (NALM), also called load disaggregation, is a method for isolating the energy consumption of individual appliances from an overall household energy consumption. Traditionally, NALM techniques are based on measuring several electrical parameters at high sampling rates, which increases the meter cost and communications and storage overhead. In this paper, we propose a low-complexity disaggregation method based on Dynamic Time Warping algorithm that uses only active power aggregate smart meter data, captured at a low frequency, for training and disaggregation . Experimental results are provided for three households using data collected during two months, showing which individual appliances were used and when. Average recognition accuracy of 85% was obtained.