Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

A real-time non-intrusive load monitoring system

Welikala, Shirantha, Dinesh, Chinthaka, Ekanayake, Mervyn Parakrama B., Godaliyadda, Roshan Indika and Ekanayake, Janaka 2018. A real-time non-intrusive load monitoring system. Presented at: 11th International Conference on Industrial and Information Systems (ICIIS-2016), Roorkee, Uttarakhand, India, 3-4 December 2016. 2016 11th International Conference on Industrial and Information Systems (ICIIS). IEEE, pp. 850-855. 10.1109/ICIINFS.2016.8263057

Full text not available from this repository.

Abstract

A complete real-time (RT) implementation of a NonIntrusive Load Monitoring (NILM) system based on uncorrelated spectral components of the active power consumption signal is presented. Unlike existing NILM techniques that rely on multiple measurements taken at high sampling rates and, yet only proven in simulated environments, this proposed RT-NILM solution yield accurate results even with a single active power measurement taken at a low sampling rate from real-time hardware. An Active Power Meter (APM) was developed and constructed, then, used with the designed MATLAB ™ Graphical User Interface (GUI) to break down the acquired active power signal of an appliance into subspace components (SCs) so as to construct a unique information rich appliance signature via the Karhunen Love expansion (KLE). Using the same GUI, signatures for all possible device combinations were constructed to form the appliance signature database. Then, a separate GUI was designed to identify the turned-on appliance combination in the current time window after reading the total power consumption of a device combination via the constructed APM. There in the identification process, SC level power conditions were used to reduce the number of possible appliance combinations rapidly before applying the maximum a posteriori estimation. The proposed RT-NILM implementation was validated by feeding the data in real-time from a laboratory arrangement consisting of ten household appliances.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Engineering
Publisher: IEEE
ISBN: 9781509038190
Last Modified: 25 Apr 2019 14:00
URI: http://orca.cf.ac.uk/id/eprint/120777

Citation Data

Cited 5 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item