Analysis and techniques for non-intrusive appliance load monitoring.

The increased public awareness of energy conservation and the demand for smart metering system have created interests in home energy monitoring. Load disaggregation using a single sensing point is considered a cost-effective way to sense individual appliance operation as opposed to using dedicated sensors for appliance monitoring. The aim of this thesis is to investigate the effectiveness of the analysis methods and techniques used in load disaggregation using a single point sensing. Time-frequency analysis methods such as Wavelet transforms are carefully examined and machine learning classifiers are used to develop the appropriate prediction models. The results have shown that the use of different Wavelet functions can significantly affect the classification accuracy. Among the four wavelets investigated in this thesis, two wavelets (Daubechies and Symlets) are able to provide the highest mean classification accuracy.

Name thesis:degree_name

Master of Applied Science (MASc)

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2014

Author dc:creator

• Alshareef, Sami

Advisor dc:contributor.advisor

• Morsi, Walid

• Non-intrusive load monitoring
• Power components
• Decision tree classification
• Edge detection
• Transient feature analysis

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/485

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/485