A comparison of generative and discriminative appliance recognition models for load monitoring

Zoha, A. , Imran, M. A. , Gluhak, A. and Nati, M. (2013) A comparison of generative and discriminative appliance recognition models for load monitoring. IOP Conference Series: Materials Science and Engineering, 51(1), 012002. (doi: 10.1088/1757-899X/51/1/012002)

Abstract

Appliance-level Load Monitoring (ALM) is essential, not only to optimize energy utilization, but also to promote energy awareness amongst consumers through real-time feedback mechanisms. Non-intrusive load monitoring is an attractive method to perform ALM that allows tracking of appliance states within the aggregated power measurements. It makes use of generative and discriminative machine learning models to perform load identification. However, particularly for low-power appliances, these algorithms achieve sub-optimal performance in a real world environment due to ambiguous overlapping of appliance power features. In our work, we report a performance comparison of generative and discriminative Appliance Recognition (AR) models for binary and multi-state appliance operations. Furthermore, it has been shown through experimental evaluations that a significant performance improvement in AR can be achieved if we make use of acoustic information generated as a by-product of appliance activity. We demonstrate that our a discriminative model FF-AR trained using a hybrid feature set which is a catenation of audio and power features improves the multi-state AR accuracy up to 10 %, in comparison to a generative FHMM-AR model.

• Item Type: Articles
• Additional Information: The authors acknowledge the support from the REDUCE project grant (no:EP/I000232/1) under the Digital Economy Programme run by Research Councils UK - a cross council initiative led by EPSRC and contributed to by AHRC, ESRC, and MRC.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zoha, Dr Ahmed and Imran, Professor Muhammad
• Authors: Zoha, A., Imran, M. A., Gluhak, A., and Nati, M.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Systems Power and Energy
• Journal Name: IOP Conference Series: Materials Science and Engineering
• Publisher: IOP Publishing
• ISSN: 1757-8981
• ISSN (Online): 1757-899X
• Copyright Holders: Copyright © 2013 The Authors
• First Published: First published in IOP Conference Series: Materials Science and Engineering 51(1): 012002
• Publisher Policy: Reproduced under a Creative Commons License