Non-intrusive Residential Electrical Consumption Traces

An active trend of research consists of understanding how electricity is used, namely for energy efficiency enforcement and in-home activity tracking. The obvious and cheapest solution is to use an inconspicuous monitoring system. Through the use of non-intrusive load monitoring systems, the signal from the aggregate consumption is captured, electrical significant features are extracted and classified and the appliances that were consuming are identified. In order to obtain a precise identification of the device, the main requirements are an electrical signature for each device and a proper classification method. The information thus obtained identifies appliance’s usage and specific consumptions. This paper describes an on-going research aiming at the development and simplification of techniques and algorithms for non-intrusive load monitoring systems (NILM). The first steps in the implementation of a NILM system were already addressed, namely we are performing an extensive study on the characterization of the appliance’s electrical signature. The proposed parameters for defining an efficient electrical signature are the step-changes in the active and reactive power and the power factor.

[1]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[2]  Lucio Soibelman,et al.  Learning Systems for Electric Consumption of Buildings , 2009 .

[3]  Paul M. B. Vitányi,et al.  Clustering by compression , 2003, IEEE Transactions on Information Theory.

[4]  Hsueh-Hsien Chang,et al.  Load identification in nonintrusive load monitoring using steady-state and turn-on transient energy algorithms , 2010, The 2010 14th International Conference on Computer Supported Cooperative Work in Design.

[5]  A. Albicki,et al.  Algorithm for nonintrusive identification of residential appliances , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[6]  Robert W. Cox,et al.  Creating low-cost energy-management systems for homes using non-intrusive energy monitoring devices , 2009, 2009 IEEE Energy Conversion Congress and Exposition.

[7]  Steven B. Leeb,et al.  A conjoint pattern recognition approach to nonintrusive load monitoring , 1993 .

[8]  Hong-Tzer Yang,et al.  Load recognition for different loads with the same real power and reactive power in a non-intrusive load-monitoring system , 2008, 2008 12th International Conference on Computer Supported Cooperative Work in Design.

[9]  M. Berenguer,et al.  Automatic detection of activities of daily living from detecting and classifying electrical events on the residential power line , 2008, HealthCom 2008 - 10th International Conference on e-health Networking, Applications and Services.

[10]  Pasquale Daponte,et al.  Wavelet network-based detection and classification of transients , 2001, IEEE Trans. Instrum. Meas..

[11]  Luis Filipe Coelho Antunes,et al.  Clustering Fetal Heart Rate Tracings by Compression , 2006, 19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06).

[12]  Gregory D. Abowd,et al.  Ubicomp 2007: Ubiquitous Computing , 2008 .

[14]  Hujun Yin,et al.  Intelligent Data Engineering and Automated Learning - IDEAL 2010, 11th International Conference, Paisley, UK, September 1-3, 2010. Proceedings , 2010, IDEAL.

[15]  A. Shrestha,et al.  Dynamic load shedding for shipboard power systems using the non-intrusive load monitor , 2009, 2009 IEEE Electric Ship Technologies Symposium.

[16]  K. El Khamlichi Drissi,et al.  State of art on load monitoring methods , 2008, 2008 IEEE 2nd International Power and Energy Conference.

[17]  Gregory D. Abowd,et al.  At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line (Nominated for the Best Paper Award) , 2007, UbiComp.

[18]  Bernardete Ribeiro,et al.  Extracting Features from an Electrical Signal of a Non-Intrusive Load Monitoring System , 2010, IDEAL.

[19]  Lucio Soibelman,et al.  Training load monitoring algorithms on highly sub-metered home electricity consumption data , 2008 .

[20]  Bernardete Ribeiro,et al.  An Experimental Study on Electrical Signature Identification of Non-Intrusive Load Monitoring (NILM) Systems , 2011, ICANNGA.

[21]  G. W. Hart,et al.  Nonintrusive appliance load monitoring , 1992, Proc. IEEE.

[22]  F. Sultanem,et al.  Using appliance signatures for monitoring residential loads at meter panel level , 1991 .

[23]  G.W. Hart,et al.  Residential energy monitoring and computerized surveillance via utility power flows , 1989, IEEE Technology and Society Magazine.

[24]  Steven B. Leeb,et al.  Power signature analysis , 2003 .

[25]  Xiaohua Xia,et al.  Active power residential non-intrusive appliance load monitoring system , 2009, AFRICON 2009.

[26]  James L. Kirtley,et al.  Fault detection and diagnostics for non-intrusive monitoring using motor harmonics , 2010, 2010 Twenty-Fifth Annual IEEE Applied Power Electronics Conference and Exposition (APEC).