Residential Appliances Identification and Monitoring by a Nonintrusive Method

The method presented in this paper is based on new residential appliances classification and an events detect model. The whole identification and monitoring system is designed in a financially viable and easily applicable method that is ensured by followed two aspects: first, the only senor is one a meter installed to the main electric supply of a residence; second, the model of appliance is absolutely unsupervised. The classification factors of the appliances are main power consumption unit and working styles. The new events detector is simple enough to install into the sensor/meter. The final identification uses mean-shift clustering and multidimensional linear discriminates. Actual trials in situ and their results are presented to reveal the performance of the system.

[1]  Alain Anglade,et al.  A New Method for Detailed Electric Consumption of Domestic Appliances , 2001 .

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

[3]  Steven R. Shaw,et al.  A Kalman-Filter Spectral Envelope Preprocessor , 2007, IEEE Transactions on Instrumentation and Measurement.

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

[5]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

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

[7]  James L. Kirtley,et al.  Development and Validation of a Transient Event Detector , 1993 .

[8]  H. Pihala Non Intrusive Appliance Load Monitoring System Based On A , 1998 .

[9]  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).