Low-cost appliance state sensing for energy disaggregation

Reliable detection of appliance state change is a barrier to the scalability of Non Intrusive Load Monitoring (NILM) beyond a small number of sufficiently distinct and large loads. We advocate a hybrid approach where a NILM algorithm is assisted by ultra-low-cost outlet-level sensors optimized for detecting appliance state change and communicating the event on a best-effort basis to a central entity for opportunistic fusion with the state change detection mechanism within NILM. In support of such an approach we present the implementation of an appliance power state sensor which achieves low cost via design choices such as a transmit-only radio. We also present results from a study where the sensors tracked power states of tens of appliances with high accuracy.

[1]  S.B. Leeb,et al.  Transient event detection for nonintrusive load monitoring and demand side management using voltage distortion , 2006, Twenty-First Annual IEEE Applied Power Electronics Conference and Exposition, 2006. APEC '06..

[2]  S. R. Shaw,et al.  Transient event detection in spectral envelope estimates for nonintrusive load monitoring , 1995 .

[3]  Corinna Fischer.  Feedback on household electricity consumption: a tool for saving energy? , 2008 .

[4]  Los Angeles.  Low-cost Appliance State Sensing for Energy Disaggregation , 2012 .

[5]  Max A. Little,et al.  Generalized methods and solvers for noise removal from piecewise constant signals. II. New methods , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[6]  Richard E. Brown,et al.  How Much Energy Are We Using? Potential of Residential Energy Demand Feedback Devices , 2006 .

[7]  Qi Han,et al.  Circuit-Level Load Monitoring for Household Energy Management , 2011, IEEE Pervasive Computing.

[8]  Michael Baranski,et al.  Detecting patterns of appliances from total load data using a dynamic programming approach , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[9]  Lawrence G. Roberts,et al.  ALOHA packet system with and without slots and capture , 1975, CCRV.

[10]  Tommi S. Jaakkola,et al.  Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation , 2012, AISTATS.

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

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

[13]  M. Baranski,et al.  Genetic algorithm for pattern detection in NIALM systems , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[14]  Andreas Savvides,et al.  Estimating building consumption breakdowns using ON/OFF state sensing and incremental sub-meter deployment , 2010, SenSys '10.

[15]  Anthony Rowe,et al.  Contactless sensing of appliance state transitions through variations in electromagnetic fields , 2010, BuildSys '10.

[16]  David E. Culler,et al.  Design and implementation of a high-fidelity AC metering network , 2009, 2009 International Conference on Information Processing in Sensor Networks.

[17]  Steven B. Leeb,et al.  Non-intrusive electrical load monitoring in commercial buildings based on steady-state and transient load-detection algorithms , 1996 .