Transient Event Classification Based on Wavelet Neuronal Network and Matched Filters

Detailed information about load behavior and home's occupancy is important to implement Home Energy Management Systems (HEMS) capable of reducing energy consumption while maintaining user comfort. This is why Non-intrusive Appliance Load Monitoring (NIALM) and Non-intrusive Occupancy Monitoring (NIOM) have an important role to play in the new context of smart grid. This paper shows the implementation of two algorithms for transient event detection and classification, which is the first key step of a NIOM process. The first method employs Wavelet transform for the feature extraction and Artificial Neural Networks for the classification problem. The second method is based on the theory of Matched Filters to achieve the transient event detection and classification. Experiments permitted to validate the proposed methods using a dataset of occupied residential building.

[1]  Kodjo Agbossou,et al.  Development of real-time admittance analysis system for residential load monitoring , 2016, 2016 IEEE 25th International Symposium on Industrial Electronics (ISIE).

[2]  Chuan Choong Yang,et al.  Comparative Study of Event Detection Methods for Non-intrusive Appliance Load Monitoring , 2014 .

[3]  Bin Yang,et al.  An Approach for Unsupervised Non-Intrusive Load Monitoring of Residential Appliances , 2013 .

[4]  Francisco Javier Ferrández Pastor,et al.  Using Wavelet Transform to Disaggregate Electrical Power Consumption into the Major End-Uses , 2014, UCAmI.

[5]  Irena Koprinska,et al.  Forecasting electricity load with advanced wavelet neural networks , 2016, Neurocomputing.

[6]  José M. F. Moura,et al.  Event detection for Non Intrusive load monitoring , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[7]  Mladen Victor Wickerhauser,et al.  Lectures On Wavelet Packet Algorithms , 1991 .

[8]  Hsueh-Hsien Chang,et al.  Non-Intrusive Demand Monitoring and Load Identification for Energy Management Systems Based on Transient Feature Analyses , 2012 .

[9]  Weidong Xiao,et al.  The meter tells you are at home! Non-intrusive occupancy detection via load curve data , 2015, 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[10]  Yogesh L. Simmhan,et al.  Energy management systems: state of the art and emerging trends , 2013, IEEE Communications Magazine.

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

[12]  Prashant J. Shenoy,et al.  Non-Intrusive Occupancy Monitoring using Smart Meters , 2013, BuildSys@SenSys.

[13]  Michel Verleysen,et al.  Les Réseaux de Neurones Artificiels , 1996 .

[14]  Silvia Santini,et al.  Occupancy Detection from Electricity Consumption Data , 2013, BuildSys@SenSys.

[15]  Steven B. Leeb,et al.  Nonintrusive Load Monitoring and Diagnostics in Power Systems , 2008, IEEE Transactions on Instrumentation and Measurement.

[16]  Kodjo Agbossou,et al.  Enabling winter behavior analysis on electrically heated residential buildings by smart sub-metering , 2018, 2018 IEEE International Conference on Industrial Technology (ICIT).

[17]  K Ramchandran,et al.  Best wavelet packet bases in a rate-distortion sense , 1993, IEEE Trans. Image Process..

[18]  G. Turin,et al.  An introduction to matched filters , 1960, IRE Trans. Inf. Theory.

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

[20]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[21]  Lucio Soibelman,et al.  User-Centered Nonintrusive Electricity Load Monitoring for Residential Buildings , 2011 .

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

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

[24]  Marie-Françoise Lucas,et al.  Compression of Biomedical Signals With Mother Wavelet Optimization and Best-Basis Wavelet Packet Selection , 2007, IEEE Transactions on Biomedical Engineering.

[25]  Wayes Tushar,et al.  Smart Grid Testbed for Demand Focused Energy Management in End User Environments , 2016, IEEE Wireless Communications.

[26]  Cesar Duarte,et al.  Feature extraction for nonintrusive load monitoring based on S-Transform , 2014, 2014 Clemson University Power Systems Conference.

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