Comprehensive feature selection for appliance classification in NILM

Abstract Since the inception of non-intrusive appliance load monitoring (NILM), extensive research has focused on identifying an effective set of features that allows to form a unique appliance signature to discriminate various loads. Although an abundance of features are reported in literature, most works use only a limited subset of them. A systematic comparison and combination of the available features in terms of their effectiveness is still missing. This paper, as its first contribution, offers a concise and updated review of the features reported in literature for the purpose of load identification. As a second contribution, a systematic feature elimination process is proposed to identify the most effective feature set. The analysis is validated on a large benchmark dataset and shows that the proposed feature elimination process improves the appliance classification accuracy for all the appliances in the dataset compared to using all the features or randomly chosen subsets of features.

[1]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[2]  Dawit Fekadu Teshome,et al.  Distinctive Load Feature Extraction Based on Fryze’s Time-Domain Power Theory , 2016, IEEE Power and Energy Technology Systems Journal.

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

[4]  Scott Dick,et al.  Toward Non-Intrusive Load Monitoring via Multi-Label Classification , 2017, IEEE Transactions on Smart Grid.

[5]  A. Albicki,et al.  Data extraction for effective non-intrusive identification of residential power loads , 1998, IMTC/98 Conference Proceedings. IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No.98CH36222).

[6]  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).

[7]  Radu Zmeureanu,et al.  Nonintrusive load disaggregation computer program to estimate the energy consumption of major end uses in residential buildings , 2000 .

[8]  Thomas G. Habetler,et al.  Electric Load Classification by Binary Voltage–Current Trajectory Mapping , 2016, IEEE Transactions on Smart Grid.

[9]  Youngwook Kim,et al.  Home appliance load disaggregation using cepstrum-smoothing-based method , 2015, IEEE Transactions on Consumer Electronics.

[10]  Manish Marwah,et al.  Unsupervised Disaggregation of Low Frequency Power Measurements , 2011, SDM.

[11]  Loi Lei Lai,et al.  Harmonics load signature recognition by wavelets transforms , 2000, DRPT2000. International Conference on Electric Utility Deregulation and Restructuring and Power Technologies. Proceedings (Cat. No.00EX382).

[12]  Radu Zmeureanu,et al.  Using a pattern recognition approach to disaggregate the total electricity consumption in a house into the major end-uses , 1999 .

[13]  Guilin Zheng,et al.  Residential Appliances Identification and Monitoring by a Nonintrusive Method , 2012, IEEE Transactions on Smart Grid.

[14]  A.C. Liew,et al.  Neural-network-based signature recognition for harmonic source identification , 2006, IEEE Transactions on Power Delivery.

[15]  Walid G. Morsi,et al.  Application of wavelet-based classification in non-intrusive load monitoring , 2015, 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE).

[16]  Jingkun Gao,et al.  A feasibility study of automated plug-load identification from high-frequency measurements , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[17]  Dongdong Li,et al.  A nonintrusive load identification method for residential applications based on quadratic programming , 2016 .

[18]  Kuo-Lung Lian,et al.  A New Power Signature for Nonintrusive Appliance Load Monitoring , 2015, IEEE Transactions on Smart Grid.

[19]  Abhay Gupta,et al.  Is disaggregation the holy grail of energy efficiency? The case of electricity , 2013 .

[20]  S. Drenker,et al.  Nonintrusive monitoring of electric loads , 1999 .

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

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

[23]  H. Y. Lam,et al.  A Novel Method to Construct Taxonomy Electrical Appliances Based on Load Signaturesof , 2007, IEEE Transactions on Consumer Electronics.

[24]  M. Baranski,et al.  Nonintrusive appliance load monitoring based on an optical sensor , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.

[25]  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.

[26]  Shinkichi Inagaki,et al.  Validation of Nonintrusive Appliance Load Monitoring Based on Integer Programming , 2008 .

[27]  Shwetak N. Patel,et al.  ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home , 2010, UbiComp.

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

[29]  Muhammad Ali Imran,et al.  Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey , 2012, Sensors.

[30]  Yi Yang,et al.  Front-End Electronic Circuit Topology Analysis for Model-Driven Classification and Monitoring of Appliance Loads in Smart Buildings , 2012, IEEE Transactions on Smart Grid.

[31]  Stefan Svensson.  Power Measurement Techniques for Nonsinusoidal Conditions. The Significance of Harmonics for the Measurement of Power and other AC quantities , 1999 .

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

[33]  Jian Liang,et al.  Load Signature Study—Part I: Basic Concept, Structure, and Methodology , 2010, IEEE Transactions on Power Delivery.

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

[35]  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).

[36]  Hsueh-Hsien Chang,et al.  Feature Selection of Non-intrusive Load Monitoring System Using STFT and Wavelet Transform , 2011, 2011 IEEE 8th International Conference on e-Business Engineering.

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

[38]  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).

[39]  C. Duarte,et al.  Non-intrusive load monitoring based on switching voltage transients and wavelet transforms , 2012, 2012 Future of Instrumentation International Workshop (FIIW) Proceedings.

[40]  A. Schoofs,et al.  Real-Time Recognition and Profiling of Appliances through a Single Electricity Sensor , 2010, 2010 7th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (SECON).

[41]  Walid G. Morsi,et al.  Nonintrusive Load Monitoring Using Wavelet Design and Machine Learning , 2016, IEEE Transactions on Smart Grid.

[42]  Jingkun Gao,et al.  PLAID: a public dataset of high-resoultion electrical appliance measurements for load identification research: demo abstract , 2014, BuildSys@SenSys.

[43]  Fahad Javed,et al.  An Empirical Investigation of V-I Trajectory Based Load Signatures for Non-Intrusive Load Monitoring , 2013, IEEE Transactions on Smart Grid.

[44]  Walid G. Morsi,et al.  Non-Intrusive Load Monitoring Using Semi-Supervised Machine Learning and Wavelet Design , 2017, IEEE Transactions on Smart Grid.

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

[46]  Lucio Soibelman,et al.  Enhancing Electricity Audits in Residential Buildings with Nonintrusive Load Monitoring , 2010 .

[47]  Leandros Tassiulas,et al.  Low Cost Disaggregation of Smart Meter Sensor Data , 2016, IEEE Sensors Journal.

[48]  B.A. Smith,et al.  Using a rule-based algorithm to disaggregate end-use load profiles from premise-level data , 1991, IEEE Computer Applications in Power.

[49]  Ming Dong,et al.  Non-Intrusive Signature Extraction for Major Residential Loads , 2013, IEEE Transactions on Smart Grid.

[50]  Hsueh-Hsien Chang,et al.  A New Measurement Method for Power Signatures of Nonintrusive Demand Monitoring and Load Identification , 2012, IEEE Transactions on Industry Applications.

[51]  S.B. Leeb,et al.  Estimation of variable-speed-drive power consumption from harmonic content , 2005, IEEE Transactions on Energy Conversion.

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