New Semi-Supervised and Active Learning Combination Technique for Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) is a procedure that is used to disaggregate the contributions of different appliances in a building. Various traditional techniques use supervised and unsupervised learning for disaggregation. Very few papers utilize the semi-supervised or active approaches. The two approaches are used in case of training data scarcity. The semi-supervised approach is prone to errors as training dataset is small, while the active leaning approach relies completely on the user to get correct labels. A technique that leverages the semi-supervised and active learning together is applied. This can reduce the number of samples required to the users, also can increase the accuracy of the semi-supervised algorithm while more reliable samples can be added. Many cases are studied and the results showed the robustness and reliability of the new combination. The proposed combined technique showed that the number of queries can be reduced to fifth without losing more than 4% of the accuracy. Also, by combining the semi-supervised and active techniques, the accuracy increased by 6% compared to the stand alone semi-supervised approach.

[1]  Bin Yang,et al.  Active learning with cross-dataset validation in event-based non-intrusive load monitoring , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[2]  Jaime G. Carbonell,et al.  Proactive learning: cost-sensitive active learning with multiple imperfect oracles , 2008, CIKM '08.

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

[4]  J. Zico Kolter,et al.  REDD : A Public Data Set for Energy Disaggregation Research , 2011 .

[5]  Tong Zhang,et al.  The Value of Unlabeled Data for Classification Problems , 2000, ICML 2000.

[6]  Bin Yang,et al.  Toward a semi-supervised non-intrusive load monitoring system for event-based energy disaggregation , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

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

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

[9]  Markus Turtinen,et al.  Labeling of Textured Data with Co-training and Active Learning , 2005 .

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

[11]  Jack Kelly,et al.  The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes , 2014, Scientific Data.

[12]  Y. Ahmet Sekercioglu,et al.  Recent approaches to non-intrusive load monitoring techniques in residential settings , 2013, 2013 IEEE Computational Intelligence Applications in Smart Grid (CIASG).

[13]  Ali Selamat,et al.  Combination of active learning and self-training for cross-lingual sentiment classification with density analysis of unlabelled samples , 2015, Inf. Sci..

[14]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

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

[16]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

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

[18]  Xin Jin.  An Active Learning Framework for Non-Intrusive Load Monitoring Preprint , 2016 .

[19]  Anthony Rowe,et al.  BLUED : A Fully Labeled Public Dataset for Event-Based Non-Intrusive Load Monitoring Research , 2012 .

[20]  Hong-Tzer Yang,et al.  Design a Neural Network for Features Selection in Non-intrusive Monitoring of Industrial Electrical Loads , 2007, 2007 11th International Conference on Computer Supported Cooperative Work in Design.