A Non Intrusive Low Cost Kit for Electric Power Measuring and Energy Disaggregation

This article presents a kit to collect data of electric loads of single and three phases main power supply of a house and perform the energy disaggregation. To collect the data, we use sensors based on open magnetic core to measure the electromagnetic field induced by the current in the electric conducting wire in a non intrusive way. In particular, each sensor from the three-phase device wraps/encloses each phase without alignment. In order to calibrate the three-phase device, we present a method to calculate the neutral RMS without complex numbers using (Analysis of Variance) ANOVA and post hoc Tukey’s multiple comparison test to assert the differences of measures among phases. We managed to validate the method using a measure reference. Additionally, to perform the energy disaggregation, we use the NILMTK tool. This toll was used, initially, to compare disaggregation algorithms on many public datasets. We use in our system two disaggregation algorithms Combinatorial Optimization and Factorial Hidden Markov Model algorithms. The results show that is possible to collect and perform energy disaggregation through our embedded system.

[1]  Prabal Dutta,et al.  Gemini: A Non-invasive, Energy-Harvesting True Power Meter , 2014, 2014 IEEE Real-Time Systems Symposium.

[2]  Hsueh-Hsien Chang,et al.  Particle-Swarm-Optimization-Based Nonintrusive Demand Monitoring and Load Identification in Smart Meters , 2013 .

[3]  Dominik Egarter,et al.  Evolving Non-Intrusive Load Monitoring , 2013, EvoApplications.

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

[5]  Joel J. P. C. Rodrigues,et al.  A non intrusive low cost Arduino-based three phase sensor kit for electric power measuring , 2017, 2017 2nd International Multidisciplinary Conference on Computer and Energy Science (SpliTech).

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

[7]  Haimonti Dutta,et al.  NILMTK: an open source toolkit for non-intrusive load monitoring , 2014, e-Energy.

[8]  Y. Wen,et al.  Nonintrusive Current Sensor for the Two-Wire Power Cords , 2015, IEEE Transactions on Magnetics.

[9]  Y. C. Chen,et al.  Anti-electromagnetic interference and calibration schemes of flexible current sensor tag for reliable current detection in household appliance , 2013, 2013 Transducers & Eurosensors XXVII: The 17th International Conference on Solid-State Sensors, Actuators and Microsystems (TRANSDUCERS & EUROSENSORS XXVII).

[10]  Alex Rogers,et al.  An unsupervised training method for non-intrusive appliance load monitoring , 2014, Artif. Intell..

[11]  Yu-Hsiu Lin,et al.  Non-Intrusive Load Monitoring by Novel Neuro-Fuzzy Classification Considering Uncertainties , 2014, IEEE Transactions on Smart Grid.

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

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

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

[15]  Chin-Sheng Chen,et al.  Applications of fuzzy classification with fuzzy c-means clustering and optimization strategies for load identification in NILM systems , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[16]  Jack Kelly,et al.  Metadata for Energy Disaggregation , 2014, 2014 IEEE 38th International Computer Software and Applications Conference Workshops.

[17]  José M. F. Moura,et al.  Unsupervised Approximate Power Trace Decomposition Algorithm , 2014 .

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