Residential load event detection in NILM using robust cepstrum smoothing based method

Event detection has an important role in detecting the switching of the state of the appliance in the residential environment. This paper proposed a robust smoothing method for cepstrum estimation using double smoothing i.e. the cepstrum smoothing and local linear regression method. The main problem is to reduce the variance of the home appliance peak signal. In the first step, the cepstrum smoothing method removed the unnecessary quefrency by applying a rectangular window to the cepstrum of the current signal. In the next step, the local regression smoothing weighted data points to be smoothed using robust least squares regression. The result of this research shows the variance of the peak signal is decreased and has a good performance with better accuracy. In noise enviromment, performance prediction quite good with values greater than 0.6 and relatively stable at values above 0.9 on SNR> 25 for single appliances. Furthermore, in multiple appliances, performance prediction quite good at SNR> 20 and begins to decrease in SNR 25.

[1]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[2]  Thomas C. M. Lee,et al.  Nonparametric Cepstrum Estimation via Optimal Risk Smoothing , 2010, IEEE Transactions on Signal Processing.

[3]  Isiaka A. Alimi,et al.  Voice-Based Door Access Control System using the Mel Frequency Cepstrum Coefficients and Gaussian Mixture Model , 2014 .

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

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

[6]  C. Venkatesh,et al.  Modelling of Nonlinear Loads and Estimation of Harmonics in Industrial Distribution System , 2008 .

[7]  Suhono Harso Supangkat,et al.  Adaptive non-intrusive Load Monitoring model using Bayesian learning , 2014, 2014 International Conference on ICT For Smart Society (ICISS).

[8]  Narender Reddy Narra,et al.  Modeling And Harmonic Analysis Of Domestic / Industrial Loads , 2012 .

[9]  Lucio Soibelman,et al.  A time-frequency approach for event detection in non-intrusive load monitoring , 2011, Defense + Commercial Sensing.

[10]  L. Angrisani,et al.  An efficient extension of the zero-crossing technique to measure frequency of noisy signals , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[11]  Teddy Surya Gunawan,et al.  Wavelet Cesptral Coefficients for Isolated Speech Recognition , 2013 .

[12]  K. Trung,et al.  Event Detection and Disaggregation Algorithms for NIALM System , 2014 .

[13]  Pradeep Kumar Juneja,et al.  Identifying Appliances using NIALM with Minimum Features , 2014 .

[14]  Suhono Harso Supangkat,et al.  Home energy management system: A framework through context awareness , 2013, International Conference on ICT for Smart Society.

[15]  Tom Dhaene,et al.  Event detection in NILM using Cepstrum smoothing , 2016 .

[16]  Petre Stoica,et al.  Total-Variance Reduction Via Thresholding: Application to Cepstral Analysis , 2007, IEEE Transactions on Signal Processing.