Event detection in NILM using Cepstrum smoothing

Event detection plays an important role in nonintrusive load monitoring to accurately detect the switching of appliances in a residential environment. Improving the detection ratios of those methods while keeping the computational cost under control is important. This paper presents a new event detection mechanism that works in the frequency domain and uses Cepstrum smoothing to eliminate noise. We explore the potential of our method by comparing with the χ GOF method on the BLUED dataset. The results indicate that our method is competitive with the state-of-the-art having as advantage that the same feature can also be used for appliance detection.

[1]  Pablo M. Granitto,et al.  Abrupt change detection with One-Class Time-Adaptive Support Vector Machines , 2013, Expert Syst. Appl..

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

[3]  B. P. Bogert,et al.  The quefrency analysis of time series for echoes : cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking , 1963 .

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

[5]  Fred Popowich,et al.  Nonintrusive load monitoring (NILM) performance evaluation , 2014, Energy Efficiency.

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

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

[8]  Gregory Nuel,et al.  Hidden Markov Model Applications in Change-Point Analysis , 2012, 1212.1778.

[9]  Amit Kumar Verma,et al.  Application of Cepstrum in Passive Sonar , 2012 .

[10]  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).

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

[12]  Kesheng Wu,et al.  Fast Change Point Detection for electricity market analysis , 2013, 2013 IEEE International Conference on Big Data.

[13]  David Pearce,et al.  The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions , 2000, INTERSPEECH.

[14]  Gustavo Camps-Valls,et al.  Unsupervised Change Detection With Kernels , 2012, IEEE Geoscience and Remote Sensing Letters.

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