On a Training-Less Solution for Non-Intrusive Appliance Load Monitoring Using Graph Signal Processing

With ongoing large-scale smart energy metering deployments worldwide, disaggregation of a household's total energy consumption down to individual appliances using analytical tools, also known as non-intrusive appliance load monitoring (NALM), has generated increased research interest lately. NALM can deepen energy feedback, support appliance retrofit advice, and support home automation. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges with respect to its practicality and effectiveness at low sampling rates. Indeed, the majority of NALM approaches, supervised or unsupervised, require training to build appliance models, and are sensitive to appliance changes in the house, thus requiring regular re-training. In this paper, we tackle this challenge by proposing an NALM approach that does not require any training. The main idea is to build upon the emerging field of graph signal processing to perform adaptive thresholding, signal clustering, and pattern matching. We determine the performance limits of our approach and demonstrate its usefulness in practice. Using two open access datasets-the US REDD data set with active power measurements downsampled to 1 min resolution and the UK REFIT data set with 8-s resolution, we demonstrate the effectiveness of the proposed method for typical smart meter sampling rate, with the state-of-the-art supervised and unsupervised NALM approaches as benchmarks.

[1]  Sundeep Pattem Unsupervised Disaggregation for Non-intrusive Load Monitoring , 2012, 2012 11th International Conference on Machine Learning and Applications.

[2]  Peng Hin Lee,et al.  Unsupervised approach for load disaggregation with devices interactions , 2016 .

[3]  Philip A. Chou,et al.  Graph Signal Processing – A Probabilistic Framework , 2016 .

[4]  Jing Liao,et al.  A graph-based signal processing approach for low-rate energy disaggregation , 2014, 2014 IEEE Symposium on Computational Intelligence for Engineering Solutions (CIES).

[5]  Gene Cheung,et al.  Estimating heart rate via depth video motion tracking , 2015, 2015 IEEE International Conference on Multimedia and Expo (ICME).

[6]  Charles A. Sutton,et al.  Signal Aggregate Constraints in Additive Factorial HMMs, with Application to Energy Disaggregation , 2014, NIPS.

[7]  Dominik Egarter,et al.  PALDi: Online Load Disaggregation via Particle Filtering , 2015, IEEE Transactions on Instrumentation and Measurement.

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

[9]  Matthew J. Johnson,et al.  Bayesian nonparametric hidden semi-Markov models , 2012, J. Mach. Learn. Res..

[10]  Nirmalya Roy,et al.  Iterative signal separation assisted energy disaggregation , 2015, 2015 Sixth International Green and Sustainable Computing Conference (IGSC).

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

[12]  Tommi S. Jaakkola,et al.  Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation , 2012, AISTATS.

[13]  Alex Rogers,et al.  Non-Intrusive Load Monitoring Using Prior Models of General Appliance Types , 2012, AAAI.

[14]  Suman Giri,et al.  An energy estimation framework for event-based methods in Non-Intrusive Load Monitoring , 2015 .

[15]  Lina Stankovic,et al.  Understanding domestic appliance use through their linkages to common activities , 2015 .

[16]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

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

[18]  Jack Kelly,et al.  Neural NILM: Deep Neural Networks Applied to Energy Disaggregation , 2015, BuildSys@SenSys.

[19]  Andrew Y. Ng,et al.  Energy Disaggregation via Discriminative Sparse Coding , 2010, NIPS.

[20]  Federica Paganelli,et al.  Context-Based Energy Disaggregation in Smart Homes , 2016, Future Internet.

[21]  Manish Marwah,et al.  A Temporal Motif Mining Approach to Unsupervised Energy Disaggregation: Applications to Residential and Commercial Buildings , 2013, AAAI.

[22]  José M. F. Moura,et al.  Classification via regularization on graphs , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[23]  Dominik Egarter,et al.  Complexity of Power Draws for Load Disaggregation , 2015, ArXiv.

[24]  Francesco Piazza,et al.  Unsupervised algorithms for non-intrusive load monitoring: An up-to-date overview , 2015, 2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC).

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

[26]  Bin Yang,et al.  A new unsupervised event detector for non-intrusive load monitoring , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

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

[28]  David E. Irwin,et al.  Redux : The Case for Emphasizing Applications over Accuracy , 2014 .

[29]  Kamin Whitehouse,et al.  Neighbourhood NILM: A Big-data Approach to Household Energy Disaggregation , 2015, ArXiv.

[30]  Sanjeev Arora,et al.  Computational Complexity: A Modern Approach , 2009 .

[31]  Jing Liao,et al.  Non-intrusive appliance load monitoring using low-resolution smart meter data , 2014, 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[32]  Mario Berges,et al.  Unsupervised disaggregation of appliances using aggregated consumption data , 2011 .

[33]  Steven K. Firth,et al.  A data management platform for personalised real-time energy feedback , 2015 .

[34]  Dominik Egarter,et al.  Autonomous load disaggregation approach based on active power measurements , 2014, 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[35]  Vladimir Stankovic,et al.  Blind non-intrusive appliance load monitoring using graph-based signal processing , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

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

[37]  Michael Zeifman,et al.  Nonintrusive appliance load monitoring: Review and outlook , 2011, IEEE Transactions on Consumer Electronics.

[38]  José M. F. Moura,et al.  Discrete Signal Processing on Graphs , 2012, IEEE Transactions on Signal Processing.

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

[40]  Jing Liao,et al.  A low-complexity energy disaggregation method: Performance and robustness , 2014, 2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG).

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