A new graph learning-based signal processing approach for non-intrusive load disaggregation with active power measurements
Recently, there is a potential technology called graph-based signal processing (GSP) that is being used in many applications. GSP has been used successfully in the domains such as signal and image filtering and processing. In the paper, GSP is used as an applicable method to non-intrusive appliance load monitoring (NILM). In NILM, all of power consumption is disaggregated down to every appliance’s consumption without hardware. Although there is over 30 years after NILM was proposed, there are still some problems faced by applications of NILM in real scenario if there is no training data. By combination of NILM with GSP concept, such a challenge is tackled with better performance over existing methods. As the first step, we propose a new graph learning algorithm to get a graph suitable for appliance load representation and for the disaggregation algorithm. In the following steps, graph-based signal processing method is used three times, from representation of the data sets of power measurements. Public datasets are used to demonstrate the proposed method’s performance and feasibility.
KeywordsGraph-based signal processing Non-intrusive appliance load monitoring Energy disaggregation Graph learning
Compliance with ethical standards
Conflict of interest
The authors declared that they have no conflicts of interest to this work.
- 2.D. of Energy, C. C. UK (2013) Government response to the consultation on the second version of the smart metering equipment technical specifications: part 2Google Scholar
- 11.Shuman DI, Narang SK, Frossard P, Ortega A, Vandergheynst P (2013) The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Process Mag 30(3):83–98. https://doi.org/10.1109/MSP.2012.2235192 CrossRefGoogle Scholar
- 14.Perraudin N, Paratte J, Shuman D, Martin L, Kalofolias V, Vandergheynst P, Hammond DK (2014) GSPBOX: a toolbox for signal processing on graphs. arXiv eprints arXiv:1408.5781
- 29.Stankovic V, Liao J, Stankovic L (2014) A graph-based signal processing approach for low-rate energy disaggregation. In: 2014 IEEE symposium on computational intelligence for engineering solutions (CIES), pp 81–87. https://doi.org/10.1109/cies.2014.7011835
- 30.Sandryhaila A, Moura JMF (2013) Classification via regularization on graphs. In: 2013 IEEE global conference on signal and information processing, pp 495–498. https://doi.org/10.1109/globalsip.2013.6736923
- 31.Zhao B, Stankovic L, Stankovic V (2015) Blind non-intrusive appliance load monitoring using graph-based signal processing. In: 2015 IEEE global conference on signal and information processing (GlobalSIP), pp 68–72. https://doi.org/10.1109/globalsip.2015.7418158
- 32.Welikala S, Dinesh C, Godaliyadda V, Ekanayake MPB, Ekanayake J (2016) Robust non-intrusive load monitoring (nilm) with unknown loads. In: 2016 IEEE international conference on information and automation for sustainability (ICIAfS), pp 1–6. https://doi.org/10.1109/iciafs
- 33.Makonin S, Popowich F, Bartram L, Gill B, Bajic IV (2013) Ampds: a public dataset for load disaggregation and eco-feedback research. In: 2013 IEEE electrical power energy conference, pp 1–6. https://doi.org/10.1109/epec.2013.6802949
- 34.Kolter J, Jaakkola T (2012) Approximate interence in additive factorial hmms with application to energy disaggregation. J Mach Learn Res 22(1):1472–1482Google Scholar