Appliance Water Disaggregation via Non-Intrusive Load Monitoring (NILM)

Last week, I learnt that a paper Bradley Ellert, myself, and Fred Popowich wrote was accepted for presentation at the EAI International Conference on Big Data and Analytics for Smart Cities in Toronto October 13 to 14. Here is the abstract:

The world’s fresh water supply is rapidly dwindling. Informing homeowners of their water use patterns can help them reduce consumption. Today’s smart meters only show a whole house’s water consumption over time. People need to be able to see where they are using water most to be able to change their habits. We are the first to present work where appliance water consumption is non-intrusively disaggregated using the results from a non-intrusive load monitoring algorithm. Unlike previous works that require the installation of water sub-meters or water sensors, our method does not. Further, our method uses low-frequency data from standardized meters and does not rely on labelled data. We modify the Viterbi Algorithm to apply a supervised method to an unsupervised disaggregation problem. We are able to achieve very high accuracy results having mean squared errors of under 0.02L²/min² .

Keywords: water disaggregation, water conservation, non-intrusive load monitoring, NILM, smart homes, sustainability