2019/07/14 by Alejandro Rodriguez-Silva, Rodriguez-Silva, Alejandro, Stephen Makonin +1
Engineering · #Building Energy and Comfort Optimization #FOS: Electrical engineering #IoT-based Smart Home Systems #Signal Processing (eess.SP) #Smart Grid Energy Management #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1907.06299
openalex publication_date 2019/07/14 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Being able to track appliances energy usage without the need of sensors can\nhelp occupants reduce their energy consumption to help save the environment all\nwhile saving money. Non-intrusive load monitoring (NILM) tries to do just that.\nOne of the hardest problems NILM faces is the ability to run unsupervised --\ndiscovering appliances without prior knowledge -- and to run independent of the\ndifferences in appliance mixes and operational characteristics found in various\ncountries and regions. We propose a solution that can do this with the use of\nan advanced filter pipeline to preprocess the data, a Gaussian appliance model\nwith a probabilistic knapsack algorithm to disaggregate the aggregate smart\nmeter signal, and partition maps to label which appliances were found and how\nmuch energy they use no matter the country/region. Experimental results show\nthat relatively complex appliance signals can be tracked accounting for 93.7%\nof the total aggregate energy consumed.\n