The goal of this project is to develop simple and inexpensive solutions for obtaining appliance-specific electricity consumption information from easy-to-obtain data sources like the overall power of the building.
We build on a technique called Non-Intrusive Non Monitoring, and attempt to detect and correctly identify state-transitions for individual appliances in a building (e.g., a light-bulb going from state "off" to state "on"), by inspecting the overall voltage and current signals for the building's electrical distribution system. We explore how different statistical and machine learning tools can be applied to solve the problem.
This video was filmed and edited in February 2009. For more updated information on the status of the project, please check our publications: http://marioberges.com/research/publications.php
Credits:
Mario Berges, Ethan Goldman, Lucio Soibelman, H. Scott Matthews
I have to say that I love how the related videos are all about hacking your electric meter...
Quatsch83 2 years ago