Non-Intrusive Load Monitoring Toolkit (nilmtk)
Below is an illustration of what NILM, in general, can do. Please note that nilmtk cannot do this yet! But we hope that it will do soon! This image is from the following paper and since the main author is contributing to nilmtk, so no permission issues.
Nipun Batra, Haimonti Dutta, Amarjeet Singh, “INDiC: Improved Non-Intrusive load monitoring using load Division and Calibration”, to appear at the 12th International Conference on Machine Learning and Applications (ICMLA’13) will be held in Miami, Florida, USA, December 4 – December 7, 2013 Preprint IPython notebook
#####Current state of the project
The project is in the very, very earliest stages. It does not do anything useful yet! If you'd like to help design the architecture please jump into the issue queue. Otherwise, if you want something usable, then please check back in a month or two ;)
#####Installing
If you just want to use the code without modifying it then:
python setup.py install
(you may have to run as sudo)
If you want to get involved in development then:
python setup.py develop
#####Software Dependencies
- Pandas
- matplotlib
- numpy => 1.8
- scikit-learn > 0.13
#####Further info
Please see the nilmtk wiki for more details.