[Nmlrg] Uses case for ML -- automating traffic prioritisation

[grenville armitage <[e-mail]>]

I've joined a little late, but understand from the archives that you're looking for example use cases?

The following links may be of interest. Between ~2005 and ~2012 my group explored the application of machine learning to the task of classifying application flows. One of the specific use cases was to classify traffic that required different QoS treatment, and automate the subsequent configuration of bottleneck home gateways to achieve said QoS treatment.

Our top-level project page: http://caia.swin.edu.au/urp/diffuse/
A proof-of-concept implemented in OpenWRT: http://caia.swin.edu.au/urp/diffuse/openwrt/
(earlier work on statistical traffic classification: http://caia.swin.edu.au/urp/dstc)

Some academic papers that might be of interest:

Thuy T. T. Nguyen, Grenville Armitage, Philip Branch and Sebastian Zander.
Timely and Continuous Machine-Learning-Based Classification for Interactive IP Traffic
IEEE/ACM Transactions on Networking, vol. 20 no. 6 pp. 1880-1894, December 2012
http://dx.doi.org/10.1109/TNET.2012.2187305

Thuy Nguyen and Grenville Armitage.
A Survey of Techniques for Internet Traffic Classification using Machine Learning
IEEE Communications Surveys & Tutorials, vol. 10 no. 4 pp. 56-76, 2008
http://dx.doi.org/10.1109/SURV.2008.080406

cheers,
gja
-- 
Professor Grenville Armitage
Director, Centre for Advanced Internet Architectures
School of Software and Electrical Engineering
Faculty of Science, Engineering and Technology
Swinburne University of Technology, Australia
http://caia.swin.edu.au