Hi, IETFers,
We have proposed a new Research Group in IRTF - Networks Machine Learning
(NML). We believe the machine learning mechanism would help the development of
the Internet. It could introduce new ways to make decision autonomically by
network devices or provide helpful information for network administrators. And
it could provide flexibility and adaptability to networks. Not any the network
management, but also network establishment or control are potentially benefited
from the machine learning mechanism. Applying the machine learning mechanism in
network domains are still not matured, that is why it is a research group. But
it would rapidly move from academic research into practical application. We are
planning to hold the first meeting in IETF 94, Yokohama. Participants from both
university environments and industrial research and development organizations
are all welcome.
The charter and mail list information is below:
Networks Machine Learning Research Group
Link: http://trac.tools.ietf.org/group/irtf/trac/wiki/nml
Mailing List
nmlrg(_at_)irtf(_dot_)org
https://www.irtf.org/mailman/listinfo/nmlrg
Charter
Machine learning technologies can learn from historical data, and make
predictions or decisions, rather than following strictly static program
instructions. They can dynamically adapt to a changing situation and enhance
their own intelligence with by learning from new data. This approach has been
successful in image analysis, pattern recognition, language recognition,
conversation simulation, and many other applications. It can learn and complete
complicated tasks. It also has potential in the network technology area. It can
be used to intelligently learn the various environments of networks and react
to dynamic situations better than a fixed algorithm. When it becomes mature, it
would be greatly accelerate the development of autonomic networking.
The Network Machine Learning Research Group (NMLRG) provides a forum for
researchers to explore the potential of machine learning technologies for
networks. In particular, the NMLRG will work on potential approaches that apply
machine learning technologies in network control, network management, and
supplying network data for upper-layer applications.
The initial focus of the NMLRG will be on higher-layer concepts where the
machine learning mechanism could be applied in order to enhance the network
establishing, controlling, managing, network applications and customer
services. This includes mechanisms to acquire knowledge from the existing
networks so that new networks can be established with minimum efforts; the
potential to use machine learning mechanisms for routing control and
optimization; using machine learning mechanisms in network management to
predict future network status; using machine learning mechanisms to autonomic
and dynamically manage the network; using machine learning mechanisms to
analyze network faults and support recovery; learning network attacks and their
behavior, so that protection mechanisms could be self-developed; unifying the
data structure and the communication interface between network/network devices
and customers, so that the upper-layer applications could easily obtain
relevant network !
information, etc.
The NMLRG is expected to identify and document requirements, to survey possible
approaches, to provide specifications for proposed solutions, and to prove
concepts with prototype implementations that can be tested in real-world
environments.
The group will report its progress through a publicly accessible web site and
presentations at IETF meetings. Specifications developed by the NMLRG will be
submitted for publication as Experimental or Informational RFCs.
This topic is rapidly moving from academic research into practical application.
Therefore we hope to attract participants from both university environments and
industrial research and development organizations, in order to create synergy
and convert theory into practice. People actively implementing relevant
software will be especially welcome.
Membership
Membership is open to any interested parties/individuals.
Meetings
Regular working meetings are held about two/three times per year at locations
convenient to the majority of the participants. Working meetings typically take
1-2 days and are typically co-located with either IETF meetings or conferences
related to machine learning or autonomic networks.
Best regards,
Sheng