Skip to main content

Liaison statement
LS (liaison statement) on Results of ITU’s work on machine learning for 5G networks

Additional information about IETF liaison relationships is available on the IETF webpage and the Internet Architecture Board liaison webpage.
State Posted
Submitted Date 2019-08-26
From Group ITU-T
From Contact Slawomir Stanczak
To Group IETF
To Contacts The IETF Chair <chair@ietf.org>
Cc Scott Mansfield <Scott.Mansfield@Ericsson.com>
The IETF Chair <chair@ietf.org>
itu-t-liaison@iab.org
The IESG <iesg@ietf.org>
Response Contact slawomir.stanczak@hhi.fraunhofer.de
Purpose For information
Attachments ML5G-O-023
Body
1       Architecture Framework for ML5G approved
The first deliverable of ITU’s Focus Group on Machine Learning for future
entworks including 5G (FG ML5G) was turned into an ITU-T Recommendation (“ITU
Standard”) by ITU-T Study Group 13 at its June 2019 meeting: Recommendation
ITU-T Y.3172 “Architectural framework for machine learning in future networks
including IMT-2020” is now publicly available free of charge here:
https://www.itu.int/rec/T-REC-Y.3172/en. Please see also the story in ITU NEWS
from 20 August 2019:
https://news.itu.int/new-itu-standard-machine-learning-5g-networks/.

2       Further specifications in the approval pipeline of ITU-T SG13
The following specifications from FG ML5G are being processed by ITU-T SG13:
•       “Machine learning in future networks including IMT-2020: use cases”
•       “Framework for evaluating intelligence level in future networks
including IMT-2020” •       “Framework for data handling to enable machine
learning in future networks including IMT-2020” The aim is to start the
approval process of these deliverables at the ITU-T SG13 meeting in October
2019.

3       Further specifications in FG ML5G
FG ML5G is currently working on these specifications:
•       “Architecture for machine learning marketplace integration in future
networks including IMT-2020” (ML5G-I-167) •       “Requirements, architecture
and design for machine learning function orchestrator” (ML5G-I-150-R1) •      
“Optimization and deployment framework for machine learning models in future
networks including IMT-2020" (ML5G-I-160)

4       Student projects in FG ML5G
More than 30 students are currently pursuing some 20 FG ML5G projects. The
projects are described here.

5       Future meetings
The 7th FG ML5G meeting will take in Berlin, Germany, hosted by Fraunhofer
Heinrich Hertz Institute: •       5 November 2019 (Tuesday): ITU workshop
“Machine Learning for 5G and beyond” •       6-8 November 2019: 7th meeting of
FG ML5G. Detailed information is available here. On 4 November 2019, Fraunhofer
Heinrich Hertz Institute organizes a workshop “5G and Beyond”. FG ML5G will
have two more meetings in 2020.

6       Participation in FG ML5G activities
ITU Focus Groups are open to all interested parties. Membership in ITU is not
required. Please join the Focus Group’s mailing list, request access to
documents and learn more about its priorities on the group’s homepage. We
welcome your input to the deliverables and updates on activities related to
ML5G, and look forward to collaborating with you.