A new ITU Focus Group will propose standardization strategies to assist Machine Learning in contributing to the efficiency of emerging IMT-2020 (5G) systems. The group will define the requirements of Machine Learning as they relate to technology, data formats and network architectures.
Contributions to the first meeting of the Focus Group in Geneva, 30 January to 2 February 2018, discussed 5G systems’ significant gains in complexity over 4G systems, highlighting potential for Machine Learning to make reliable predictions; support robust, efficient network operations; and increase the feasibility of network self-organization.
The first meeting of the Focus Group established three interdependent working groups:
WG ‘Use cases, services & requirements’ will document promising use cases of Machine Learning and describe their surrounding technological ecosystem. The study will identify the requirements of these use cases and bring greater clarity to the ICT industry’s vision for Machine Learning’s contribution to 5G systems.
WG ‘Data formats & Machine Learning technologies’ will produce a categorization of Machine Learning algorithms in communication networks, highlighting the implications of such algorithms for 5G systems. Key to this work will be the definition of required data formats and associated mechanisms to safeguard security and privacy.
WG ‘Machine Learning-aware network architecture’ will analyze the requirements of network architectures from the perspective of their expected interaction with Machine Learning algorithms. This work will describe the demands of Machine Learning on network functionality, interfaces and resources.
The next meeting of the Focus Group will take place in Xi’an, China, 24-27 April 2018, in conjunction with an ITU workshop on 25 April 2018.
ITU Focus Groups are open to all interested parties. Join the Focus Group’s mailing list, request access to documents and learn more about its priorities on the group’s homepage.
Learn more about the aims of the Focus Group in an ITU interview with the group’s Chairman Slawomir Stanczak of Fraunhofer Heinrich Hertz Institut.