The International Telecommunications Union (ITU), the United Nations specialised agency for
information and communication technologies (ICTs), has launched
a new ITU Focus Group to establish a basis for ITU standardisation to assist
machine learning (ML) in bringing more automation and intelligence to ICT
network design and management.
Machine learning algorithms are helping operators to make
smarter use of network-generated data. These algorithms enable ICT networks and
their components to adapt their behaviour autonomously in the interests of
efficiency, security and optimal user experience.
Fixed and mobile networks generate a huge amount of data both
at the network infrastructure level and at the user/customer level, which
contain a lot of useful information such as data on location, mobility and call
patterns. New ML methods for big data analytics in communication networks can
extract relevant information from the network data, and then leverage this knowledge
for autonomic network control and management as well as service provisioning.
ML also impacts ICT in areas related to security or
protection of personal information. Regulations in ICT may require that the
learning algorithms do not provide personally identifiable information (PII). The
Terms
of Reference document notes that hence, ML algorithms that also work under
uncertainty and incompleteness are of increasing interest in ICT.
The standardisation of interfaces, processes and data
formats is of high importance in communications, because it increases the
reliability, interoperability and modularity of a system and its respective
components. Standardised formats may be needed to specify how to train, adapt,
compress and exchange individual ML algorithms, as well as to ensure that
multiple ML algorithms correctly interact with each other and that certain
security or protection of personal information requirements are fulfilled.
The objective of the Focus Group is to conduct an analysis of
ML for future networks in order to identify relevant gaps and issues in
standardisation activities. It includes technical aspects such as use cases,
possible requirements, architectures and others. The Focus Group also serves as
an open platform for experts representing ITU members and non-members to
quickly move forward studies on ML related to future networks including 5G.
The objectives of the focus group include helping adoption of ML in future networks
including architecture, interfaces, use cases, protocols, algorithms, data formats, interoperability, performance,
evaluation, security and protection of personal information; to study, review and survey
existing technologies, platforms, guidelines and standards for ML in future
networks; and to identify aspects enabling safe and trusted use of ML
frameworks.
The creation of the Focus Group was agreed by ITU’s
standardisation expert group for future networks, ITU-T Study
Group 13. The ITU
Focus Group on Machine Learning for Future Networks including 5G will
lead an intensive one-year investigation into where technical standardisation
could support emerging applications of machine learning in fields such as big
data analytics, network management and orchestration, and security and data
protection. The first meeting of the Focus Group is scheduled for 29 January to
2 February 2018. Contributions are invited on state-of-the-art use cases of
machine learning and underlying technical requirements.
“ITU Focus Groups define new directions in ITU standardisation,”
said Chaesub Lee, Director of the ITU Telecommunication Standardization Bureau.
“These groups deliver base documents to stimulate international standardisation
work. They are effective in accelerating ITU studies in fields of growing
strategic relevance to the ITU membership.”
The Focus Group’s Chairman, Slawomir Stanczak of Germany’s
Fraunhofer Heinrich-Hertz-Institut commented, “Machine learning and artificial
intelligence are finding promising applications in communications networking. This
Focus Group will establish a basis for ITU standards experts to capitalize on
machine learning in their preparations for the 5G era.”