AI/ML for beyond 5G systems: Concepts, technology enablers & solutions

Tarik Taleb, Chafika Benzaïd, Rami Akrem Addad, Konstantinos Samdanis*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

10 Citations (Scopus)

Abstract

5G brought an evolution on the network architecture employing the service-based paradigm, enabling flexibility in realizing customized services across different technology domains. Such paradigm gives rise to the adoption of analytics and Artificial Intelligence/Machine Learning (AI/ML) in mobile communications with the ease of collecting various measurements related to end-users and the network, which can be exposed towards consumers, including 3rd party applications. AI/ML may influence network planning and optimization considering the service life-cycle and introduce new operations provision, paving the way towards 6G. This article provides a survey on AI/ML considering the business, the fundamentals and algorithms across the radio, control, and management planes. It sheds light on the key technologies that assist the adoption of AI/ML in 3rd Generation Partnership Project (3GPP) networks considering service request, reporting, data collection and distribution and it overviews the main AI/ML algorithms characterizing them into user-centric and network-centric. Finally, it explores the main standardization and open source activities on AI/ML, highlighting the lessons learned and the further challenges that still need to be addressed to reap the benefits of AI/ML in automation for beyond 5G/6G mobile systems.

Original languageEnglish
Article number110044
Number of pages34
JournalComputer Networks
Volume237
DOIs
Publication statusPublished - Dec 2023
MoE publication typeA1 Journal article-refereed

Keywords

  • AI/ML
  • Data analytics
  • Intelligent networks
  • Network automation

Fingerprint

Dive into the research topics of 'AI/ML for beyond 5G systems: Concepts, technology enablers & solutions'. Together they form a unique fingerprint.

Cite this