Artificial Intelligence and Machine Learning for 5G and 6G Networks

Dear Colleagues,

In September 2020, 3GPP approved studies concerning the deployment of Artificial Intelligence and Machine Learning (AI/ML subsystem) in 5G RAN. Since then, the RAN3 3GPP group has identified a functional framework for RAN intelligence and some related use cases for the current 5G RAN architecture where AI/ML techniques could provide substantial benefits. Studies have been motivated by the strong interest by the 3GPP community (including Telcos and manufacturers) in improving RAN automation with the aim of achieving network optimization decisions in multi-variable scenarios for which classic, “rule-based” techniques would not be equally effective. The introduction of AI/ML in new cellular networks such as 5G and in the future 6G networks allow managing their increasing complexity and to support various deployment scenarios and innovative applications. Furthermore, AI/ML techniques and data analytics also allow identifying patterns in data, which are useful to optimize the network design and operations. These innovations open new challenges for manufacturers and telcos that should be adequately addressed. Studies in the 3GGP RAN3 group have concluded in March 2022. Three main use cases have been identified and investigated in the RAN3 3GPP group: Network Energy Saving (traffic offloading, coverage modification and cell deactivation), Load Balancing (to distribute load effectively among cells or areas of cells in a multifrequency/multi-RAT deployment to improve network performance based on load predictions) and Mobility Optimization (optimal mobility targets are selected based on predictions of how UEs may be served). Advanced 5G and 6G networks will also integrate non-terrestrial networks, and AI/ML technologies are of interest to manage communications, protocols and interfaces exchanging heterogeneous data.

The possibility of integrating AI/ML technologies in 5G and future 6G networks is related to their acceptance and adoption by Telcos. For Telcos to be convinced to invest in AI/ML for transforming their networks requires the investigation of many technical–economic topics including: analysis of the costs for the integration of these technologies into their infrastructures, the quantification of the benefits that can be achieved and in how long these can be obtained, the expected revenues related to the creation of innovative applications, the possibility of introducing new business models, and the impact of AI/ML on the network management. In particular, the management of innovative networks adopting AI/ML will require the re-organization of Telco OSS with the acquisition and training of personnel with advanced skills in the IT sector. Finally, security aspects in networks integrating AI/ML technologies are another important aspect to be investigated.

The main purpose of this Special Issue is to try to provide a clearer view of how AI could be helpful in building advanced 5G and future 6G mobile networks with an emphasis on how AI allows us to optimize/improve their operations and to manage them efficiently. The assessment of the economic aspects related to the introduction of AI/ML techniques in modern 5G and future 6G networks represents another important point to be clarified.

Prof. Dr. Franco Mazzenga
Dr. Romeo Giuliano
Dr. Alessandro Vizzarri
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• AI for network planning, (self) adaptation and (self) optimization even at runtime
• AI solutions/algorithms in the access network and in the core network: AI for user and control planes and AI for management
• data collection, processing and management for AI in 5G and 6G networks
• AI solutions for improving energy saving in 5G/6G networks
• QoS/QoE management with AI/ML-based techniques and technologies
• AI/ML applications for improved security in advanced 5G and 6G networks
• improved indoor-outdoor localization in 5G/6G networks based on AI/ML
• AI/ML for managing 5G/6G networks in emergency situations
• dynamic management of 5G/6G networks using AI-driven policies, e.g., AI routing policies, intent-based approach for advanced network management
• AI/ML for the integration and efficient management of 3GPP and non-3GPP networks even including non-terrestrial networks
• AI/ML and Open-RAN for 5G and 6G (heterogeneous) access networks
• AI/ML for IoT / IoE in 5G and 6G networks
• technical-economic analysis of the impact of AI/ML solutions integrated into the existing 5G and future 6G networks operations and management
• AI/ML and innovative business models for telcos