| CODE | CCE5311 | ||||||||||||||||||||
| TITLE | AI & ML in Telecommunication Systems | ||||||||||||||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | ||||||||||||||||||||
| MQF LEVEL | 7 | ||||||||||||||||||||
| ECTS CREDITS | 5 | ||||||||||||||||||||
| DEPARTMENT | Communications and Computer Engineering | ||||||||||||||||||||
| DESCRIPTION | Driven initially by the revolutionary successes in computer vision, deep neural networks have precipitated an explosion of Artificial Intelligence (AI) and Machine Learning (ML) techniques that are impacting all fields of study. The study-unit will first summarize the work that the International Telecommunications Union Radio Committee (ITU-R) does in laying out its visions for International Mobile Telecommunications (IMT) every ten years and then the work carried out by the Third Generation Partnership Project (3GPP) turns these into technical specification releases in overlapping 7-year cycles. Then the study-unit teaches telecommunication engineers how to apply AI/ML techniques in the Physical Layer, Link Layer, Network Layer, Transport Layer and Management and Orchestration Plane of 5G, Beyond 5G and 6G systems based on realistic use cases identified by international bodies as well as in the literature. Crucially, they will learn when to apply such techniques as well as when not to apply them, since classical telecommunication solutions may well be optimised when deterministic or stochastic telecommunication models are known. The study-unit then introduces students to how 5G and 6G networks will support AI applications at the edge so that they can support latency-sensitive, real-time Edge-AI applications. This will include an exposure to distributed and federated learning which ensure training data privacy at the distributed training nodes. The study-unit features hands-on assignments/labs that expose telecommunications engineers to the design and development of AI/ML solutions and their deployment on terrestrial- and non-terrestrial testbeds. Study-unit Aims: - The aim of the study-unit is to introduce telecommunication engineers who are already familiar with the fundamentals of Artificial Intelligence (AI) and Machine Learning (ML) techniques, to the use of AI/ML techniques in the design, operation and maintenance of 5G, Beyond 5G and 6G telecommunication Systems; - By following this study-unit the students will become familiar with the work of international bodies in the area of AI/ML techniques applied to the field of wireless communications; - In addition they will become familiar with use case that will benefit from AI/ML techniques and learn how to design, train, deploy and orchestrate AI/ML solutions and applications; - Students will learn how 5G and 6G networks will support distributed and federated learning whilst maintaining the privacy of training data at the distributed training nodes; - Students will learn how to design, implement and deploy AI/ML solutions on terrestrial and non-terrestrial network test-beds at the UM. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - Describe the work of the international standardization bodies such as the ITU-R, 3GPP, and the IEEE in the adoption of AI/ML techniques for 5G, Beyond 5G and 6G telecommunication systems; - Identify the AI/ML features, challenges and implementations in IMT-2020 and IMT-2030 use cases, and as studied and implemented into specifications by 3GPP in Releases 15 onwards; - Identify and describe use cases that will benefit from AI/ML solutions; - Describe the role of data and datasets in the design of AI/ML solutions and applications; - Describe AI/ML development and deployment frameworks and platforms; - Identify and discuss areas which will benefit from AI/ML solutions; - Describe Supervised and Unsupervised Learning Techniques that are applicable to Telecommunication Systems including Deep Learning techniques; - Describe when and where AI/ML are applicable in telecommunication systems and when they are not; - Describe Edge AI applications especially those that benefit from latency reduation at the Edge; - Describe how techniques such as Federated Learning can help maintain data privacy in distributed learning systems. 2. Skills By the end of the study-unit the student will be able to: - Identify instances where telecommunication systems and subsystems will benefit for AI/ML techniques; - Source or create data sets for training telecommunications AI/ML applications and solutions; - Set up an AI/ML framework for training Telecommunications AI/ML applications and solutions; - Design and implement Supervised and Unsupervised AI/ML techniques, including the use of Deep Neural Networks, solutions and applications in the Physical Layer, Link Layer and Network Layer; - Design orchestration systems for the deployment, management and monitoring of telecommunications-related AI/ML applications; - Design Edge AI/ML solutions including those deployed in Non-Terrestrial-Networks (NTN) including UAV relays for use cases such as V2X, AR/VR/MR, and Digital Twin applications; - Design telecommunication systems for supporting real-time Edge AI applications including those using Federated Learning to maintain privacy of the training data; - Deploy AI/ML solutions over AI/ML terrestrial- and non-terrestrial networks; - Design AI/ML solutions that guarantee trust and privacy in and for telecommunication systems. Main Text/s and any supplementary readings: Text Book - Kim, Haesik. Artificial intelligence for 6G. Springer, 2022. Reference Book - Eldar, Y. C., Goldsmith, A., Gündüz, D., & Poor, H. V. (Eds.). (2022). Machine learning and wireless communications. Cambridge University Press. - Journal Paper - available online - Taleb, T., Benzaïd, C., Addad, R. A., & Samdanis, K. (2023). AI/ML for beyond 5G systems: Concepts, technology enablers & solutions. Computer Networks, 237, 110044. - Rahman, Imadur, Sara Modarres Razavi, Olof Liberg, Christian Hoymann, Henning Wiemann, Claes Tidestav, Paul Schliwa-Bertling, Patrik Persson, and Dirk Gerstenberger. "5G evolution toward 5G advanced: An overview of 3GPP releases 17 and 18." Ericsson Technology Review 2021, no. 14 (2021): 2-12. - Reference Reports available online - Series, M. (2015). IMT Vision–Framework and overall objectives of the future development of IMT for 2020 and beyond. Recommendation ITU, 2083(0). - Union, Internation Telecommunication. "Future technology trends of terrestrial International Mobile Telecommunications systems towards 2030 and beyond." (2022). - Kataria, Deepak, Anwar Walid, Mahmoud Daneshmand, Ashutosh Dutta, Michael A. Enright, Rentao Gu, Alex Lackpour et al. "Artificial Intelligence And Machine Learning." In 2022 IEEE Future Networks World Forum (FNWF), pp. 1-70. IEEE, 2022. |
||||||||||||||||||||
| ADDITIONAL NOTES | Pre-Requisite Study-units: CCE5502 or equivalent as determined by the BoS | ||||||||||||||||||||
| STUDY-UNIT TYPE | Independent Study, Lecture, Practical & Tutorials | ||||||||||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||||||||||
| LECTURER/S | Saviour Zammit |
||||||||||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
|||||||||||||||||||||