Intelligent resource allocation for fifth-generation mobile networks using network slicing

• Grant number: 22/05397-5
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Effective date (Start): June 01, 2022
• Effective date (End): May 31, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Acordo de Cooperação: MCTI/MC
• Principal Investigator: José Ferreira de Rezende
• Grantee: Flávio Geraldo Coelho Rocha
• Host Institution: Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa (COPPE). Universidade Federal do Rio de Janeiro (UFRJ). Ministério da Educação (Brasil)
• Associated research grant: 18/23097-3 - SFI2: slicing future internet infrastructures, AP.TEM

Abstract

Fifth-generation mobile networks are characterized by highly heterogeneous demands and services that include ultra-speed data transmission, ultra-reliable and very low-latency communications, and massive communications between machines and devices. Network slicing is a novel paradigm for mobile networks that allows the creation of multiple virtual networks that run simultaneously on the same physical network infrastructure, which allows heterogeneous demands and services to work concurrently, but also efficiently, in the infrastructure of telecommunication operators. However, it is challenging to manage the various resources of the different network slices, since the demands for efficient network management involve decision-making that must be made in real-time and with a high level of accuracy. In addition, the high volume of connected devices incurs a large volume of data to be processed by operators, on which decision-making about the efficient allocation of resources depends. A complex and multifactorial problem that generally cannot be successfully solved by traditional approaches with deterministic and non-adaptive calculations. In this context, artificial intelligence is a promising tool, as it hasthe ability to process a high volume of information, provide simpler solutions to complexproblems, and provide solutions in real-time and, often, in an adaptive way. In this project, weinvestigate the use of artificial intelligence for automation, adaptive management, and intelligentallocation of physical infrastructure resources of 5G networks using the network slicing paradigm. (AU)