Network slicing meets artificial intelligence: an AI-based framework for slice management Articles uri icon

authors

  • BEGA, DARIO
  • GRAMAGLIA, MARCO
  • GARCIA SAAVEDRA, ANDRES
  • BANCHS ROCA, ALBERT
  • FIORE, MARCO
  • COSTA-PEREZ, XAVIER

publication date

  • June 2020

start page

  • 32

end page

  • 38

issue

  • 6

volume

  • 58

International Standard Serial Number (ISSN)

  • 0163-6804

Electronic International Standard Serial Number (EISSN)

  • 1558-1896

abstract

  • Network slicing is an emerging paradigm in mobile networks that leverages Network Function Virtualization (NFV) to enable the instantiation of multiple virtual networks -named slices- over the same physical network infrastructure. The operator can allocate to each slice dedicated resources and customized functions that allow meeting the highly heterogeneous and stringent requirements of modern mobile services. Managing functions and resources under network slicing is a challenging task that requires making efficient decisions at all network levels, in some cases even in real-time, which can be achieved by integrating artificial intelligence (AI) in the network. We outline a general framework for AI-based network slice management, introducing AI in the different phases of the slice lifecycle, from admission control to dynamic resource allocation in the network core and at the radio access. A sensible use of AI for network slicing results in strong benefits for the operator, with expected performance gains between 25% and 80% in representative case studies.

keywords

  • artificial intelligence; admission control; network slicing; resource management; dynamic scheduling; heuristic algorithms; task analysis