Optimization of Flow Allocation in Asynchronous Deterministic 5G Transport Networks by Leveraging Data Analytics

Jonathan Prados-Garzon, Tarik Taleb, Miloud Bagaa

Research output: Contribution to journalArticleScientificpeer-review

8 Downloads (Pure)

Abstract

Time-Sensitive Networking (TSN) and Deterministic Networking (DetNet) technologies are increasingly recognized as key levers of the future 5G transport networks (TNs) due to their capabilities for providing deterministic Quality-ofService and enabling the coexistence of critical and best-effort services. Additionally, they rely on programmable and costeffective Ethernet-based forwarding planes. In this article, we address the flow allocation problem in 5G backhaul networks realized as asynchronous TSN networks, whose building block is the Asynchronous Traffic Shaper. We propose an offline solution, dubbed Next Generation Transport Network Optimizer (NEPTUNO), that combines exact optimization methods and heuristic techniques and leverages data analytics to solve the flow allocation problem. NEPTUNO aims to maximize the flow acceptance ratio while guaranteeing the deterministic Qualityof-service requirements of the critical flows. We carried out a performance evaluation of NEPTUNO in terms of the degree of optimality, execution time, and flow rejection ratio. Furthermore, we compare NEPTUNO with two online baseline solutions. Online methods compute the flows allocation configuration right after the flow arrives at the network, whereas offline solutions like NEPTUNO compute a long-term configuration allocation for the whole network. Our results highlight the potential of the data analytics for the self-optimization of the future 5G TNs.
Original languageEnglish
Number of pages16
JournalIEEE Transactions on Mobile Computing
DOIs
Publication statusE-pub ahead of print - 26 Jul 2021
MoE publication typeA1 Journal article-refereed

Keywords

  • transport networks
  • QoS
  • Performance guarantees
  • Flow Allocation
  • Time-Sensitive Networking
  • 5G
  • Data Analytics
  • Asynchronous Traffic Shaper

Fingerprint

Dive into the research topics of 'Optimization of Flow Allocation in Asynchronous Deterministic 5G Transport Networks by Leveraging Data Analytics'. Together they form a unique fingerprint.

Cite this