AI/ML-aided capacity maximization strategies for URLLC in 5G/6G wireless systems: A survey

Razeena Begum Shaik, Prabagarane Nagaradjane, Iacovos Ioannou, Vitawat Sittakul, Vasos Vasiliou, Andreas Pitsillides

Research output: Contribution to journalShort surveypeer-review

Abstract

Ultra-reliable low-latency communication (URLLC) refers to cellular applications in fifth and sixth-generation (5G/6G) networks with specific latency, reliability, and availability demands. Most of the reported 5G/6G applications are focused on URLLC, which necessitates a latency of milliseconds and very high dependability for transmitted data. These systems encounter several obstacles since conventional networks cannot fulfill such demands. According to the standards of the 3rd generation partnership project URLLC, it is predicted that the dependability of a single transmission of a 32-byte packet would be no less than 99.999%, and the latency will not exceed 1 ms. The exceptional degree of dependability and minimal delay will result in the emergence of many novel applications, including smart grids, industrial automation, and intelligent transport systems. This review discusses several methods for maximizing capacity in URLLC, focusing on resource allocation strategies, multi-access approaches, and beamforming with massive MIMO. Furthermore, it explores the requirements and constraints of URLLC and the role of AI/ML in URLLC. Finally, this study examines possible future research areas and obstacles to achieving the URLLC standards.

Original languageEnglish
Article number110506
JournalComputer Networks
Volume249
DOIs
Publication statusPublished - Jul 2024

Keywords

  • Artificial intelligence
  • Beamforming
  • Capacity maximization
  • Machine learning
  • Resource allocation
  • URLLC

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'AI/ML-aided capacity maximization strategies for URLLC in 5G/6G wireless systems: A survey'. Together they form a unique fingerprint.

Cite this