Bayesian_Optimization_of_Queuing_based_Multi_Channel_URLLC_Scheduling__Transaction.pdf (756.11 kB)
Download file

Bayesian optimization of queuing-based multi-channel URLLC scheduling

Download (756.11 kB)
journal contribution
posted on 22.09.2022, 11:03 authored by Wenheng ZhangWenheng Zhang, Mahsa DerakhshaniMahsa Derakhshani, Gan Zheng, Chung Shue Chen, Sangarapillai LambotharanSangarapillai Lambotharan

This paper studies the allocation of shared resources between ultra-reliable low-latency communication (URLLC) and enhanced mobile broadband (eMBB) in the emerging 5G and beyond cellular networks. In this paper, we design a unique queuing mechanism for the joint eMBB/URLLC system. The aim is to flexibly schedule URLLC traffic to enhance the total eMBB throughput and the reliability of URLLC packets (i.e., the probability of not dropping URLLC packets in each mini-slot) while maintaining a satisfactory transmission latency as per the 3GPP requirements. Precisely, by deriving the steady-state probabilities of URLLC queue backlog analytically, we formulate a stochastic optimization problem to maximize the total normalized eMBB throughput and the URLLC utility. Due to the stochastic nature of the objective function, it is expensive to evaluate it for any set of inputs, and thus the Bayesian optimization is applied to obtain the optimal results of such a black-box objective function. Numerical results demonstrate that the proposed queuing mechanism never violates the latency requirement of the URLLC services but improves the reliability. It also enhances the total normalized eMBB throughput as compared to the method without queuing.

Funding

Royal Academy of Engineering under the Leverhulme Trust Research Fellowship scheme (Derakhshani-LTRF1920\16\67)

Leverhulme Trust Research Project Grant under grant number RPG-2017-129

Unlocking Potentials of MIMO Full-duplex Radios for Heterogeneous Networks (UPFRONT)

Engineering and Physical Sciences Research Council

Find out more...

Communications Signal Processing Based Solutions for Massive Machine-to-Machine Networks (M3NETs)

Engineering and Physical Sciences Research Council

Find out more...

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Published in

IEEE Transactions on Wireless Communications

Publisher

Institute of Electrical and Electronics Engineers

Version

AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) license to any Author Accepted Manuscript version arising.

Acceptance date

29/08/2022

Publication date

2022-09-21

Copyright date

2022

ISSN

1536-1276

eISSN

1558-2248

Language

en

Depositor

Dr Mahsa Derakhshani. Deposit date: 21 September 2022