Throughput Maximization and Latency Optimization in Fifth-Generation Networks Using a Multistage Machine Learning for Early Hybrid Automatic Repeat Request

Aug 5, 2026

Upload by Aurelia

The physical layer Hybrid Automatic Repeat Request (HARQ) protocol supports low error-rate transmission and high reliability in 5G Ultra-Reliable Low Latency Communication (URLLC) networks. Its main drawback is increased transmission latency, driven largely by receiver channel-decoding delay and the need to wait for acknowledgement. This study introduces multistage machine learning Early HARQ (E-HARQ) to predict acknowledgement prior to decoding. A multistage decision mitigates throughput loss from incorrect predictions by adapting bandwidth using channel state information (CSI).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages85

Reading Time3 h 34 min

AccessFree to download

Chapter 1 - Introduction

Introduction

Problem statement

Research motivation

Literature review

Aim and objectives

Research questions

Methodology

THROUGHPUT MAXIMIZATION AND LATENCY OPTIMIZATION IN FIFTHGENERATION NETWORKS USING A MULTISTAGE MACHINE LEARNING FOR EARLY HYBRID AUTOMATIC REPEAT REQUEST By Nhlanhla Patrick Hlewane DISSERTATION Submitted in fulfilment of the requirements for the degree of MASTER OF SCIENCE in the FACULTY OF SCIENCE AND AGRICULTURE (School of Mathematical and Computer Sciences) at the UNIVERSITY OF LIMPOPO Supervisor: Prof. Mthulisi Velempini 2023 DEDICATION This dissertation is dedicated to my beloved people: My mother, Martha Hlewane. My sister, Siphokazi Hlewane. My aunts, Siphiwe and Nomsa Msimango. DECLARATION I, Nhlanhla Patrick Hlewane hereby declare that this dissertation titled: THROUGHPUT MAXIMIZATION AND LATENCY OPTIMIZATION IN FIFTHGENERATION NETWORKS USING A MULTISTAGE MACHINE LEARNING FOR EARLY HYBRID AUTOMATIC REPEAT REQUEST submitted at the University of Limpopo for master’s degree is my original work and has not been previously submitted to any university or institution of higher learning. I further declare that all the sources cited are acknowledged and correctly referenced. Signature: Nhlanhla Patrick Hlewane Date: 17 November 2022 ACKNOWLEDGMENTS I thank the almighty God for strengthening me throughout this journey. To myself for not giving up. To my supervisor, Professor Mthulisi Velempini, thank you for your guidance throughout this journey. It was not simple at all for me, but your availability every time I needed help made the journey much lighter. Your feedback, comments and advice have grown me so much. To my mother, Martha Hlewane , thank you for caring and loving. You always told me not to give up. To all my colleagues in the Department of Computer Sciences, thank you a lot for your amazing support. I also acknowledge the University of Limpopo for this opportunity granted to me. ABSTRACT The physical layer Hybrid Automatic Repeat Request (HARQ) protocol efficiently achieves low error-rate transmission and high network reliability in the fifth generation (5G) Ultra Reliable Low Latency Communication (URLLC) network. However, this retransmission protocol suffers from increased transmission latency resulting mainly from the delay caused by channel decoding. This problem is caused by the fact that the sender has to wait for acknowledgement of the transmission which is generated after the decoding process at the receiver, resulting in increased latency. To address the latency problem, this study proposed the multistage machine learning Early HARQ (E-HARQ) which uses machine learning algorithms for predicting the acknowledgement before the decoding process. Furthermore, the proposed scheme uses the multistage decision to mitigate the throughput loss resulting from incorrect predictions of the acknowledgement. The multistage decision controls the transmission bandwidth in a multilevel manner depending on channel conditions measured by the Channel State Information (CSI) . The study used jupyter notebook and MATLAB for developing the proposed scheme and then evaluating its performance. Simulation results show that the proposed scheme improves the achievable trade-off between the transmission latency and throughput which contributes to the performance of 5G URLLC networks. Keywords: Multistage decision, Hybrid Automatic Repeat Request (HARQ), machine learning, fifth generation (5G) TABLE OF CONTENTS DEDICATION ............................................................................................................................................. i DECLARATION ......................................................................................................................................... ii ACKNOWLEDGMENTS ............................................................................................................................ iii ABSTRACT.........................................................................................................

FAQs

Why does HARQ in 5G URLLC increase transmission latency?

Because the sender must wait for acknowledgement that is generated only after receiver channel decoding, which adds delay.

What is the purpose of the proposed Early HARQ (E-HARQ) scheme?

To reduce latency by using machine learning to predict acknowledgement before the decoding process, rather than after decoding.

How does the multistage decision improve throughput reliability?

It uses channel state information (CSI) to control transmission bandwidth in multiple levels, mitigating throughput loss caused by incorrect acknowledgement predictions.

Aug 5, 2026

Upload by Aurelia