Optimizing Public Edge Clouds Computing Environment for Telecom Application

No Thumbnail Available

URL

Journal Title

Journal ISSN

Volume Title

Sähkötekniikan korkeakoulu | Master's thesis

Date

2023-05-15

Department

Major/Subject

Cloud and Network Infrastructures

Mcode

ELEC3059

Degree programme

Master's Programme in ICT Innovation

Language

en

Pages

80 + 10

Series

Abstract

The goal of this internship is to benchmark and optimize the performance characteristics of public cloud computing environments for telecom applications. This will be done by conducting tests using different system configurations to evaluate the impact of the baseline workload on the Amazon Web Services (AWS) public cloud computing environment using a system equipped with an ARM SoC. The tests will focus on Operating System scheduling, latency, and memory performance, and will help to understand the behavior of the system and the relationships between its performance parameters. The results of the tests will be analyzed and used to identify the most effective parameters configuration for the virtualized Distributed Unit (vDU) telecom application on the AWS environment. The work will be described in the context of 5G technology, with a focus on 5G architecture, Cloud RAN, and the vRAN with the vDU. The first test scenario was conducted using the cyclictest tool and the Raspberry Pi 4 environment to validate system tunings and understand the effects on latency. Then, the tests were then conducted on various AWS instances with different hardware resources using the ODP test tool, and on a bare metal instance running the Graviton 2 ARM-based SoC. The results showed overall improvements in performance with the tunings applied, especially in latency, and confirmed the benefits of using the Amazon Linux 2 operating system.

Description

Supervisor

Spathis, Promèthèe

Thesis advisor

Manner, Jukka

Keywords

5G, edgecCloud, performance tests, optimization

Other note

Citation