Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Performance Evaluation of QUIC vs TCP for Cloud Control Systems

Peng, Haorui LU orcid ; Tärneberg, William LU ; Fitzgerald, Emma LU orcid and Kihl, Maria LU (2023) 31st International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2023
Abstract
QUIC is a UDP-based transport layer protocol developed by Google that boasts lower latency performance than TCP. However, different conclusions have been reported regarding its performance due to variations in targeted applications and experimental setups. This leads to our conclusion that protocol performance evaluation should be heavily dependent on the QoS requirements of the target application. Therefore, in this paper, we evaluate the performance of QUIC in the context of cloud control systems by comparing it with TCP and TCP-based protocols. We performed the evaluation under two different cloud environments: a private edge cluster and public cloud. Meanwhile, different networks were utilized under different evaluation scenarios,... (More)
QUIC is a UDP-based transport layer protocol developed by Google that boasts lower latency performance than TCP. However, different conclusions have been reported regarding its performance due to variations in targeted applications and experimental setups. This leads to our conclusion that protocol performance evaluation should be heavily dependent on the QoS requirements of the target application. Therefore, in this paper, we evaluate the performance of QUIC in the context of cloud control systems by comparing it with TCP and TCP-based protocols. We performed the evaluation under two different cloud environments: a private edge cluster and public cloud. Meanwhile, different networks were utilized under different evaluation scenarios, including 5G, Ethernet LAN and Internet. Our objective is to determine if QUIC can meet the quality of service requirements of a cloud control system. By focusing on this specific use case, we aim to provide a more comprehensive understanding of the potential benefits and limitations of QUIC on cloud control systems. From our evaluation results, we concluded that the performance of different protocols varies based on the characteristics of different control systems. However, QUIC offers more advantages for deploying and enhancing more time-critical systems. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Cloud control systems, QUIC, Transport layer protocols
host publication
The 31st International Conference on Software, Telecommunications and Computer Networks - SoftCOM 2023
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
31st International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2023
conference location
Split, Croatia
conference dates
2023-09-21 - 2023-09-23
external identifiers
  • scopus:85174519495
ISBN
979-8-3503-0107-6
DOI
10.23919/SoftCOM58365.2023.10271592
project
Design, optimisation and control of cloud-integrated autonomous networked systems
language
English
LU publication?
yes
id
b4c45405-3445-4366-b858-79d93d327f0d
date added to LUP
2023-10-11 10:57:24
date last changed
2023-12-18 13:28:50
@inproceedings{b4c45405-3445-4366-b858-79d93d327f0d,
  abstract     = {{QUIC is a UDP-based transport layer protocol developed by Google that boasts lower latency performance than TCP. However, different conclusions have been reported regarding its performance due to variations in targeted applications and experimental setups. This leads to our conclusion that protocol performance evaluation should be heavily dependent on the QoS requirements of the target application. Therefore, in this paper, we evaluate the performance of QUIC in the context of cloud control systems by comparing it with TCP and TCP-based protocols. We performed the evaluation under two different cloud environments: a private edge cluster and public cloud. Meanwhile, different networks were utilized under different evaluation scenarios, including 5G, Ethernet LAN and Internet. Our objective is to determine if QUIC can meet the quality of service requirements of a cloud control system. By focusing on this specific use case, we aim to provide a more comprehensive understanding of the potential benefits and limitations of QUIC on cloud control systems. From our evaluation results, we concluded that the performance of different protocols varies based on the characteristics of different control systems. However, QUIC offers more advantages for deploying and enhancing more time-critical systems.}},
  author       = {{Peng, Haorui and Tärneberg, William and Fitzgerald, Emma and Kihl, Maria}},
  booktitle    = {{The 31st International Conference on Software, Telecommunications and Computer Networks - SoftCOM 2023}},
  isbn         = {{979-8-3503-0107-6}},
  keywords     = {{Cloud control systems; QUIC; Transport layer protocols}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Performance Evaluation of QUIC vs TCP for Cloud Control Systems}},
  url          = {{https://lup.lub.lu.se/search/files/162076810/1570917060.pdf}},
  doi          = {{10.23919/SoftCOM58365.2023.10271592}},
  year         = {{2023}},
}