Towards Digital Network Twins: Can we Machine Learn Network Function Behaviors?

Razvan Mihai Ursu, Johannes Zerwas, Patrick Kramer, Navidreza Asadi, Phil Rodgers, Leon Wong, Wolfgang Kellerer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Cluster orchestrators such as Kubernetes (K8s) provide many knobs that cloud administrators can tune to conFigure their system. However, different configurations lead to different levels of performance, which additionally depend on the application. Hence, finding exactly the best configuration for a given system can be a difficult task. A particularly innovative approach to evaluate configurations and optimize desired performance metrics is the use of Digital Twins (DT). To achieve good results in short time, the models of the cloud network functions underlying the DT must be minimally complex but highly accurate. Developing such models requires detailed knowledge about the system components and their interactions. We believe that a data-driven paradigm can capture the actual behavior of a network function (NF) deployed in the cluster, while decoupling it from internal feedback loops. In this paper, we analyze the HTTP load balancing function as an example of an NF and explore the data-driven paradigm to learn its behavior in a K8s cluster deployment. We develop, implement, and evaluate two approaches to learn the behavior of a state-of-The-Art load balancer and show that Machine Learning has the potential to enhance the way we model NF behaviors.

Original languageEnglish
Title of host publication2023 IEEE 9th International Conference on Network Softwarization
Subtitle of host publicationBoosting Future Networks through Advanced Softwarization, NetSoft 2023 - Proceedings
EditorsCarlos J. Bernardos, Barbara Martini, Elisa Rojas, Fabio Luciano Verdi, Zuqing Zhu, Eiji Oki, Helge Parzyjegla
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages438-443
Number of pages6
ISBN (Electronic)9798350399806
DOIs
StatePublished - 2023
Event9th IEEE International Conference on Network Softwarization, NetSoft 2023 - Madrid, Spain
Duration: 19 Jun 202323 Jun 2023

Publication series

Name2023 IEEE 9th International Conference on Network Softwarization: Boosting Future Networks through Advanced Softwarization, NetSoft 2023 - Proceedings

Conference

Conference9th IEEE International Conference on Network Softwarization, NetSoft 2023
Country/TerritorySpain
CityMadrid
Period19/06/2323/06/23

Fingerprint

Dive into the research topics of 'Towards Digital Network Twins: Can we Machine Learn Network Function Behaviors?'. Together they form a unique fingerprint.

Cite this