TY - GEN
T1 - Towards Digital Network Twins
T2 - 9th IEEE International Conference on Network Softwarization, NetSoft 2023
AU - Ursu, Razvan Mihai
AU - Zerwas, Johannes
AU - Kramer, Patrick
AU - Asadi, Navidreza
AU - Rodgers, Phil
AU - Wong, Leon
AU - Kellerer, Wolfgang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85166484028&partnerID=8YFLogxK
U2 - 10.1109/NetSoft57336.2023.10175422
DO - 10.1109/NetSoft57336.2023.10175422
M3 - Conference contribution
AN - SCOPUS:85166484028
T3 - 2023 IEEE 9th International Conference on Network Softwarization: Boosting Future Networks through Advanced Softwarization, NetSoft 2023 - Proceedings
SP - 438
EP - 443
BT - 2023 IEEE 9th International Conference on Network Softwarization
A2 - Bernardos, Carlos J.
A2 - Martini, Barbara
A2 - Rojas, Elisa
A2 - Verdi, Fabio Luciano
A2 - Zhu, Zuqing
A2 - Oki, Eiji
A2 - Parzyjegla, Helge
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 June 2023 through 23 June 2023
ER -