2025
Carlos Eduardo Menin, Igor Martins Silva, Vinícius Boff Alves, Gabriel Lando, Cristiano Bonato Both, José Marcos Silva Nogueira, Juliano Araujo Wickboldt
Explainable performance analysis of open-source 5G core network implementations via observability Inproceedings
In: 11th IEEE International Conference on Network Softwarization, NetSoft 2025, Budapest, Hungary, Jun 23-27, 2025, pp. 397-405, IEEE, 2025, ISSN: 2693-9789, (Best student paper award).
Abstract Links BibTeX Tags: 5G Microservices Network Virtualization & Slicing Observability
@inproceedings{conf/netsoft/Menin5GCore25,
title = {Explainable performance analysis of open-source 5G core network implementations via observability},
author = {Carlos Eduardo Menin and Igor Martins Silva and Vinícius Boff Alves and Gabriel Lando and Cristiano Bonato Both and José Marcos Silva Nogueira and Juliano Araujo Wickboldt},
url = {https://ieeexplore.ieee.org/abstract/document/11080540},
doi = {10.1109/NetSoft64993.2025.11080540},
issn = {2693-9789},
year = {2025},
date = {2025-06-23},
urldate = {2025-06-23},
booktitle = {11th IEEE International Conference on Network Softwarization, NetSoft 2025, Budapest, Hungary, Jun 23-27, 2025},
pages = {397-405},
publisher = {IEEE},
abstract = {The advent of fifth-generation mobile networks (5G) has brought transformative improvements in data transfer speeds, latency reduction, and device connectivity, enabled by the softwarization, virtualization, and disaggregation of network functions. Open-source projects have been instrumental in facilitating software-driven 5G deployments on standard hardware, accelerating the development of private 5G networks, test environments, and advancing research and innovation in the domain. Despite these advancements, the current maturity of open-source solutions remains inadequate for high-performance, large-scale 5G deployments. Existing 5G performance testing approaches primarily adopt a black-box perspective, which fails to capture the intricate interactions among core 5G components, thereby hindering the identification of performance bottlenecks. Additionally, testing is often limited to small-scale environments, and publicly available datasets from real-world deployments are scarce. To overcome these challenges, this paper introduces an observability-driven methodology for testing 5G core network performance, offering deeper insights into the internal interactions of network components. We contribute to research and innovation in 5G and beyond field by (i) enabling the simulation of varying user arrival rates, (ii) releasing a public dataset capturing data of 5G core components interactions, logs, and performance metrics, and (iii) providing a comparative analysis of two popular open-source 5G core implementations based on our observability-oriented methodology.},
note = {Best student paper award},
keywords = {5G, Microservices, Network Virtualization & Slicing, Observability},
pubstate = {published},
tppubtype = {inproceedings}
}
The advent of fifth-generation mobile networks (5G) has brought transformative improvements in data transfer speeds, latency reduction, and device connectivity, enabled by the softwarization, virtualization, and disaggregation of network functions. Open-source projects have been instrumental in facilitating software-driven 5G deployments on standard hardware, accelerating the development of private 5G networks, test environments, and advancing research and innovation in the domain. Despite these advancements, the current maturity of open-source solutions remains inadequate for high-performance, large-scale 5G deployments. Existing 5G performance testing approaches primarily adopt a black-box perspective, which fails to capture the intricate interactions among core 5G components, thereby hindering the identification of performance bottlenecks. Additionally, testing is often limited to small-scale environments, and publicly available datasets from real-world deployments are scarce. To overcome these challenges, this paper introduces an observability-driven methodology for testing 5G core network performance, offering deeper insights into the internal interactions of network components. We contribute to research and innovation in 5G and beyond field by (i) enabling the simulation of varying user arrival rates, (ii) releasing a public dataset capturing data of 5G core components interactions, logs, and performance metrics, and (iii) providing a comparative analysis of two popular open-source 5G core implementations based on our observability-oriented methodology.
Carlos Eduardo Menin, Igor Martins Silva, Vinícius Boff Alves, Gabriel Lando, Cristiano Bonato Both, José Marcos Silva Nogueira, Juliano Araujo Wickboldt
Enabling cloud-native observability for white-box performance analysis of the 5G core Inproceedings
In: 38th IEEE/IFIP Network Operations and Management Symposium, NOMS 2025, Honolulu, HI, USA, May 12-16, 2025, pp. 1–6, IEEE, 2025, ISSN: 2374-9709, (Experience session paper).
Abstract Links BibTeX Tags: 5G Microservices Network Virtualization & Slicing Observability
@inproceedings{conf/noms/Menin5GCore25,
title = {Enabling cloud-native observability for white-box performance analysis of the 5G core},
author = {Carlos Eduardo Menin and Igor Martins Silva and Vinícius Boff Alves and Gabriel Lando and Cristiano Bonato Both and José Marcos Silva Nogueira and Juliano Araujo Wickboldt},
url = {https://ieeexplore.ieee.org/abstract/document/11073613},
doi = {10.1109/NOMS57970.2025.11073613},
issn = {2374-9709},
year = {2025},
date = {2025-05-12},
urldate = {2025-05-12},
booktitle = {38th IEEE/IFIP Network Operations and Management Symposium, NOMS 2025, Honolulu, HI, USA, May 12-16, 2025},
pages = {1--6},
publisher = {IEEE},
abstract = {The fifth generation of mobile networks (5G) has introduced significant advancements in data transfer rates, latency, and device density, empowered by softwarization, virtualization, and disaggregation of network functions. Open-source initiatives have played a crucial role in enabling software-based 5G network deployments on commodity hardware, driving the growth of private 5G networks and testbeds, and fostering research and innovation in the field. However, the maturity level of such open-source technologies is still insufficient for highly performant large-scale deployments. Current 5G performance testing methodologies rely predominantly on a black-box approach, which overlooks the complexity of interactions between 5G core components, limiting the ability to explain performance bottlenecks. To address this limitation, this paper proposes a new observability-driven methodology for 5G core network performance testing, which improves visibility into internal component interactions. We contribute to research and innovation in 5G and beyond field by (i) implementing testing workloads that are able to simulate varying user arrival rates and (ii) integrate a set of cloud-native observability tools to allow white-box performance evaluation of the 5G core.},
note = {Experience session paper},
keywords = {5G, Microservices, Network Virtualization & Slicing, Observability},
pubstate = {published},
tppubtype = {inproceedings}
}
The fifth generation of mobile networks (5G) has introduced significant advancements in data transfer rates, latency, and device density, empowered by softwarization, virtualization, and disaggregation of network functions. Open-source initiatives have played a crucial role in enabling software-based 5G network deployments on commodity hardware, driving the growth of private 5G networks and testbeds, and fostering research and innovation in the field. However, the maturity level of such open-source technologies is still insufficient for highly performant large-scale deployments. Current 5G performance testing methodologies rely predominantly on a black-box approach, which overlooks the complexity of interactions between 5G core components, limiting the ability to explain performance bottlenecks. To address this limitation, this paper proposes a new observability-driven methodology for 5G core network performance testing, which improves visibility into internal component interactions. We contribute to research and innovation in 5G and beyond field by (i) implementing testing workloads that are able to simulate varying user arrival rates and (ii) integrate a set of cloud-native observability tools to allow white-box performance evaluation of the 5G core.
2023
Gabriel Lando, Lucas Augusto Fonseca Schierholt, Mateus Paludo Milesi, Juliano Araujo Wickboldt
Evaluating the performance of open source software implementations of the 5G network core Inproceedings
In: 36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023, Miami, FL, USA, May 8-12, 2023, pp. 1–7, IEEE, 2023, ISSN: 2374-9709, (Mini conference paper).
Abstract Links BibTeX Tags: 5G Microservices Network Virtualization & Slicing
@inproceedings{conf/noms/Lando5GCore23,
title = {Evaluating the performance of open source software implementations of the 5G network core},
author = {Gabriel Lando and Lucas Augusto Fonseca Schierholt and Mateus Paludo Milesi and Juliano Araujo Wickboldt},
url = {https://ieeexplore.ieee.org/document/10154399},
doi = {10.1109/NOMS56928.2023.10154399},
issn = {2374-9709},
year = {2023},
date = {2023-05-08},
urldate = {2023-05-08},
booktitle = {36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023, Miami, FL, USA, May 8-12, 2023},
pages = {1--7},
publisher = {IEEE},
abstract = {Open source implementations of software-based network components have become a viable alternative to deploy and operate 5G networks. Although these implementations provide great flexibility, overall network performance becomes dependent not only on the choice of the software stack, but also on its combination with suitable hardware. In this context, performance testing becomes an essential tool to assess the behavior of these software-based mobile networks under different deployment scenarios. Therefore, the goal of this work is to analyze how the different open source implementations of the 5G network core behave for the execution of procedures at scale. To achieve this goal, we propose and apply performance tests on some of the main open source implementations of the 5G network core. We focus on the evaluation of the performance of two essential procedures: (i) the user equipment registration and session establishment and (ii) the streaming of user data over parallel data plane connections. Among the main results obtained, it was possible to observe that the open source implementation free5GC presents better performance regarding data plane bit rates, while Open5GS shows better stability during the registration process of multiple devices.},
note = {Mini conference paper},
keywords = {5G, Microservices, Network Virtualization & Slicing},
pubstate = {published},
tppubtype = {inproceedings}
}
Open source implementations of software-based network components have become a viable alternative to deploy and operate 5G networks. Although these implementations provide great flexibility, overall network performance becomes dependent not only on the choice of the software stack, but also on its combination with suitable hardware. In this context, performance testing becomes an essential tool to assess the behavior of these software-based mobile networks under different deployment scenarios. Therefore, the goal of this work is to analyze how the different open source implementations of the 5G network core behave for the execution of procedures at scale. To achieve this goal, we propose and apply performance tests on some of the main open source implementations of the 5G network core. We focus on the evaluation of the performance of two essential procedures: (i) the user equipment registration and session establishment and (ii) the streaming of user data over parallel data plane connections. Among the main results obtained, it was possible to observe that the open source implementation free5GC presents better performance regarding data plane bit rates, while Open5GS shows better stability during the registration process of multiple devices.
Rafael de Jesus Martins, Juliano Araujo Wickboldt, Lisandro Zambenedetti Granville
Assisted Monitoring and Security Provisioning for 5G Microservices-Based Network Slices with SWEETEN Journal Article
In: Journal of Network and Systems Management (JNSM), 31 (2), pp. 36, 2023, ISSN: 1573-7705.
Abstract Links BibTeX Tags: 5G Cloud Computing Microservices Network Orchestration Network Security Network Virtualization & Slicing
@article{journals/jnsm/Martins5GMS23,
title = {Assisted Monitoring and Security Provisioning for 5G Microservices-Based Network Slices with SWEETEN},
author = {Rafael de Jesus Martins and Juliano Araujo Wickboldt and Lisandro Zambenedetti Granville},
url = {https://link.springer.com/article/10.1007/s10922-023-09728-1},
doi = {10.1007/s10922-023-09728-1},
issn = {1573-7705},
year = {2023},
date = {2023-02-12},
urldate = {2023-02-12},
journal = {Journal of Network and Systems Management (JNSM)},
volume = {31},
number = {2},
pages = {36},
abstract = {5G networks have imposed a drastic shift in how mobile telecommunications must operate. In order to comply with the new requirements, solutions based on network function virtualization (NFV) and network slicing must be carried out. Regarding NFV in particular, the trend towards pulverizing the monolithic software in a microservices-based one carries network management challenges to operators. The deployment and integration of one or more network management software with the managed services is as important as it is delicate, as stringent requirements of 5G applications must be respected. In this paper, we propose SWEETEN as a solution for automating the deployment and transparently integrating network management solutions from different management disciplines, in this case, monitoring and security. Demonstrating its usability through a intelligent healthcare use case, SWEETEN is shown to transparently provide monitoring and security solutions for a complete network slice, enabling compliance with privacy requirements through minimal low-level interventions from the network slice tenant. The results show how SWEETEN integration of monitoring and security disciplines can assist users in guaranteeing the correct operation of their deployments regardless of the underlying software solutions used.},
keywords = {5G, Cloud Computing, Microservices, Network Orchestration, Network Security, Network Virtualization & Slicing},
pubstate = {published},
tppubtype = {article}
}
5G networks have imposed a drastic shift in how mobile telecommunications must operate. In order to comply with the new requirements, solutions based on network function virtualization (NFV) and network slicing must be carried out. Regarding NFV in particular, the trend towards pulverizing the monolithic software in a microservices-based one carries network management challenges to operators. The deployment and integration of one or more network management software with the managed services is as important as it is delicate, as stringent requirements of 5G applications must be respected. In this paper, we propose SWEETEN as a solution for automating the deployment and transparently integrating network management solutions from different management disciplines, in this case, monitoring and security. Demonstrating its usability through a intelligent healthcare use case, SWEETEN is shown to transparently provide monitoring and security solutions for a complete network slice, enabling compliance with privacy requirements through minimal low-level interventions from the network slice tenant. The results show how SWEETEN integration of monitoring and security disciplines can assist users in guaranteeing the correct operation of their deployments regardless of the underlying software solutions used.
2020
Rafael de Jesus Martins, Juliano Araujo Wickboldt, Lisandro Zambenedetti Granville
SWEETEN: Automated Network Management Provisioning for 5G Microservices-Based Virtual Network Functions Inproceedings
In: 16th International Conference on Network and Service Management, CNSM 2020, Virtual Conference, November 2-6, 2020, pp. 1-9, International Federation for Information Processing (IFIP), Virtual Conference, 2020, ISBN: 978-3-903176-31-7.
Abstract Links BibTeX Tags: 5G Cloud Computing Microservices Network Orchestration Network Virtualization & Slicing
@inproceedings{conf/cnsm/Martins20,
title = {SWEETEN: Automated Network Management Provisioning for 5G Microservices-Based Virtual Network Functions},
author = {Rafael de Jesus Martins and Juliano Araujo Wickboldt and Lisandro Zambenedetti Granville},
url = {http://dl.ifip.org/db/conf/cnsm/cnsm2020/1570662948.pdf},
isbn = {978-3-903176-31-7},
year = {2020},
date = {2020-11-02},
booktitle = {16th International Conference on Network and Service Management, CNSM 2020, Virtual Conference, November 2-6, 2020},
pages = {1-9},
publisher = {International Federation for Information Processing (IFIP)},
address = { Virtual Conference},
abstract = {Forthcoming 5G systems promise a myriad of new and improved applications, relying on Network Functions Virtualization (NFV) to realize some of 5G's stringent requirements. To guarantee that these requirements are met, network monitoring and management must be deployed and fine-tuned according each application's specificity. As Virtual Network Functions (VNFs) adhere to the microservice paradigm, picking and configuring the right tools is not a trivial task for users. In this paper, we present SWEETEN, a system that assists user to operate a 5G network with the appropriate management tools for the job, in a transparent manner to the user. By enriching their function stack with high-level annotation of the management features they desire, users can easily deploy an augmented stack with both network and management functions. A prototype is presented and evaluated in a dynamic Cloud Radio Access Network (C-RAN) split case study. The evaluation confirms that SWEETEN can assist users in effortlessly deploying complex management solutions, while incurring in acceptable deployment time overhead and negligible computational overhead for throughout the functions life-cycle.},
keywords = {5G, Cloud Computing, Microservices, Network Orchestration, Network Virtualization & Slicing},
pubstate = {published},
tppubtype = {inproceedings}
}
Forthcoming 5G systems promise a myriad of new and improved applications, relying on Network Functions Virtualization (NFV) to realize some of 5G's stringent requirements. To guarantee that these requirements are met, network monitoring and management must be deployed and fine-tuned according each application's specificity. As Virtual Network Functions (VNFs) adhere to the microservice paradigm, picking and configuring the right tools is not a trivial task for users. In this paper, we present SWEETEN, a system that assists user to operate a 5G network with the appropriate management tools for the job, in a transparent manner to the user. By enriching their function stack with high-level annotation of the management features they desire, users can easily deploy an augmented stack with both network and management functions. A prototype is presented and evaluated in a dynamic Cloud Radio Access Network (C-RAN) split case study. The evaluation confirms that SWEETEN can assist users in effortlessly deploying complex management solutions, while incurring in acceptable deployment time overhead and negligible computational overhead for throughout the functions life-cycle.
Rafael de Jesus Martins, Rodolfo Bruno Hecht, Ederson Ribas Machado, Jéferson Campos Nobre, Juliano Araujo Wickboldt, Lisandro Zambenedetti Granville
Micro-service Based Network Management for Distributed Applications Inproceedings
In: 34th IEEE International Conference on Advanced Information Networking and Applications, AINA 2020, Caserta, Italy, April 15-17, 2020, pp. 922–933, Springer International Publishing, 2020, ISBN: 978-3-030-44041-1.
Abstract Links BibTeX Tags: Cloud Computing Microservices Network Orchestration Network Virtualization & Slicing
@inproceedings{conf/aina/Martins20,
title = {Micro-service Based Network Management for Distributed Applications},
author = {Rafael de Jesus Martins and Rodolfo Bruno Hecht and Ederson Ribas Machado and Jéferson Campos Nobre and Juliano Araujo Wickboldt and Lisandro Zambenedetti Granville},
url = {https://doi.org/10.1007/978-3-030-44041-1_80},
doi = {10.1007/978-3-030-44041-1_80},
isbn = {978-3-030-44041-1},
year = {2020},
date = {2020-04-15},
booktitle = {34th IEEE International Conference on Advanced Information Networking and Applications, AINA 2020, Caserta, Italy, April 15-17, 2020},
pages = {922--933},
publisher = {Springer International Publishing},
abstract = {Computer networks and their services have become increasingly dynamic with the introduction of concepts such as Network Functions Virtualization (NFV) and cloud computing. To understand and configure such a complex network to their best interests, users must use several management tools that they are not necessarily familiar with. In this paper, we present an architecture that provides network management for distributed applications as easy-to-use micro-services. Our solution is based on container virtualization technologies to offer, to the user, the maximum benefit through minimal cost. We present a proof-of-concept for our architecture through a use case. Our results show that acceptable overhead is added when deploying a solution for a distributed application, and negligible overhead is added by the management tools when the user application is under heavy stress.},
keywords = {Cloud Computing, Microservices, Network Orchestration, Network Virtualization & Slicing},
pubstate = {published},
tppubtype = {inproceedings}
}
Computer networks and their services have become increasingly dynamic with the introduction of concepts such as Network Functions Virtualization (NFV) and cloud computing. To understand and configure such a complex network to their best interests, users must use several management tools that they are not necessarily familiar with. In this paper, we present an architecture that provides network management for distributed applications as easy-to-use micro-services. Our solution is based on container virtualization technologies to offer, to the user, the maximum benefit through minimal cost. We present a proof-of-concept for our architecture through a use case. Our results show that acceptable overhead is added when deploying a solution for a distributed application, and negligible overhead is added by the management tools when the user application is under heavy stress.