PORVIR-5G Project

Description Members Opportunities Publications Development News Acknowledgement

Description

The expected massive growth of mobile Internet traffic in 5G mobile networks introduces the need to change the operators’ networks. Such networks require a drastic transformation towards open, scalable and elastic ecosystems supporting new types of communication. The PORVIR-5G project will develop and demonstrate a programmable fronthaul and backhaul integrating wireless with optical-packet networks and cloud solutions. It is intended to exploit virtual network splits that optimise resource allocation across the wireless, optical, packet, and compute/storage domains. Key enablers for PORVIR-5G are (i) Slicing over packet, wireless, and optical resources, controlled by (ii) deep programmability interfaces, where the devices are configured by network functions to provide the required performance for the future applications on the Internet. This programmability allows a more refined (iii) end-to-end and multilayer orchestration, considering the quality of experience of the users for each type of applications over the network. This project will validate and demonstrate the proposed programmability and virtualization capabilities in three demonstrations, each one of them enabling the key performance demands of 5G networks: an Internet of Things demonstrator focusing on massive machine-type communication; a smart city demonstration for reliable and ultra-low latency flows; and a high bandwidth video demonstrator showcasing the next-generation mobile broadband.

Acknowledgement

PORVIR-5G Project has received funding from the Brazilian Ministry of Science, Technology and Innovation (MCTI) through FAPESP.

Members

Opportunities

Open opportunities to join our team.

#1 - Post-doctoral fellowship in 5G slicing, orchestration, and programmability

Possible working places (universities in Brazil): UFMG, UFES, UFRGS, UNICAMP, UNISINOS

Post-doctoral fellowship: Monthly stipend of R$ 12,000 (about USD 2,200 or EUR 2,000) plus research contingency funds and moving assistance.

Deadline to apply: November 15th, 2024

Beginning at: Dez 2024 or Jan 2025

Duration: 12 months

Application: https://forms.gle/CxeuBrpBsumHvvKq7

We are seeking **two candidates** for a 12-month postdoctoral fellowship to work on a joint research project among these Brazilian institutions or universities: UFMG, UFES, UFRGS, UNICAMP, UNISINOS. The place of work is flexible, in one of the cities of the partners. The selected candidate will be allocated to one of the partner universities and will work with consortium researchers.

This scholarship is part of the Project, entitled “Programmability, Orchestration, and Virtualization on 5G Networks” (PORVIR-5G), which aims to develop new architectures and mechanisms to improve 5G networks in general. The post-doc candidate will work on the use of AI and machine learning in the orchestration of 5G, B5G, and 6G networks, as well as network slicing and programmability of virtual networks. The project focuses on some of the 5G verticals, namely ultra-high quality video, autonomous drones, and Industry 4.0. More information at: https://porvir-5g-project.github.io/

To succeed in this position, you are expected to have:

How to apply

Interested candidates should fill out the online form by 31 October, 2024, by adding the documents listed below:

  1. A motivation letter for the application;
  2. Curriculum vitae, with list of publications, education background, research track-record, and previous experience;
  3. Ph.D. degree certificate (Thesis defense must be up to 7 years);

The most suited candidates will be invited for an interview (via videoconference) in the week following the application deadline.

Additional Information

Eligibility Criteria: Ph.D. in Computer Science or related areas. The post-doctoral fellowship includes a monthly stipend of R$ 12,000 (about USD 2,200 or EUR 2,000), and research contingency funds (10% of the annual value of the fellowship, each year). For more details, check out Fapesp’s webpage https://fapesp.br/en/postdoc . Additionally, there is the possibility of an installation aid for the scholarship holder that lives in a different domicile and needs to move to the city where the host institution in which the scholarship will be developed is located. For journeys equal to or greater than 350 km, he/she will have an additional monthly scholarship fee and resources to cover land transportation and/or air transportation expenses in the promotional or economic category, for the scholarship holder, spouse and dependents.

Publications

MACHADO, A. A. ; FIOROTTI, R. ; VILLACA, R. S. ; ROCHA, H. R. O. . Profit distribution through blockchain solution from battery energy storage system in a virtual power plant using intelligence techniques. Journal Of Energy Storage, v. 98, p. 113150, 2024. Abstract: The implementation of Virtual Power Plants (VPPs) with appropriate energy management can provide consumer units (CUs) with a significant reduction in energy purchase costs and stimulate the use of distributed generation from renewable energy sources, thereby reducing the environmental impact of the energy sector. This study presents a new methodology that integrates meteorological forecasts to estimate renewable energy production through mathematical models and from the day-ahead demands forecast, the Whale Optimization Algorithm (WOA) is applied to optimize the Battery Energy Storage System (BESS) parameters to minimize the total VPPs energy costs. Additionally, a smart contract was written in Solidity and implements user registration, an oracle mechanism to integrate real-world data on-chain, such as Time-of-Use (TOU) prices and feed-in tariffs. An optimization-based profit distribution algorithm is employed to distribute the value generated by the Demand Side Management (DSM) operation among all participants, utilizing Load Factor and a modified Peak-to-Average Ratio. The study case results show a cost reduction of 22.63%, the energy consumption at the peak periods reduced by 48.67%, and 83.53% of the energy exported into the grid, due to the aggregation of the CUs and the BESS implementation. Results from DSM’s blockchain-based system have achieved savings for consumer units ranging from 10.41% to 114.80%. The savings of 114.80% represents a nominal profit of 14.80% compared to the previous cost (without DSM). The profit distribution mechanism plays an important role in encouraging consumer units to improve their demand profile in order to maximize the efficiency of the DSM system and consequently obtain financial benefits. Finally, the Deployment costs and operational expenses of the proposed DSM smart contract on various Ethereum-based blockchains are also analyzed, providing insights into the feasibility and scalability of the system. URL: http://dx.doi.org/10.1016/j.est.2024.113150


SARMENTO, EDUARDO MONTAGNER DE MORAES ; RIBEIRO, IRAN FREITAS ; MARCIANO, PABLO RAFAEL NEVES ; NERIS, YRUI GIOVAN ; ROCHA, HELDER ROBERTO DE OLIVEIRA ; MOTA, VINÍCIUS FERNANDES SOARES ; Villaça, Rodolfo da Silva . Forecasting energy power consumption using federated learning in edge computing devices. Internet Of Things, v. 25, p. 101050, 2024. Abstract: Several studies in the literature propose using machine learning algorithms to forecast consumers’ energy consumption. However, such data is sensitive and has privacy constraints. On the other hand, federated learning is a technique in which the training of machine learning algorithms is performed locally, where the data is generated. In this context, this article presents a hybrid neural network architecture, named CNN-LSTM FED, trained using the public Smart* and The Building Data Genome Project 2 datasets. Additionally, an augmented Smart* dataset was generated using Generative Adversarial Networks (GANs). The performance of CNN-LSTM FED was evaluated by comparing it against the MultiLayer Perceptron (MLP), which serves as a baseline, and against a non-federated version of the CNN-LSTM FED, named CNN-LSTM. Our approach was able to generalize the model even when less than 1% of buildings participated in the modeling process, forecasting with good results the energy consumption of other buildings. Furthermore, the deployment of this architecture in an edge computing device, with limited computational resources for training, is evaluated. URL: http://dx.doi.org/10.1016/j.iot.2023.101050


COELHO, W. B. ; ZANOTELLI, V. ; COMARELA, G. ; VILLACA, RODOLFO S. . RAVEN: Detecção e Classificação Precoce de Atores Maliciosos em uma Rede Acadêmica. In: XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024, Niteroi/RJ. XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024. Abstract: A varredura de portas é uma importante técnica de coleta de informações sensíveis, por isso, destacamos a necessidade de sistemas aprimorados de segurança e ressaltamos que a varredura, considerada uma anomalia, deve ser identificada e suprimida precocemente, especialmente diante do número significativo de incidentes reportados. Em resposta a esse desafio, propõe-se um sistema inteligente e automatizado que analisa fluxos de rede para detectar e classificar varreduras no menor tempo possível. As contribuições incluem a implementação e avaliação do sistema, a demonstração da melhoria do desempenho com a ampliação das features e a disponibilização de conjuntos de dados para a comunidade acadêmica. URL: https://sol.sbc.org.br/index.php/sbrc/article/view/29804


SANTOS, G. O. ; VILLACA, RODOLFO S. ; DOMINICINI, C. K. ; VASSOLER, G. L. ; GUIMARAES, R. S. ; PEREIRA, I. O. ; PARAISO, D. J. P. . MTS-PolKA: Divisão de tráfego multicaminhos em proporção de peso com roteamento na fonte. In: XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024, Niteroi/RJ. XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024. Abstract: O artigo apresenta a proposta inovadora chamada MTS-PolKA para otimizar o tráfego em redes de datacenters. Introduz um método dinâmico de divisão de tráfego com rótulos (routeIDs e weightIDs) no cabeçalho dos pacotes, utilizando tabelas estáticas nos switches para permitir ajustes flexíveis em tempo real, eliminando reconfigurações complexas. A abordagem emprega o roteamento na origem com o Protocolo M-Polka modificado, utilizando um sistema numérico de resíduos para roteamento de fonte sem armazenamento de estado e sem alterações nos hosts finais. O MTS-PolKA destaca-se pela agilidade na (re)configuração de caminhos e pesos, com o plano de controle calculando identificadores de rota (routeIDs), peso (weightIDs) e nó (nodeIDs). Experimentos demonstram a eficácia da solução, possibilitando reconfigurações ágeis de perfis de divisão de tráfego na origem, com potencial de melhorar o desempenho e eficiência em redes de datacenters. URL: https://sol.sbc.org.br/index.php/sbrc/article/view/29784


ZANOTELLI, V. ; BOTTACIN, W. E. ; MARTIN, M. S. ; MORAIS, P. I. G. ; COMARELA, G. ; VILLACA, RODOLFO DA SILVA ; MOTA, V. F. S. ; ROCHA, A. A. A. . Além da Conexão: Combinando Múltiplas Fontes de Dados para Entender e Prever Evasão de Internet Residencial. In: XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024, Niteroi/RJ. XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024. Abstract: A retenção de usuários é uma preocupação crescente entre os provedores de acesso à Internet residencial. Nesse contexto, este trabalho explora dados internos de uma multinacional de telecomunicações e da Anatel para treinamento de modelos de aprendizado de máquina visando a previsão de evasão de seus clientes. Uma análise inicial mostra o desempenho desses modelos, quem alcançaram resultados de acurácia próxima aos 80%, e precisão e recall na faixa dos 70%. Também são identificadas as características mais influentes na decisão de saída de um cliente, viabilizando a implementação da abordagem proposta em estratégias para mitigação do problema de evasão. URL: https://sol.sbc.org.br/index.php/sbrc/article/view/29802


DE MORAES SARMENTO, EDUARDO MONTAGNER ; MOTA, V. F. S. ; VILLACA, RODOLFO S. . Privacidade e Comunicação Eficiente em Aprendizado Federado: Uma abordagem utilizando estruturas de dados probabilísticas e seleção de clientes. In: XLII Simposio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024, Niteroi/RJ. XLII Simposio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024. Abstract: Para mitigar ataques de inferência e melhorar a eficiência de comunicação no aprendizado federado, este artigo propõe uma abordagem dupla: i) FedSketch, que utiliza estruturas de dados probabilísticas (sketches) para aumentar a privacidade e eficiência na comunicação, aplicando privacidade diferencial e compactação dos modelos; e ii) MetricBasedSelection, algoritmo de seleção de clientes com base em métricas personalizadas. A solução proposta reduziu o custo da comunicação, em até 73 vezes, mantendo acurácia similar ao aprendizado federado convencional, com altíssimo nível de privacidade diferencial (ϵ ≈ 10−6), representando uma abordagem eficaz para enfrentar desafios de privacidade e comunicação associados ao aprendizado federado. URL: https://sol.sbc.org.br/index.php/sbrc/article/view/29785


BRAGATTO, M. N. ; CLEVELARES, J. P. M. ; VILLACA, R. S. ; DOMINICINI, C. K. ; VERDI, FÁBIO LUCIANO . MM-INT: Telemetria em Switches Programáveis com Múltiplas Filas usando Roteamento Multicaminhos na Origem. In: XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024, Niteroi/RJ. XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2024), 2024. Abstract: Este artigo destaca a importância das filas associadas às portas dos switches no monitoramento de uma rede. Tradicionalmente, a coleta de dados sobre essas filas é feito com o uso de planos de dados programáveis, e telemetria baseada em sondas INT (In-band Network Telemetry), assumindo que há apenas uma única fila por porta de saída. O MM-INT (Multiqueue Multicast - INT) é uma solução que utiliza registradores para armazenar dados de todas as filas e de todas as portas, permitindo a coleta eficiente de informações de monitoramento. O MM-INT evita a sobrecarga de sondas e emprega o mecanismo de roteamento na origem e árvores multicaminhos para as sondas. Os resultados demonstram reduções significativas na quantidade de sondas enviadas, em comparação com outras soluções tradicionais da literatura. URL: https://sol.sbc.org.br/index.php/sbrc/article/view/29814


BASTOS, J. J. S. ; DE MORAES SARMENTO, EDUARDO MONTAGNER ; VILLACA, R. S. ; MOTA, V. F. S. . MiniNetFED: Uma Ferramenta para Emulação e Análise de Aprendizado Federado com Dispositivos Heterogêneos. In: Salão de Ferramentas do SBRC 2024, 2024, Niteroi/RJ. XLII Simpósio Brasileiro de Redes de Computadores e SIstemas Distribuídos (SBRC 2024), 2024. Abstract: Este artigo apresenta o MiniNetFed, uma ferramenta de emulação de um ambiente com dispositivos heterogêneos para análise de algoritmos de aprendizado federado. A ferramenta permite aos usuários definirem: i) modo de divisão do conjunto de dados entre os dispositivos; ii) políticas de seleção de clientes; iii) função de agregação de modelos; iv) utilizar modelos para os principais datasets disponíveis; e v) visualizações gráficas das principais métricas de desempenho. Por fim, além do potencial educacional, o MiniNetFed foi projetado de forma que novos algoritmos e modelos sejam facilmente estendidos, permitindo que pesquisadores implementem e avaliem suas propostas. URL: https://sol.sbc.org.br/index.php/sbrc_estendido/article/view/29955


RIBEIRO, IRAN FREITAS ; BROTTO, G. S. G. ; COMARELA, G. ; VILLAÇA, RODOLFO S. ; MOTA, V. F. S. . IoTTraffic: Assessing Generative Models for Internet of Things Attack Data Flows. In: 2024 IEEE 10th World Forum on Internet of Things (WF-IoT): Special Session - Cybersecurity Issues of IoT in Ambient Intelligence (Ami) Environment, 2024, Ottawa, Canada. 2024 IEEE 10th World Forum on Internet of Things (WF-IoT). New York / USA: IEEE, 2024. Abstract: Analyzing the data generated by gadgets is crucial for spotting and minimizing cyberattacks on the Internet of Things. However, public data representing real attacks still tends to be scarce. To increase data availability, this work presents a study on the use of Generative Adversarial Networks (GANs) to generate synthetic attack data on IoT devices with high fidelity to real data, i.e., with similar characteristics. Simultaneously, ensuring privacy and that the utility of synthetic data in machine learning tasks is similar to real data. For this purpose, two GAN models, CTGAN and NetShare, were compared using a dataset containing normal traffic and attacks on IoT devices. The results indicate that both GAN models are efficient in generating synthetic data, both in fidelity and quality. However, CTGAN proves to be the most efficient model, considering execution time and memory consumption. URL: To appear.


BATISTA, J. P. C. ; BASTOS, J. J. S. ; DE MORAES SARMENTO, EDUARDO MONTAGNER ; MOTA, V. F. S. ; VILLAÇA, RODOLFO S. . Mitigação de Ataques 'Label-Flipping' no Aprendizado Federado: Experimentos e Estratégias de Seleção de Clientes. In: IX Escola Regional de Informática do Espírito Santo (ERI-ES 2024), 2024, Vitória/ES. IX Escola Regional de Informática do Espírito Santo (ERI-ES 2024), 2024. Abstract: This article explores challenges affecting model efficacy in Federated Learning, particularly due to malicious clients engaging in attacks like "label-flipping". Through experiments in the MininetFed environment, it assesses the influence of these clients and the effectiveness of different client selection strategies and clustering algorithms in mitigating such specific attacks. The findings provide crucial insights for enhancing training process security and effectively safeguarding models in Federated Learning against internal threats. URL: To appear.


MOURA, H. D. ; OLIVEIRA, J. ; SOARES, D. H. C. M. ; MACEDO, DANIEL FERNANDES ; VIEIRA, Marcos Augusto Menezes "Improved Video QoE in Wireless Networks using Deep Reinforcement Learning." In: 19th International Conference on Network and Service Management (CNSM), 2023 Abstract: Millions of videos are watched per minute on the Internet. Due to real-time performance demands, such as high-quality video streaming, network administrators face new challenges to control the network and cope with the expected quality of experience (QoE). Automatic control is a necessity to reduce the OPEX, because it could reduce the need for resource overprovisioning, as well as the number of human administrators. Dynamic rate in video streaming alleviates the resource usage, but it worsens the video quality when a network bottleneck occurs, lowering the QoE. This paper dynamically adjusts the IEEE 802.11 parameters to improve the network condition and hence maintain a higher QoE. While traditional networks are not aware of the application, in our proposal the controller learns the configuration of the access points (APs) (in terms of transmission power and channel number) that provide the best QoE, using double deep Q-Learning (DDQL). The proposal improves video QoE by 91 % in the best case, when compared to three baselines. It also balances the QoE among clients, improving the fairness up to 115% when compared to the baselines. URL: https://doi.org/10.23919/CNSM59352.2023.10327822


Gilson Miranda; Jetmir Haxhibeqiri; Daniel F. Macedo; Johann M. Marquez-Barja "Soft-W-TSN: Extending Time-Sensitive Networking Capabilities to Wi-Fi Using Virtualized Elements." In: IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), 2023 Abstract: Industrial processes are becoming increasingly complex, demanding accurate monitoring and timely communication for process correction and optimization actions. Time-Sensitive Networking (TSN) comprises a set of standards being developed by IEEE to enable reliable and bounded low-latency communication over Ethernet networks. These standards allow an operator to have more control over traffic prioritization and latency, and offer features to enhance network communication reliability. Extending such features to wireless networks is a natural step in achieving more flexible deployments and supporting use cases involving mobility. In this work, we present an architecture and proof-of-concept to support extending TSN capabilities to Wi-Fi deployments and to enable flexible deployments of Wi-Fi access points tailored for different use cases. We show the experimental results with a testbed highlighting the main functionalities implemented to support an example use case. URL: https://doi.org/10.1109/NFV-SDN59219.2023.10329591


Franco, G., Crovella, M., Comarela, G. "Dependence and Model Selection in LLP: The Problem of Variants." In: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023 Abstract: The problem of Learning from Label Proportions (LLP) has received considerable research attention and has numerous practical applications. In LLP, a hypothesis assigning labels to items is learned using knowledge of only the proportion of labels found in predefined groups, called bags. While a number of algorithmic approaches to learning in this context have been proposed, very little work has addressed the model selection problem for LLP. Nonetheless, it is not obvious how to extend straightforward model selection approaches to LLP, in part because of the lack of item labels. More fundamentally, we argue that a careful approach to model selection for LLP requires consideration of the dependence structure that exists between bags, items, and labels. In this paper we formalize this structure and show how it affects model selection. We show how this leads to improved methods of model selection that we demonstrate outperform the state of the art over a wide range of datasets and LLP algorithms. URL: https://doi.org/10.1145/3580305.3599307


Cavalini, A., Malini, F., Gouveia, F., Comarela G. "Politics and disinformation: Analyzing the use of Telegram's information disorder network in Brazil for political mobilization" In: First Monday, 2023 Abstract: Over the past few years, with the increasing popularization of network communication in place of traditional mass communication, supported by social platforms and messengers, political campaigns have come to rely on new tools and methods, including the use of these structures to promote an environment of information disorder for the purpose of mobilization. This work followed the use of Telegram as a tool for political mobilization in Brazil, collecting data from a dense network of information disorder used to mobilize voters in support of then-president Jair Bolsonaro on 7 September 2021 and 2022, Independence Day in Brazil. The results showed that engagement was reduced, mainly due to the lack of support from certain groups such as anti-vaccination advocates and the truck drivers’ class. There was also a decrease in extremism on discussion themes and lower user activity levels. URL: https://doi.org/10.5210/fm.v28i5.12901


Martínez, V.M.G., Ribeiro, M.R.N., Mota, V.F.S. "Wi-Fi faces the new wireless ecosystem: a critical review." In: Annals of Telecommunications. vol 78. Springer, 2023. Abstract: Over the last three decades, we have become more dependent on wireless connectivity to access services and applications from nearly anywhere. The overstated emergence of the all-encompassing fifth generation (5G) of mobile systems begs the question of the future of the new generation of IEEE 802.11 (Wi-Fi) solutions. However, Wi-Fi has certain advantages compared to cellular systems in different ways: (i) a fast-paced standardization process; (ii) a diverse, agile, and highly competitive manufacturer base; and (iii) a broad base of early adopters for both office and house wireless networks. In addition, the rise of enabling technologies, such as software-defined wireless networks, may allow more robust and reliable Wi-Fi networks to bridge gaps in Wi-Fi technology to reach several vertical sectors. This review provides a technical analysis of the relationship between broadband wireless and Wi-Fi technologies. Wi-Fi has taken decisive steps with the evolution of several standards, and there is already evidence that Wi-Fi may partially (or completely) fulfill 5G’s strict service requirements. Next, we discussed the Wi-Fi and 5G convergence, which allow more control over user experiences and provide better service. This review concludes with an analysis of open challenges in the convergence of 5G and Wi-Fi systems. We conclude that Wi-Fi technology has and will continue to have a decisive role as an access technology in the new ecosystem of wireless networks. URL: https://doi.org/10.1007/s12243-023-00995-2


Martínez, Víctor M. G., Guimarães, Rafael S., Mello, Ricardo C., do Carmo, Alexandre P., Vassallo, Raquel F., Villaça, Rodolfo S., Ribeiro, Moisés R. N., Martinello, Magnos. "Make Before Degrade: A Context-Aware Software-Defined WiFi Handover" In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2023. Lecture Notes in Networks and Systems, vol 654. Springer, Cham. Abstract: Ultra-reliable and low-latency communications are essential for new services and applications in Industry 4.0. URLLC is also required to provide traffic density to meet the throughput demands of its clients across the coverage area via cell densification. However, cell densification implies that handover between serving stations will become more and more frequent. In this paper, we introduce the Make Before Degrade solution for zero mobility interruption with a single radio connection. Mobility management is based on contextual information that allows prudently to shift traffic flows before their propagation paths are compromised. The paper brings a proof-of-principle software-defined WiFi testbed able to meet 3GPP’s traffic density specifications in which contextual information is provided by computer vision. An Industry 4.0 use case based on cloud robotics demonstrates the practical applicability of our proposal. URL: https://doi.org/10.1007/978-3-031-28451-9_49


de O. Pereira, I., Dominicini, C.K., Guimarães, R.S., Villaça, R.S., Almeida, L.R., Vassoler, G. "MPolKA-INT: Stateless Multipath Source Routing for In-Band Network Telemetry." In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2023. Lecture Notes in Networks and Systems, vol 654. Springer, Cham. Abstract: Real-time monitoring and measurement are the basis for most management operations, such as traffic engineering, quality of service assurance, and anomaly detection. Nevertheless, collecting measurements from all network devices with sampling and polling-based methods is not scalable. To tackle this issue, the P4 Language Consortium proposed the In-band Network Telemetry (INT) framework that provides real-time and fine-grain measurements in the data plane using telemetry packets. However, the task of specifying the route taken by a telemetry probe still relays on the traditional routing protocols, which require state changes in routing tables and fail to achieve the required accuracy, coverage and latency. In this context, this article investigates how to combine INT with a source routing method based on the stateless Multipath Polynomial Key-based Architecture (M-PolKA). We implemented this multipath telemetry solution as MPolKA-INT using the P4 language, and the experimental results showed low overhead in the data and control planes with agile and flexible path (re)configuration, since it does not require state changes in the routing tables of the devices in the network core. URL: https://doi.org/10.1007/978-3-031-28451-9_45


M. Carvalho and D. F. Macedo, "Container Scheduling in Co-Located Environments Using QoE Awareness" in IEEE Transactions on Network and Service Management, 2023. Abstract: Existing Cloud deployments usually perform automated scheduling and rescheduling based on Quality of Service (QoS) objectives. Services are migrating towards Quality of Experience (QoE), which maps the user experience more effectively than QoS. This work proposes extensions to the Kubernetes scheduler in order to employ QoE objectives into the algorithm. For that, we created deep learning models (using LSTM) to estimate user’s QoE that the cloud can offer. The evaluation was performed on a testbed, and considered two QoE-aware applications (live classroom and video on demand). Experimental results in a testbed show that our scheduler improves the average QoE by at least 61.5% compared to other schedulers, while our proposed resource rescheduling improved the QoE by up to 119%, keeping the average QoE closer to the maximum.. URL: https://doi.org/10.1109/TNSM.2023.3244090


M. Carvalho, D. Soares and D. F. Macedo, "Transfer Learning-Based QoE Estimation For Different Cloud Gaming Contexts" in 2023 IEEE 9th International Conference on Network Softwarization (NetSoft), 2023. Abstract: Cloud Gaming renders game data in the cloud and forwards it to players over the network. While this reduces hardware costs for players, it introduces challenges in network management and delivering a good gaming experience. In this context, network providers are encouraged to implement QoE-aware management systems to guarantee a desired Quality of Experience (QoE), in which Machine Learning (ML) models achieve the state-of-the-art on QoE estimation/monitoring. However, it is hard to create ML models that generalize to different contexts, especially since QoE perception is subjective and varies among games and players. This paper employs transfer learning and fine-tuning to adjust a source model to different target domains. First, we performed a subjective QoE assessment with real users playing on a realistic testbed. Based on this, we derived four datasets, one being the source dataset (to create the source model) and three distinct target datasets. Experiments show that transfer learning can decrease the average MSE error by at least 41.6% compared to the source model performance on the target datasets while decreasing the demand for labeled data by at least 81.1%. Furthermore, the improvement is greater when compared to models trained from scratch for each target dataset. URL: https://doi.org/10.1109/NetSoft57336.2023.10175441


G. Lando, L. A. F. Schierholt, M. P. Milesi, J. A. Wickboldt, "Evaluating the performance of open source software implementations of the 5G network core" in NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, 2023. 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. URL: https://doi.org/10.1109/NOMS56928.2023.10154399


D. Soares, M. Carvalho and D. F. Macedo, "A Stacking Learning-Based QoE Model for Cloud Gaming" in NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, 2023. Abstract: Cloud gaming is a new paradigm that allows more cost-effective gaming for both users and game developers. The market is expected to grow 50-60% annually, reaching 22 billion USD by 2030. Gaming providers and ISPs require models of user satisfaction in order to improve their management of the cloud and network infrastructure. This paper analyses and proposes models that estimate the QoE of cloud gaming. Such models take as features network and game metrics. We assume an information sharing agreement among the cloud gaming platform and the ISP, allowing for a richer dataset. Data collection is performed with real users playing on a realistic testbed using similar protocols of the NVIDIA Geforce Now cloud gaming platform. We use stacking learning in order to improve the accuracy of the models, making a search for the best models and stacking them. We tested various improvements to the models, such as removing users with very low number of matches. Experiments show that models with more experienced players obtained a better precision, achieving 36.08%. When considering a range of plus or minus one within the estimated precision, the hit ratio was 86.56%. We also analyzed the model’ s sensitivity to inputs using feature importance analysis. URL: https://doi.org/10.1109/NOMS56928.2023.10154380


B. M. Xavier, R. S. Guimarães, G. Comarela and M. Martinello, " MAP4: A Pragmatic Framework for In-Network Machine Learning Traffic Classification " in IEEE Transactions on Network and Service Management, 2022. Abstract: Self-driving networks guided by machine-learning (ML) algorithms are the driving force for building networks of the future. ML is effective at making inferences about data that is too complex or too unpredictable for humans. The network softwarization enabled by a deep programmability approach opens up new opportunities to deploy ML at the programmable data plane. In this paper, we introduce the MAP4 as a framework that explores the feasibility of mapping ML models in programmable network devices. To achieve this, we rely on the P4 language to deploy a pre-trained model into a programmable switch, utilizing the ML model to accurately classify flows at line rate. Our approach demonstrates that ML models working as classifiers can better fit the data by using the new levels of network programmability from the P4 language. The results showed that with few packets, most of the flows are properly classified. In some use cases, with two packets in the flow, 97% of traffic can be correctly classified, and all classes are properly labeled with a maximum of four packets. URL: https://ieeexplore.ieee.org/document/9913715


J. P. De Brito Gonçalves, G. Alochio, R. Da Silva Villaça and R. L. Gomes, "Data Integrity Verification in Network Slicing using Oracles and Smart Contracts," 2022 IEEE International Conference on Blockchain (Blockchain), 2022, pp. 476-481. Abstract: The fifth-generation (5G) wireless networks are expected to provide various services compared to the 4G and previous generations of networks. The Quality of Service requirements can be quite different in terms of latency, bandwidth, reliability, and availability. 5G technology allows the fragmentation of the network into small pieces, known as network slices. This network slicing is done by specific tools and the configuration must be protected from attacks that may be performed by malicious users. Thus in this paper, a solution to protect and prevent these failures from happening is addressed. For this solution to be carried out, a study was conducted on the Blockchain technology, as well as the use of Oracles in order to implement an integrity verification system, a system capable of assuring 5G network slices' configuration integrity through a complete architecture involving Blockchain, Smart Contracts and Oracles. URL: https://doi.org/10.1109/Blockchain55522.2022.00073


J. P. De Brito Gonçalves and R. Da Silva Villaça, "A Blockchained Incentive Architecture for Federated Learning," 2022 IEEE International Conference on Blockchain (Blockchain), 2022, pp. 482-487. Abstract: The naive use of Federated Learning (FL) in a distributed environment exposes it to a risk of corruption, whether intentional or not, during the training phase. It happens because of the lack of monitoring of the training increments and difficulty of checking the quality of the training datasets. A very common type of attack of this type is Model Poisoning. To improve the security of the FL structure, we propose a decentralized FL framework based on blockchain, that is, a blockchain-based FL framework to increment the system security using an incentive mechanism to reward good trainers in the form of tokens. The system modeling will be presented as well as its implementation in the Mininet simulator. The validation tests performed to attest its accuracy were executed using the MNIST dataset. URL: https://doi.org/10.1109/Blockchain55522.2022.00074


J. P. de Brito Gonçalves, G. Spelta, R. da Silva Villaça and R. L. Gomes, "IoT Data Storage on a Blockchain Using Smart Contracts and IPFS," 2022 IEEE International Conference on Blockchain (Blockchain), 2022, pp. 508-511. Abstract: Since the creation of the cryptocurrency Bitcoin, the interest in blockchain technology has increased, entering areas such as loT (Internet of Things) and data sharing. The main objective of this paper is to develop a system that allows the storage of data from loT services in a decentralized network with a blockchain managing transactions through a smart contract. The project was carried out using the blockchain Ethereum, IPFS (InterPlanetary File System) for storage, Solidity language for contract development, NodeJS for coding the simulation of loT devices, web interface and back-end of the solution. The MQTT protocol was used to transport data from the devices. Our main objective was achieved, as the tests carried out show use cases in which this solution has an advantage over the direct storage in the Ethereum blockchain. URL: https://doi.org/10.1109/Blockchain55522.2022.00078


Cussuo, E., Sachetti L., Santos B., Mota V.F.S "OTALab: um ambiente de experimentação remota de protocolos e aplicações em Internet das Coisas" In Salão de Ferramentas Jointly XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Fortaleza, 2022. Abstract: This paper presents the OTALab, a tool for creating and deploying experimentation environments of Internet of Things applications in low-cost microcontrollers. The OTALab aims for fast deployment and configuration of an experimentation environment testbed. OTALab has two users profiles: administrators and experimenters. For the former, the OTALab exposes an admin interface able to add/remove IoT devices, services, and functionalities to the system. For the latter, the experimenters, can visualize the available services in each device and submit their own code to the devices through a command line or a Web application. OTALab receives the source code, compiles it to the specific microcontroller, and updates the device's firmware through the OTA paradigm. The OTALab is composed by a library of microcontrollers, a device management server, and a Web application. The tool can be instantiated locally or in a distributed fashion, improving its flexibility.


T. A. N. do Amaral, R. V. Rosa, D. Moura and C. E. Rothenberg, "Run-Time Adaptive In-Kernel BPF/XDP Solution for 5G UPF" In Electronics 11, no. 7. 2022. Abstract: Flexibility is considered a key feature of 5G softwarization to deliver a timely responseto changes in network requirements that may be caused by traffic variation, user mobility, dynamicnetwork function chains, slice lifecycle management operations, among others. In this article, weevolve the upf-bpf open-source project by proposing a new design to improve its flexibility byreducing the run-time adaptation time. The project proposes an in-kernel solution based on BPF andeXpress Data Path (XDP) for 5G User Plane Function (UPF) implementations. The Just-In-Time (JIT)compilation may have a huge impact on the adaptation time due to the in-kernel verification of theBPF programs at run-time. Our results show latency improvements of around 95% to inject the BPFprogram into the Linux kernel. Furthermore, the solution keeps the same functionalities and deliversa packet processing performance of around 10–11 Mpps using 6 cores with almost 70% of the CPUutilization in downlink/uplink directions. URL: https://github.com/navarrothiago/upf-bpf


E. Borges "A lifecycle experience of PolKA: From prototyping to deployment at Geant Lab with RARE/FreeRouter " in WPEIF 2022 Abstract: In this paper, we take the position of developers that need to deploy emerging programmable protocols (or services) with specific network requirements and want to know how to benefit from an open router platform and testbed infrastructure. Our focus is to exploit the PolKA lifecycle experience as a use case to figure out a balance between integrating and reusing legacy protocols with new protocols.


R. S. Guimarães "M-PolKA: Multipath Polynomial Key-based Source Routing for Reliable Communications" in IEEE Transactions on Network and Service Management. Abstract: Innovative traffic engineering functions and services require disrupting routing and forwarding mechanisms to be performed with low overhead over complex network topologies. Source routing (SR) is a prominent alternative to table-based routing for providing the needed expressiveness and agility by reducing the number of network states. This work proposes the M-PolKA, a topology-agnostic multipath source routing scheme and orchestration architecture for reliable communications, which explores special properties from the Residue Number System (RNS) polynomial arithmetic. A P4-based proof-of-concept is experimentally demonstrated using emulated and hardware prototypes. Also, use cases for revealing M-PolKA’s functionalities are tested in different scenarios in order to address problems, such as communication reliability improvement, agile path migration and fast failure reaction. Finally, low overhead for extra functionalities is observed when RNS-based SR is compared to traditional routing approaches. URL: https://doi.org/10.1109/TNSM.2022.3160875


G. Miranda, D. F. Macedo and J. M. Marquez-Barja, "Estimating Video on Demand QoE from Network QoS through ICMP Probes," in IEEE Transactions on Network and Service Management. Abstract: With the increasing traffic of vod, network providers are seeking to deliver high qoe for their users. Many methods have been proposed to assess vod-related qoe. Some of them rely on client instrumentation and reporting qoe information to network elements, such as Server and Network Assisted DASH, others are based on statistical methods that make qoe inferences using monitored network conditions, such as throughput and delays. In this article, we present a practical method to estimate qoe for vod using the widely supported icmp probes. Measured network conditions are used as input to a ml model that estimates qoe in terms of mos, based on the ITU-T P.1203 Recommendation. The estimation encompasses video quality switches and playback stalls. We estimate mos with an average rmse of 1.05 for a catalog of 25 different videos, training a model with sessions of the shortest video, and evaluating the generalization to the full catalog. We performed experiments using a virtualized setup as well as in a Wide Area Network. URL: https://doi.org/10.1109/TNSM.2021.3129610


G. Miranda, E. Municio, J. M. Marquez-Barja and D. F. Macedo, "Machine Learning-based End-to-End QoE Monitoring Using Active Network Probing," in 25th Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN), 2022, Paris. Abstract: Abstract here! URL: To appear


T. A. N. do Amaral, R. V. Rosa, D. Moura and C. E. Rothenberg, "An In-Kernel Solution Based on XDP for 5G UPF: Design, Prototype and Performance Evaluation," in 1st Joint International Workshop on Network Programmability & Automation (NetPA), 2021. Abstract: The edge computing infrastructure can scale from datacenters to single device. The well-known technology for fast packet processing is DPDK, which has outstanding performance regarding the throughput and latency. However, there are some drawbacks when the usage is done in the edge: (i) the polling mechanism for packet processing keeps the CPU exclusively occupied even if there is no traffic, leading to wasted resources; and (ii) DPDK interface becomes unavailable for the applications inside the host, so the integration between a non-DPDK application and a DPDK application becomes a hard task. In this paper, we propose an open-source in-kernel 5G UPF solution based on 3GPP Release 16 to be deployed in a restrictive environment like MEC, where MEC host and UPF are collocated with the Base Station, sharing the same computational and network resources. The solution leverages the eBPF/XDP, a novel Linux kernel technology for fast packet processing. We show it can scale and achieve 10 Mpps using only 60% of the CPU with 6 cores. URL: https://github.com/navarrothiago/upf-bpf


L. Sachetti, E. Cussuol, J. Nogueira, and V. Mota, "pmSensing: Uma Rede de Sensoriamento Participativo para Monitoramento Preditivo de Material Particulado," in Anais do V Workshop de Computação Urbana, Uberlândia, 2021, pp. 168-181. Abstract: Este trabalho apresenta uma proposta de uma rede de sensores sem fio para sensoriamento participativo, com dispositivos IoT de sensoriamento desenvolvidos especialmente para monitoramento e predição da qualidade do ar, como alternativa a estações meteorológicas de alto custo. O sistema, batizado de pmSensing, objetiva fazer a medição de material particulado. Uma validação é feita comparando os dados coletados pelo protótipo com dados das estações. A comparação mostra que os resultados são próximos, o que pode viabilizar soluções de baixo custo para o problema. O sistema ainda apresenta uma análise preditiva utilizando redes neurais recorrentes, no caso a rede LSTM-RNN, onde as predições apresentaram alta acurácia em relação aos dados reais. URL: https://doi.org/10.5753/courb.2021.17112


V. Zanotelli, G. Comarela, R. Villaca, and M. Martinello. "Caracterização e Previsão de Falhas em Serviços de Conectividade: uma Aplicação à Rede Ipê," in Anais do XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Uberlândia, 2021, pp. 141-154. Abstract: A Rede Ipê é fundamental para a comunidade científica brasileira por interconectar universidades e centros de pesquisa de todo o país. Este artigo analisa algumas características da Rede Ipê e explora o uso de técnicas de aprendizado de máquina para predição de falhas em serviços de conectividade usando dados públicos disponibilizados pela ferramenta ViaIpê. O problema é abordado como uma tarefa de classificação binária utilizando redes neurais recorrentes. Os resultados mostram que a dependabilidade do serviço de conectividade varia significativamente nos diferentes PoPs da Rede Ipê. Além disso, apesar da heterogeneidade deste serviço, os modelos de predição mostram-se promissores, apresentando boa acurácia e boa precisão em alguns cenários. URL: https://doi.org/10.5753/sbrc.2021.16717


G. R. Zibetti, J. A. Wickboldt, and E. P. de Freitas. "Context-aware environment monitoring to support LPWAN-based battlefield applications," in Computer Communications, Volume 189, 2022, ISSN 0140-3664, pp. 141-154. Abstract: The use of IoT-related technologies is growing in several areas. Applications of environmental monitoring, logistics, smart cities are examples of applications that benefit from advances in IoT. In the military context, IoT applications can support the decision-making process by delivering information collected directly from the battlefield to Command, Control, Communications, Computers, Intelligence, Surveillance and Reconnaissance (C4ISR) systems. Taking the benefit of the installed IoT network in the battlefield, the use of the data collected by the IoT nodes is a way to improve resiliency and increase the survivability of networks, as well as to optimize the use of available resources. Towards improving the communication network present on the battlefield, this work presents a context-aware environmental monitoring system that uses real-time battlefield information to increase military networks’ resilience and survivability. The proposed approach is validated by a proof-of-concept experiment. The obtained results show that the implementation of this system can improve the communication process even when the network is exposed to unfavorable climatic factors. URL: https://doi.org/10.1016/j.comcom.2022.02.020


Grings, F., Silveira, L., Muller, N., Lúcio Prade, Cardoso, K., Correa, S. and Both, C., "Orquestração dinâmica total de fatiamento de rede no nucleo 5G sobre plataforma nativa de computação em nuvem," XL Brazilian Symposium on Computer Networks and Distributed Systems (SBRC). Abstract: Technological advances in the fifth-generation (5G) mobile networks are based on native cloud computing platforms and Kubernetes has emerged as the orchestration system for virtualized infrastructure. However, these platforms were not designed to natively support 5G services. To illustrate, Kubernetes is designed to be agnostic to the services which orchestrates and is not able to dynamically reconfigure the 5G core according to existing network resources, i.e., it provides a partial dynamic orchestration to perform network slicing. This paper proposes a solution integrated with Kubernetes to allow full dynamic orchestration of network slicing at runtime, adjusting the 5G core. This integration is accomplished through a Kubernetes-integrated controller and a proxy for control plane. The controller adjusts the 5G core and adapts the virtualized infrastructure, while the proxy creates an abstraction for the control communication between access and transport networks with the core. The experimental results showed a reconfiguration total dynamic orchestration without interruption of the services, reducing the total reconfiguration requests number by network slices by 47.5%. URL: https://doi.org/10.5753/sbrc.2022.222327


Prade, L., Moraes, J., Albuquerque, E., Rosário, D., Both, C., "Multi-radio and multi-hop LoRa communication architecture for large scale IoT deployment," in Computers and Electrical Engineering, Volume 102, 2022, ISSN 0045-7906, pp. 108242-108256. Abstract: Internet of Things (IoT) devices must cover large areas in the farmlands to collect vital information and avoid financial losses to improve agriculture efficiency. It is crucial to hold data acquisition in farms where network connectivity is a limitation in this context. Long-Range Wide Area Network (LoRaWAN) provides a broad coverage area tailored for IoT applications using unlicensed frequency bands with low power consumption and throughput. However, LoRaWAN might not be suitable for data acquisition on farms with hundreds of kilometers. Therefore, a multi-hop Long-Range (LoRa) network emerged as a promising solution in applications requiring extensive deployment. However, a multi-hop architecture must be designed to cope with the limitations of LoRa deployment in large-scale scenarios. This article introduces a multi-radio and multi-hop LoRa communication architecture to enhance the coverage and service for large-scale IoT deployment in rural areas, called Multi-LoRa. We present a hardware prototype for physically implementing the Multi-LoRa architecture. The results show that Multi-LoRa effectively mitigates the difficulties of multi-hop communication over LoRa for large-scale IoT deployment. Multi-LoRa reduced the delay by 60% and packet loss by 2.9% compared to different setups of Multi-LoRa on a small-scale physical testbed and large-scale simulation environment. URL: https://doi.org/10.1016/j.compeleceng.2022.108242


Silveira, L., De Resende, H., Both, C., Marquez-Barja, J., Silvestre, B., Cardoso, K.,"Tutorial on communication between access networks and the 5G core," in Computer Networks, Volume 216, 2022, ISSN 1389-1286, pp. 109301-109316. Abstract: Fifth-generation (5G) networks enable a variety of use cases that require differentiated connectivity, e.g., Ultra-Reliable and Low-Latency Communications (URLLC), enhanced Mobile Broadband (eMBB), and massive Machine Type Communication (mMTC). To explore the full potential of these use cases, it is mandatory to understand the communication along with the 5G network segments and architecture components. User Equipment (UE), Radio Access Network (RAN), and 5G Core (5GC) are the main components that support these new network concepts and paradigms. 3rd Generation Partnership Project has recently published Release 16, including the protocols used to communicate between RANs and 5GC, i.e., Non-Access Stratum (NAS) and NG Application Protocol (NGAP). The main goal of this work is to present a comprehensive tutorial about NAS and NGAP specifications using a didactic and practical approach. The tutorial describes the protocol stacks and aspects of the functionality of these protocols in 5G networks, such as authentication and identification procedures, data session establishment, and resource allocation. Moreover, we review the message flows related to these protocols in UE and Next Generation Node B (gNodeB) registration. To illustrate the concepts presented in the tutorial, we developed the my5G Tester: a 5GC tester that implements NAS and NGAP for evaluating three open-source 5GC projects using a black-box testing methodology. URL: https://doi.org/10.1016/j.comnet.2022.109301


Morais, F., Bruno, G., Renner, J., Almeida, G., Contreras, L., Righi, R., Cardoso, K., Both, C."OPlaceRAN - a Placement Orchestrator for Virtualized Next-Generation of Radio Access Network," in IEEE Transactions on Network and Service Management, Volume 1, 2022, ISSN 1932-4537, pp. 1-1. Abstract: The fifth-generation mobile evolution enables Next- Generation Radio Access Networks (NG-RAN) transformations. The RAN protocol stack is split into eight disaggregated options combined in three network units, i.e., Central, Distributed, and Radio. Further advances allow the RAN functions to be virtualized on top of general-purpose hardware using the virtualized RAN (vRAN). The combination of NG-RAN and vRAN results in vNG-RAN, enabling the management of the disaggregated units and protocols as a set of radio functions. However, the orchestration-based placement of these radio func- tions is challenging since the best decision can be determined by multiple constraints involving RAN disaggregation, crosshaul network requirements, availability of computational resources, etc. This article proposes OPlaceRAN, a vNG-RAN deployment orchestrator framed within the NFV reference architecture and aligned with the Open RAN initiative. OPlaceRAN supports the dynamic placement of radio functions focusing on vNG- RAN planning and is designed to be agnostic to the placement optimization solution. We developed a prototype based on cloud- native tools to deploy RAN using containerized virtualization and the OpenAirInterface emulator. The evaluation is analyzed considering two different approaches as a proof-of-concept. First, we applied two placement solutions in a controlled real computing infrastructure with a crosshaul network. Second, we investigated the orchestrator’s scalability with a real and larger-scale topology. Our results show that OPlaceRAN is an effective cloud-native solution for containerized network function placement and agnostic to the placement solution, handling scale- out well. OPlaceRAN is up-to-date with the most advanced vNG- RAN design and development approaches, contributing to the evolution of fifth-generation networks. URL: https://doi.org/10.1109/TNSM.2022.3222298


Grings, F., Silveira, L., Lúcio Prade, Cardoso, K., Correa, S. and Both, C., "Full dynamic orchestration in 5G core network slicing over a cloud-native platform," IEEE Global Communications Conference (GLOBECOM), 2022, pp. 2885-2890. Abstract: Technological advances in the fifth-generation (5G) mobile networks are based on native cloud computing platforms, and Kubernetes (K8S) has emerged as a relevant orchestration system in this context. However, these platforms were not designed to support 5G services natively. To illustrate, Kubernetes is designed to be agnostic to the services that it orchestrates and cannot dynamically reconfigure the 5G core according to existing network resources, i.e., it provides a partial dynamic orchestration to perform network slicing. This paper proposes a solution integrated with K8S to allow full dynamic orchestration of network slicing at runtime, including online adjustments in the 5G core. This integration is accomplished through a K8S-integrated controller for the control plane. The controller adjusts the 5G core and adapts the virtualized infrastructure. The results show a reconfiguration based on full dynamic orchestration without interruption of the services provided, reducing by close to 50% the full reconfiguration requests number by network slices. URL: https://doi.org/10.1109/GLOBECOM48099.2022.10000663


Bruno, G., Rodrigues, K., Cardoso, K., Correa, Both, C."Anomaly Detection in Cloud­native B5G Systems usingObservability and Machine Learning COTS Solutions," in Journal of Internet Services and Applications, Volume 14, 2023, pp. 189–199. Abstract:The advent of B5G networks has revolutionized the telecommunications landscape by transitioning hardware resources to software components, predominantly running on cloud-­based infrastructures. However, this ‘softwarization’ extends across the radio access, transport, and core networks, introducing complex challenges in real-time network management. In this context of the ‘softwarization’, it is imperative to make the behavior of B5G systems readily observable for effective management and fault diagnosis. This article presents a comprehensive empirical investigation of observability within a B5G system, specifically focusing on its radio access and core networks. The study enhances the system’s observability by combining advanced metric analysis and log parsing. Our method integrates Commercial Off­-The-­Shelf machine learning algorithms to diagnose anomalies and automate failure tasks. Besides that, our evaluation of the Cloud­-Native Observability Tools services revealed a significant memory footprint, accounting for 86% of the total memory usage and 22% overall CPU utilization. The findings also highlight that our approach mitigates the issue of non-­standardization in log data, thereby facilitating proactive failure anticipation. This study can aggregate significant value for developing automated, self­healing B5G network systems. URL: https://doi.org/10.5753/jisa.2023.3551


Veiga, R., Both, C., Medeiros, I., Rosário, D., Cerqueira, E."A Federated Learning Approach for Authentication and User Identification based on Behavioral Biometrics," in Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 41, 2023, pp. 15-28. Abstract:A smartphone can collect behavioral data without requiring additional actions on the user’s part and without the need for additional hardware. In an active or continuous user authentication process, information from integrated sensors, such as touch, and gyroscope, is used to monitor the user continuously. These sensors can capture behavioral (touch patterns, accelerometer) or physiological (fingerprint, face) data of the user naturally interacting with the device. However, transferring data from multiple users’ mobile devices to a server is not recommended due to user data privacy concerns. This paper introduces an Federated Learning (FL) approach to define a user’s biometric behavior pattern for continuous user identification and authentication. We also evaluate whether FL can be helpful in behavioral biometrics. Evaluation results compare CNNs in different epochs using FL and a centralized method with low chances of wrong predictions in user identification by the gyroscope. URL: https://doi.org/10.5753/sbrc.2023.536


Bruno, G., Almeida, G., Sathish, A., da Silva, A., DaSilva, L., Huff, A., Cardoso, K., Both, C."Evaluating the Deployment of a Disaggregated Open RAN Controller on a Distributed Cloud Infrastructure," in IEEE Transactions on Network and Service Management, Volume 21, 2024, ISSN 1932-4537, pp. 4213-4225. Abstract:This article investigates the deployment of a NearReal-Time Radio Access Network (RAN) Intelligent Controller (near-RT RIC) on a distributed cloud infrastructure composed of multiple physical sites with different amounts of resources and associated costs. The challenge is dynamically adapting the nearRT RIC deployment to the most cost-effective arrangement while meeting the latency requirements between the near-RT RIC and the controlled nodes. We introduce an optimization model to solve the disaggregated near-RT RIC placement problem, considering a cloud-native infrastructure to minimize the placement cost while satisfying the latency-sensitive control loop requirements across the cloud-edge continuum. Moreover, we describe an experimental environment we created using geographically disparate cloud sites. We present data detailing the latencies of the communication links among these sites and the costs incurred in using this real-world infrastructure. We conduct a performance evaluation of the near-RT RIC deployment, comparing the distributed approach versus a traditional monolithic strategy and evaluating positioning costs, deployment, setup and registration times, and the control loop latency considering three scenarios. Our results show that in a cloud-native environment, the disaggregated near-RT RIC allows cost savings of up to 60% in comparison to a monolithic near-RT RIC while satisfying the control loop latency and achieving time efficiency in terms of deployment and registration of xApps and near-RT RIC components. URL: https://doi.org/10.1109/TNSM.2024.3386902


Arnhold, F., Anbazhagan, S., Prade, L., Nogueira, J., Klautau, A., Both, C."Network Slicing Support by Fronthaul Interface in Disaggregated Radio Access Networks: A Survey," in IEEE Transactions on Network and Service Management, Volume 21, 2024, ISSN 1932-4537, pp. 4510-4530. Abstract:Beyond 5G (B5G) and 6G networks must offer network slicing as a service to support disruptive applications using mobile network infrastructures. Moreover, network slicing as a service should enable the orchestration and management of disaggregated radio access networks (RAN), i.e., it allows the automation and abstraction of network configurations composed of physical and virtualized components such as defined by the 3rd Generation Partnership Project (3GPP) and Open RAN (O-RAN) Alliance. Network slicing must reach the part of the network between the radio units and the distribution units, i.e., the fronthaul network. Fronthaul is essential and diverse in 5G and B5G networks and can be composed of point-to-point or multipoint connections. In this context, the literature presents several works investigating the problems of network slicing and disaggregated networks. However, no survey explores current works integrating network slicing in disaggregated networks, specifically in the fronthaul network. This article surveys network slicing on disaggregated networks and its potential use in point-to-point and multipoint fronthaul infrastructures. We cover the state-of-the-art by analyzing four fundamental research questions and discuss existing solutions, open challenges, and research opportunities in B5G and 6G networks. URL: https://doi.org/10.1109/TNSM.2024.3400019


Almeida, G., Bruno, G., Huff, A., Hiltunen, M., Duarte, E., Both, C., Cardoso, K."RIC-O: Efficient Placement of a Disaggregated and Distributed RAN Intelligent Controller With Dynamic Clustering of Radio Nodes," in IEEE Journal on Selected Areas in Communications, Volume 42, no. 2, 2024, pp. 446-459. Abstract:The Radio Access Network (RAN) is the segment of cellular networks that provides wireless connectivity to end-users. The O-RAN Alliance has been transforming the RAN industry by proposing open RAN specifications and the programmable Non-Real-Time and Near-Real-Time RAN Intelligent Controllers (Non-RT RIC and Near-RT RIC). Both RICs provide platforms for running applications called rApps and xApps, respectively, to optimize the RAN behavior. We investigate the disaggregation of the Near-RT RIC into components that meet stringent latency requirements while presenting a cost-effective solution. For example, the O-RAN Signalling Storm Protection requires the Near-RT RIC to support end-to-end control loop latencies as low as 10 ms. We propose the novel RIC Orchestrator (RIC-O) that optimizes the deployment of the Near-RT RIC components across the cloud-edge continuum. Edge computing nodes often present limited resources and are expensive compared to cloud computing. Performance-critical components of Near-RT RIC and certain xApps should run at the edge while other components can run on the cloud. Furthermore, RIC-O employs an efficient strategy to react to sudden changes and re-deploy components dynamically. The proposal is evaluated both analytically and through real-world experiments in an extended Kubernetes deployment implementing RIC-O and the disaggregated Near-RT RIC. URL: https://doi.org/10.1109/JSAC.2023.3336159


Kopper, G., Schulz, E., Huff, A., Both, C., Cardoso, K."Uma análise de interoperabilidade e desempenho de projetos Open RAN com núcleos de redes móveis de quinta geração," in Workshop de Gerência e Operação de Redes e Serviços (WGRS), 29, 2024, pp. 43-56. Abstract:Os padrões 3rd Generation Partnership Project (3GPP) e Open Radio Access Network Alliance (O-RAN) definem interfaces abertas para que componentes de software e hardware da RAN e núcleo possam interoperar entre diferentes fornecedores. A interoperabilidade é uma das principais características desejadas pelos operadores de redes de telecomunicações móveis e órgãos padronizadores, permitindo a entrada de novos fornecedores e acelerando a inovação da indústria de telecomunicações. Entretanto, poucos trabalhos têm investigado a interoperabilidade de projetos O-RAN com os núcleos de redes móveis de quinta geração. Este trabalho analisa a interoperabilidade entre projetos de código aberto utilizando as interfaces abertas da RAN e do núcleo. O trabalho também realiza uma avaliação de desempenho dos projetos que apresentam interoperabilidade entre si. A avaliação de desempenho inclui uma discussão acerca dos projetos OpenAirInterface e Software Radio Systems RAN, na qual o primeiro apresenta um consumo de memória três vezes menor do que o segundo, enquanto que ambos apresentam taxas de transferências similares. URL: https://doi.org/10.5753/wgrs.2024.3234


Development

Source routing (SR) is a prominent alternative to table-based routing for reducing the number of network states. Actually the traditional SR approaches, based on Port Switching, still maintain a state in the packet by using a header rewrite operation. The residue number system (RNS) is a promising way to achieve fully stateless SR, in which forwarding decisions at core nodes rely on a simple modulo operation over a route label. Nevertheless, such operation over integer arithmetic is not natively supported by commodity network hardware. Thus, PolKA proposes a novel RNS-based SR scheme that explores binary polynomial arithmetic using Galois field (GF) of order 2.

News

News #1 - PolKA proposal will be demonstrated as a Network Research Exibition in SuperComputing 2022 https://sc22.supercomputing.org/

This NRE proposes to demonstrate PolKA functionalities to support the TE extreme challenges for data-intensive science (DIS). PolKA is a novel source routing approach that explores the Residue Number System (RNS) and Chinese Remainder Theorem (CRT) by performing the forwarding as an arithmetic operation: the remainder of division. PolKA encodes the path in a routeID using the RNS in contrast to the conventional list-based representation, which transports the path information “in clear” inside the packet header. Then, PolKA core nodes use this encoded route label to discover the output ports.

The plan of demonstration is to create an overlay network with PolKA tunnels forming virtual circuits to validate the data-intensive transfer over 10G and 100G+ as a proof-of-principle of PolKA mechanisms. At the edge, flows can be classified, balanced and steered by using a Policy-Based Routing (PBR). A number of virtual circuits may be configured by dividing the capacity of the physical links and using them to serve the flows. Underlay congestion can be detected by tunnel monitoring and signalized to the overlay, and overlay routing can steer traffic from congested tunnels to other paths. Comparisons between segment routing and PolKA regarding controllability and performance metrics are also planned in this demonstation.

The goal is to investigate whether PolKA approach deployed at Global P4 Lab (RARE/freeRtr) meets the needs of DIS networks, working with other software tools and subsystems developed by the DIS-WG for constructing switched overlay networks composed of network paths with bandwidth guarantees, load balancing, prioritizing and scheduling flows over selected multi-domain paths, and making decisions on the coordinated use of network and site computing and storage resources to help accelerate the science workflows.