Exploring telemetry overhead in programmable networks for QoS estimation with machine learning

• Rebeca Dantas Cabral IFPB http://orcid.org/0009-0002-4820-892X
• Gabriel Santos de Andrade UFSCar https://orcid.org/0009-0001-5639-5959
• Luis Kilmer da Silva Bernardo IFPB https://orcid.org/0009-0004-6164-0578
• Pedro Batista de Carvalho Filho IFPB https://orcid.org/0009-0000-5120-4052
• Leandro C. de Almeida IFPB https://orcid.org/0000-0003-4342-3030
• Fábio L. Verdi UFSCar https://orcid.org/0000-0002-5455-8910

DOI: https://doi.org/10.5753/sbrc.2025.6299

Abstract

Monitoring the quality of service (QoS) of real-time applications is challenging for network service providers due to limited access to metrics within the user domain. This study evaluates the impact of INT (In-Band Network Telemetry) and ONT (Out-of-Band Network Telemetry) telemetry strategies on the performance of machine learning algorithms for QoS prediction in video services. Experiments conducted on P4-programmable switches showed that the INT approach reduces prediction error by up to 7 times compared to ONT, although it introduces an overhead of 25% compared to the original throughput of the network without INT. The study also defines an overhead metric and makes the implementations available in a public repository.

Keywords: Telemetry, Machine Learning, Quality of Service

References

Almeida, L., Silva, J., Lins, R., Jr., P. M., Pasquini, R., and Verdi, F. (2023). Wave - um gerador de cargas múltiplas para experimentação em redes de computadores. In Anais Estendidos do XLI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 9–16, Porto Alegre, RS, Brasil. SBC.

Arslan, S. and McKeown, N. (2019). Switches know the exact amount of congestion. In Proceedings of the 2019 Workshop on Buffer Sizing, BS ’19, New York, NY, USA. Association for Computing Machinery.

Ben Basat, R., Ramanathan, S., Li, Y., Antichi, G., Yu, M., and Mitzenmacher, M. (2020). Pint: Probabilistic in-band network telemetry. In Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM ’20, pages 662–680, New York, NY, USA. Association for Computing Machinery.

Bosshart, P., Daly, D., Gibb, G., Izzard, M., McKeown, N., Rexford, J., Schlesinger, C., Talayco, D., Vahdat, A., Varghese, G., and Walker, D. (2014). P4: Programming protocol-independent packet processors. SIGCOMM Comput. Commun. Rev., 44(3):87–95.

Calasans, M. (2020). DASH sobre OpenFlow: estimando métricas de QoS a partir da rede. PhD thesis, Universidade Federal de Uberlândia, Uberlândia - MG - Brazil.

de Almeida, L. C., Pasquini, R., and Verdi, F. L. (2021). Using machine learning and in-band network telemetry for service metrics estimation. In 2021 IEEE 10th International Conference on Cloud Networking (CloudNet), pages 33–39.

Dimoglis, A., de Almeida, L. C., Papadopoulos, K., Papagianni, C., Papadimitriou, P., and Grosso, P. (2024). Lightweight in-band network telemetry on the Tofino programmable switch. In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking, ACM MobiCom ’24, pages 2430–2436, New York, NY, USA. Association for Computing Machinery.

Góes de Castro, A., Rossi, F., Lorenzon, A., Caggiani Luizelli, M., Vogt, F., Hohemberger, R., and Mansilha, R. (2019). Orchestrating in-band data plane telemetry with machine learning. IEEE Communications Letters, 23:20.

ISO (2014). Dynamic adaptive streaming over HTTP (DASH) - Part 1: Media presentation description and segment formats. ISO/IEC, pages 23009–1.

Jalilvand, A. and Diyanat, A. (2024). A new approach for predicting the quality of experience in multimedia services using machine learning.

James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning. Springer Texts in Statistics. Springer, New York, NY.

Marques, J. A. and Gaspary, L. (2018). Explorando estratégias de orquestração de telemetria em planos de dados programáveis. In Anais do XXXVI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 1299–1312, Porto Alegre, RS, Brasil. SBC.

Miranda, G., Macedo, D. F., and Marquez-Barja, J. M. (2022). Estimating video on demand QoE from network QoS through ICMP probes. IEEE Transactions on Network and Service Management, 19(2):1890–1902.

Orsolic, I. and Seufert, M. (2021). On machine learning based video QoE estimation across different networks. In 2021 16th International Conference on Telecommunications (ConTEL), pages 62–69.

P4 (2021). In-band network telemetry (INT) dataplane specification. Technical report, P4 Consortium.

Papadopoulos, K., Papadimitriou, P., and Papagianni, C. (2023). Deterministic and probabilistic P4-enabled lightweight in-band network telemetry. IEEE Transactions on Network and Service Management, 20(4):4909–4922.

Stadler, R., Pasquini, R., and Fodor, V. (2017). Learning from network device statistics. Journal of Network and Systems Management, 25(4):672–698.