Um Modelo de IA para Predição De Vazão De Rede considerando as Características da Janela de Congestionamento do TCP
Resumo
A predição de desempenho é essencial para o gerenciamento proativo de redes, sendo a predição de vazão crucial para a antecipação de gargalos. Visto que algoritmos de controle de congestionamento, como TCP Cubic e TCP BBR, impõem dinâmicas distintas ao tráfego, suas características influenciam diretamente a precisão dos modelos preditivos. Este trabalho apresenta a dissertação que propõe uma abordagem de predição de vazão utilizando redes neurais de aprendizado profundo, considerando explicitamente o algoritmo TCP aplicado e seu comportamento estatístico. Experimentos realizados com dados reais da Rede Nacional de Ensino e Pesquisa (RNP) avaliam o impacto do controle de congestionamento no processo preditivo. Os resultados reforçam a necessidade de alinhar modelos preditivos às especificidades do protocolo de transporte e do ambiente de rede para otimizar decisões operacionais.Referências
Bayne, L., Schepis, D., and Purchase, S. (2017). A framework for understanding strategic network performance: Exploring efficiency and effectiveness at the network level. Industrial Marketing Management, 67:134–147.
Brito, M. L. L., Ferreira, M. C. M., Portela, A. L. C., and Gomes, R. L. (2026). Ai-based estimation of bandwidth availability for data offloading in edge-cloud computing. IEEE Networking Letters, 8:69–73.
Chai, T. and Draxler, R. R. (2014). Root mean square error (rmse) or mean absolute error (mae)?–arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247–1250.
Cleveland, R. B., Cleveland, W. S., McRae, J. E., and Terpenning, I. (1990). Stl: A seasonal-trend decomposition. J. Off. Stat, 6(1):3–73.
Ferreira, M. C., Ribeiro, S. E., Nobre, F. V., Linhares, M. L., Araújo, T. P., and Gomes, R. L. (2024). Mitigating measurement failures in throughput performance forecasting. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–7.
Gomes, R. L., Bittencourt, L. F., Madeira, E. R., Cerqueira, E., and Gerla, M. (2016). A combined energy-bandwidth approach to allocate resilient virtual software defined networks. Journal of Network and Computer Applications, 69:98–106.
Gomes, R. L., Bittencourt, L. F., and Madeira, E. R. M. (2013). A virtual network allocation algorithm for reliability negotiation. In 2013 22nd International Conference on Computer Communication and Networks (ICCCN), pages 1–7.
Kanaya, T., Tabata, N., and Yamaguchi, S. (2020). A study on performance of cubic tcp and tcp bbr in 5g environment. In 2020 IEEE 3rd 5G World Forum (5GWF), pages 508–513.
Lara-Benítez, P., Carranza-García, M., and Riquelme, J. C. (2021). An experimental review on deep learning architectures for time series forecasting. International Journal of Neural Systems, 31(03):2130001. PMID: 33588711.
Miyazawa, K., Yamaguchi, S., and Kobayashi, A. (2020). Mechanism of cyclic performance fluctuation of tcp bbr and cubic tcp communications. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1139–1144.
Redhu, P., Kumar, K., et al. (2023). Short-term traffic flow prediction based on optimized deep learning neural network: Pso-bi-lstm. Physica A: Statistical Mechanics and its Applications, 625:129001.
Ribeiro, S. E., Menezes, R. A., Portela, A. L., Araújo, T. P., and Gomes, R. L. (2023). Aplicando redes neurais e análise temporal para predição adaptativa de desempenho de rede. In Anais do XLI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 490–503. SBC.
Sepasgozar, S. S. and Pierre, S. (2022). Network traffic prediction model considering road traffic parameters using artificial intelligence methods in vanet. IEEE Access, 10:8227–8242.
Silveira, M. M., Portela, A. L., Menezes, R. A., Souza, M. S., Silva, D. S., Mesquita, M. C., and Gomes, R. L. (2023). Data protection based on searchable encryption and anonymization techniques. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, pages 1–5. IEEE.
Sone, S. P., Lehtomäki, J. J., and Khan, Z. (2020). Wireless traffic usage forecasting using real enterprise network data: Analysis and methods. IEEE Open Journal of the Communications Society, 1:777–797.
Wang, Y., Ke, S., An, C., Lu, Z., and Xia, J. (2024). A hybrid framework combining lstm nn and bnn for short-term traffic flow prediction and uncertainty quantification. KSCE Journal of Civil Engineering, 28(1):363–374.
Yamak, P. T., Yujian, L., and Gadosey, P. K. (2019). A comparison between arima, lstm, and gru for time series forecasting. In Proceedings of the 2019 2nd international conference on algorithms, computing and artificial intelligence, pages 49–55.
Yang, H., Li, X., Qiang, W., Zhao, Y., Zhang, W., and Tang, C. (2021). A network traffic forecasting method based on sa optimized arima–bp neural network. Computer Networks, 193:108102.
Brito, M. L. L., Ferreira, M. C. M., Portela, A. L. C., and Gomes, R. L. (2026). Ai-based estimation of bandwidth availability for data offloading in edge-cloud computing. IEEE Networking Letters, 8:69–73.
Chai, T. and Draxler, R. R. (2014). Root mean square error (rmse) or mean absolute error (mae)?–arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247–1250.
Cleveland, R. B., Cleveland, W. S., McRae, J. E., and Terpenning, I. (1990). Stl: A seasonal-trend decomposition. J. Off. Stat, 6(1):3–73.
Ferreira, M. C., Ribeiro, S. E., Nobre, F. V., Linhares, M. L., Araújo, T. P., and Gomes, R. L. (2024). Mitigating measurement failures in throughput performance forecasting. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–7.
Gomes, R. L., Bittencourt, L. F., Madeira, E. R., Cerqueira, E., and Gerla, M. (2016). A combined energy-bandwidth approach to allocate resilient virtual software defined networks. Journal of Network and Computer Applications, 69:98–106.
Gomes, R. L., Bittencourt, L. F., and Madeira, E. R. M. (2013). A virtual network allocation algorithm for reliability negotiation. In 2013 22nd International Conference on Computer Communication and Networks (ICCCN), pages 1–7.
Kanaya, T., Tabata, N., and Yamaguchi, S. (2020). A study on performance of cubic tcp and tcp bbr in 5g environment. In 2020 IEEE 3rd 5G World Forum (5GWF), pages 508–513.
Lara-Benítez, P., Carranza-García, M., and Riquelme, J. C. (2021). An experimental review on deep learning architectures for time series forecasting. International Journal of Neural Systems, 31(03):2130001. PMID: 33588711.
Miyazawa, K., Yamaguchi, S., and Kobayashi, A. (2020). Mechanism of cyclic performance fluctuation of tcp bbr and cubic tcp communications. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1139–1144.
Redhu, P., Kumar, K., et al. (2023). Short-term traffic flow prediction based on optimized deep learning neural network: Pso-bi-lstm. Physica A: Statistical Mechanics and its Applications, 625:129001.
Ribeiro, S. E., Menezes, R. A., Portela, A. L., Araújo, T. P., and Gomes, R. L. (2023). Aplicando redes neurais e análise temporal para predição adaptativa de desempenho de rede. In Anais do XLI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 490–503. SBC.
Sepasgozar, S. S. and Pierre, S. (2022). Network traffic prediction model considering road traffic parameters using artificial intelligence methods in vanet. IEEE Access, 10:8227–8242.
Silveira, M. M., Portela, A. L., Menezes, R. A., Souza, M. S., Silva, D. S., Mesquita, M. C., and Gomes, R. L. (2023). Data protection based on searchable encryption and anonymization techniques. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, pages 1–5. IEEE.
Sone, S. P., Lehtomäki, J. J., and Khan, Z. (2020). Wireless traffic usage forecasting using real enterprise network data: Analysis and methods. IEEE Open Journal of the Communications Society, 1:777–797.
Wang, Y., Ke, S., An, C., Lu, Z., and Xia, J. (2024). A hybrid framework combining lstm nn and bnn for short-term traffic flow prediction and uncertainty quantification. KSCE Journal of Civil Engineering, 28(1):363–374.
Yamak, P. T., Yujian, L., and Gadosey, P. K. (2019). A comparison between arima, lstm, and gru for time series forecasting. In Proceedings of the 2019 2nd international conference on algorithms, computing and artificial intelligence, pages 49–55.
Yang, H., Li, X., Qiang, W., Zhao, Y., Zhang, W., and Tang, C. (2021). A network traffic forecasting method based on sa optimized arima–bp neural network. Computer Networks, 193:108102.
Publicado
25/05/2026
Como Citar
PORTELA, Ariel Lima De Carvalho; GOMES, Rafael Lopes.
Um Modelo de IA para Predição De Vazão De Rede considerando as Características da Janela de Congestionamento do TCP. In: CONCURSO DE TESES E DISSERTAÇÕES - SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 44. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 310-319.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc_estendido.2026.19563.
