Otimizando Energia no Aprendizado Federado em Redes de Baixa potência e com Alta Taxa de Perda de Pacotes
Resumo
O Aprendizado Federado (FL) permite o treinamento distribuído de modelos de aprendizado de máquina, sem necessidade de compartilhamento de dados brutos. Em redes IoT com dispositivos de recursos limitados e alta perda de pacotes, a seleção de dispositivos para treinamento é desafiadora. Este trabalho propõe otimizar essa seleção focando na eficiência energética de dispositivos que utilizam o protocolo RPL (Routing Protocol for Low-Power and Lossy Networks), um protocolo que constrói uma topologia de árvore da rede. A proposta foi avaliada em uma extensão da plataforma MininetFed, que adicionou suporte a redes RPL, monitoramento de consumo de energia e um algoritmo de seleção para prolongar a vida útil das redes IoT durante o treinamento sem comprometer a eficácia. A abordage proposta atingiu uma redução de aproximadamente 6,5% no consumo de nós centrais.
Palavras-chave:
Aprendizado Federado, Redes IoT, Eficiência Energética, RPL (Routing Protocol for Low-Power and Lossy Networks), Seleção de Dispositivos, MininetFed
Referências
AbdulRahman, S., Tout, H., Mourad, A., and Talhi, C. (2020). Fedmccs: Multicriteria client selection model for optimal IoT federated learning. IEEE Internet of Things Journal, 8(6), 4723–4735.
Albishari, M., Alhassan, M., Alhusseini, M., and Zaidan, A. A. (2024). Federated deep learning models for detecting RPL attacks on large-scale hybrid IoT networks. Computer Networks, 254, 110837.
Bastos, J., Sarmento, E., Villaça, R., and Mota, V. (2024). Mininetfed: Uma ferramenta para emulação e análise de redes.
Flinn, J. and Satyanarayanan, M. (1999). Energy-aware adaptation for mobile applications. ACM SIGOPS Operating Systems Review, 33(5), 48–63.
Fontes, R. R., Afzal, S., Brito, S. H., Santos, M. A., and Rothenberg, C. E. (2015). Mininet-wifi: Emulating software-defined wireless networks. In 11th CNSM. IEEE.
Fu, L., Zhang, H., Gao, G., Zhang, M., and Liu, X. (2023). Client selection in federated learning: Principles, challenges, and opportunities. IEEE Internet of Things Journal.
Kairouz, P., McMahan, H. B., Avent, B., and others. (2021). Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 14(1–2), 1–210.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
Li, T., Sahu, A. K., Talwalkar, A., and Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
Peuster, M., Karl, H., and van Rossem, S. (2016). Medicine: Rapid prototyping of production-ready network services in multi-pop environments. In IEEE Conference on Network Function Virtualization and Software Defined Networks, pages 148–153.
Polastre, J., Szewczyk, R., and Culler, D. (2005). Telos: Enabling ultra-low power wireless research. In IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, pages 364–369. IEEE.
Sarmento, E., Bastos, J., Mota, V., and Villaça, R. (2024). Mininetfed: A tool for assessing client selection, aggregation, and security in federated learning. In IEEE 10th World Forum on Internet of Things (WFIoT), pages 1–6. IEEE.
Sharma, P., Sakthivel, T., and Alnajjar, I. A. (2023). Optimized federated learning with ensemble of sequential models for detecting RPL routing attacks for AMI networks.
Tariq, N., Khan, R., Almufareh, M. F., Humayun, M., and Shaheen, M. (2024). A federated learning mechanism for mitigating selective forwarding attacks in RPL-based Internet of Things. In IEEE ICC Workshops, pages 871–877.
Winter, T., Thubert, P., Brandt, A., Hui, J., and Group, R. W. (2012). RPL: IPv6 Routing Protocol for Low-Power and Lossy Networks. RFC 6550, IETF.
Ye, W., Heidemann, J., and Estrin, D. (2002). An energy-efficient MAC protocol for wireless sensor networks. In Proceedings. Twenty-first Annual Joint Conference of the IEEE Computer and Communications Societies, volume 3, pages 1567–1576. IEEE.
Yu, L., Albelaihi, R., Sun, X., Ansari, N., and Devetsikiotis, M. (2021). Jointly optimizing client selection and resource management in wireless federated learning for Internet of Things. IEEE Internet of Things Journal, 9(6), 4385–4395.
Zhao, J., Feng, Y., Chang, X., and Liu, C. H. (2022). Energy-efficient client selection in federated learning with heterogeneous data on edge. Peer-to-Peer Networking and Applications, 15(2), 1139–1151.
Albishari, M., Alhassan, M., Alhusseini, M., and Zaidan, A. A. (2024). Federated deep learning models for detecting RPL attacks on large-scale hybrid IoT networks. Computer Networks, 254, 110837.
Bastos, J., Sarmento, E., Villaça, R., and Mota, V. (2024). Mininetfed: Uma ferramenta para emulação e análise de redes.
Flinn, J. and Satyanarayanan, M. (1999). Energy-aware adaptation for mobile applications. ACM SIGOPS Operating Systems Review, 33(5), 48–63.
Fontes, R. R., Afzal, S., Brito, S. H., Santos, M. A., and Rothenberg, C. E. (2015). Mininet-wifi: Emulating software-defined wireless networks. In 11th CNSM. IEEE.
Fu, L., Zhang, H., Gao, G., Zhang, M., and Liu, X. (2023). Client selection in federated learning: Principles, challenges, and opportunities. IEEE Internet of Things Journal.
Kairouz, P., McMahan, H. B., Avent, B., and others. (2021). Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 14(1–2), 1–210.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
Li, T., Sahu, A. K., Talwalkar, A., and Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
Peuster, M., Karl, H., and van Rossem, S. (2016). Medicine: Rapid prototyping of production-ready network services in multi-pop environments. In IEEE Conference on Network Function Virtualization and Software Defined Networks, pages 148–153.
Polastre, J., Szewczyk, R., and Culler, D. (2005). Telos: Enabling ultra-low power wireless research. In IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, pages 364–369. IEEE.
Sarmento, E., Bastos, J., Mota, V., and Villaça, R. (2024). Mininetfed: A tool for assessing client selection, aggregation, and security in federated learning. In IEEE 10th World Forum on Internet of Things (WFIoT), pages 1–6. IEEE.
Sharma, P., Sakthivel, T., and Alnajjar, I. A. (2023). Optimized federated learning with ensemble of sequential models for detecting RPL routing attacks for AMI networks.
Tariq, N., Khan, R., Almufareh, M. F., Humayun, M., and Shaheen, M. (2024). A federated learning mechanism for mitigating selective forwarding attacks in RPL-based Internet of Things. In IEEE ICC Workshops, pages 871–877.
Winter, T., Thubert, P., Brandt, A., Hui, J., and Group, R. W. (2012). RPL: IPv6 Routing Protocol for Low-Power and Lossy Networks. RFC 6550, IETF.
Ye, W., Heidemann, J., and Estrin, D. (2002). An energy-efficient MAC protocol for wireless sensor networks. In Proceedings. Twenty-first Annual Joint Conference of the IEEE Computer and Communications Societies, volume 3, pages 1567–1576. IEEE.
Yu, L., Albelaihi, R., Sun, X., Ansari, N., and Devetsikiotis, M. (2021). Jointly optimizing client selection and resource management in wireless federated learning for Internet of Things. IEEE Internet of Things Journal, 9(6), 4385–4395.
Zhao, J., Feng, Y., Chang, X., and Liu, C. H. (2022). Energy-efficient client selection in federated learning with heterogeneous data on edge. Peer-to-Peer Networking and Applications, 15(2), 1139–1151.
Publicado
19/05/2025
Como Citar
SCHMITZ BASTOS, Johann J.; C. BATISTA, João Pedro; DOS REIS FONTES, Ramon; CERQUEIRA, Eduardo; S. VILLAÇA, Rodolfo; F. S. MOTA, Vinícius.
Otimizando Energia no Aprendizado Federado em Redes de Baixa potência e com Alta Taxa de Perda de Pacotes. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 43. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 43-56.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2025.5786.
