Transmissão Inteligente de Parâmetros no Aprendizado Federado: Gerenciando o trade-off entre o desempenho e o consumo energético em Redes IoT sem Fio
Resumo
O Aprendizado Federado (Federated Learning - FL) permite que dispositivos treinem um modelo global de aprendizado de máquina sem o compartilhamento de dados, preservando a privacidade dos usuários. O FL enfrenta desafios significativos relacionados ao custo energético, especialmente em ambientes com recursos limitados, como redes sem fio e soluções emergentes da Internet das Coisas (Internet of Things - IoT). Este trabalho apresenta uma estratégia de transmissão inteligente de parâmetros no contexto do FL em redes IoT sem fio. A abordagem proposta é baseada na diferença percentual relativa entre os pesos antigos e os novos pesos atualizados dos modelos locais, utilizando um limiar definido para decidir sobre a necessidade de transmissão. Os resultados demonstram que a transmissão condicional reduz o número de transmissões sem comprometer significativamente a acurácia do modelo global.
Palavras-chave:
Aprendizado Federado, IoT, Transmissão Inteligente, Consumo Energético, Redes sem Fio
Referências
Amannejad, Y. (2020). Building and Evaluating Federated Models for Edge Computing. 2020 16th International Conference on Network and Service Management (CNSM), pages 1–5.
Asad, M., Moustafa, A., Ito, T., and Aslam, M. (2020). Evaluating the Communication Efficiency in Federated Learning Algorithms. CoRR, abs/2004.02738.
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Parcollet, T., and Lane, N. D. (2020). Flower: A Friendly Federated Learning Research Framework. CoRR.
Chen, H., Huang, S., Zhang, D., Xiao, M., Skoglund, M., and Poor, H. V. (2022). Federated Learning Over Wireless IoT Networks With Optimized Communication and Resources. IEEE Internet of Things Journal, 9(17):16592–16605.
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., and Cui, S. (2021). A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks. IEEE Transactions on Wireless Communications, 20(1):269–283.
ETSI (2022). Multi-Access Edge Computing (MEC) Framework and Reference Architecture. ETSI Standard GS MEC 003.
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2021). A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection. IEEE Transactions on Knowledge and Data Engineering, PP:1–1.
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2016). Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv.
Nakayama, K. and Jeno, G. (2022). Federated Learning with Python: Design and implement a federated learning system and develop applications using existing frameworks. Packt Publishing.
Wong, K. D. (2012). Fundamentals of Wireless Communication Engineering Technologies. Wiley Telecom. Chapters 1–25.
Yang, Z., Chen, M., Wong, K.-K., Poor, H. V., and Cui, S. (2022). Federated Learning for 6G: Applications, Challenges, and Opportunities. Engineering, 8:33–41.
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., and Chandra, V. (2022). Federated Learning with Non-IID Data. arXiv.
Zhu, G., Wang, Y., and Huang, K. (2020). Broadband Analog Aggregation for Low-Latency Federated Edge Learning. IEEE Transactions on Wireless Communications, 19(1):491–506.
Asad, M., Moustafa, A., Ito, T., and Aslam, M. (2020). Evaluating the Communication Efficiency in Federated Learning Algorithms. CoRR, abs/2004.02738.
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Parcollet, T., and Lane, N. D. (2020). Flower: A Friendly Federated Learning Research Framework. CoRR.
Chen, H., Huang, S., Zhang, D., Xiao, M., Skoglund, M., and Poor, H. V. (2022). Federated Learning Over Wireless IoT Networks With Optimized Communication and Resources. IEEE Internet of Things Journal, 9(17):16592–16605.
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., and Cui, S. (2021). A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks. IEEE Transactions on Wireless Communications, 20(1):269–283.
ETSI (2022). Multi-Access Edge Computing (MEC) Framework and Reference Architecture. ETSI Standard GS MEC 003.
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2021). A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection. IEEE Transactions on Knowledge and Data Engineering, PP:1–1.
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2016). Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv.
Nakayama, K. and Jeno, G. (2022). Federated Learning with Python: Design and implement a federated learning system and develop applications using existing frameworks. Packt Publishing.
Wong, K. D. (2012). Fundamentals of Wireless Communication Engineering Technologies. Wiley Telecom. Chapters 1–25.
Yang, Z., Chen, M., Wong, K.-K., Poor, H. V., and Cui, S. (2022). Federated Learning for 6G: Applications, Challenges, and Opportunities. Engineering, 8:33–41.
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., and Chandra, V. (2022). Federated Learning with Non-IID Data. arXiv.
Zhu, G., Wang, Y., and Huang, K. (2020). Broadband Analog Aggregation for Low-Latency Federated Edge Learning. IEEE Transactions on Wireless Communications, 19(1):491–506.
Publicado
05/12/2024
Como Citar
DE OLIVEIRA, Renan R.; S. BELO, Pedro Augusto; C. SILVA, Nickolas Carlos; OLIVEIRA-JR, Antonio.
Transmissão Inteligente de Parâmetros no Aprendizado Federado: Gerenciando o trade-off entre o desempenho e o consumo energético em Redes IoT sem Fio. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 12. , 2024, Ceres/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 11-20.
DOI: https://doi.org/10.5753/erigo.2024.4832.
