CANOPY: Alocação Orientada por Predição Energética de Aplicações no Contínuo Computacional
Resumo
A alocação de módulos energeticamente eficiente tornou-se um desafio crítico no contínuo computacional, onde aplicações modulares de IoT precisam operar sob recursos heterogêneos e cargas de trabalho dinâmicas. Embora abordagens baseadas em Aprendizado por Reforço tenham sido amplamente exploradas, elas frequentemente exigem extensos períodos de treinamento e, em geral, tratam o consumo de energia como uma métrica secundária ou reativa. Este artigo propõe o CANOPY, uma estratégia de Alocação Ótima de Aplicações Consciente do Contínuo guiada por predição de energia. O CANOPY emprega um modelo de aprendizado supervisionado baseado em um Regressor de Floresta Aleatória para estimar proativamente o consumo de energia da alocação de módulos de aplicações em dispositivos candidatos. Essas predições são integradas diretamente à lógica de alocação, possibilitando decisões energeticamente eficientes ao longo do contínuo computacional. Os resultados experimentais mostram que o CANOPY supera consistentemente estratégias de alocação do estado da arte, alcançando reduções no consumo de energia de até 12,42% em cenários com saturação de recursos.Referências
Ansere, J. A., Gyamfi, E., Sharma, V., Shin, H., Dobre, O. A., and Duong, T. Q. (2024). Quantum deep reinforcement learning for dynamic resource allocation in mobile edge computing-based iot systems. IEEE Transactions on Wireless Communications, 23(6):6221–6233.
Atwal, S., Singh, D., and Chhabra, A. (2025). Resource allocation strategies for edge and fog computing in the cloud continuum. In 2025 International Conference on Intelligent Control, Computing and Communications (IC3), pages 208–213.
Bai, W. and Qian, C. (2021). Deep reinforcement learning for joint offloading and resource allocation in fog computing. In 2021 IEEE 12th International Conference on Software Engineering and Service Science (ICSESS), pages 131–134.
Goudarzi, M., Palaniswami, M., and Buyya, R. (2023). A distributed deep reinforcement learning technique for application placement in edge and fog computing environments. IEEE Transactions on Mobile Computing, 22(5):2491–2505.
Gupta, H., Vahid Dastjerdi, A., Ghosh, S. K., and Buyya, R. (2017). ifogsim: A toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments. Software: Practice and Experience, 47(9):1275–1296.
Huang, Y. and Xie, T. (2024). Edge computing resource allocation method based on federated reinforcement learning. In 2024 2nd International Conference on Signal Processing and Intelligent Computing (SPIC), pages 254–258.
Karthiga, M., Paramasivam, J., Raja, P. V., Kumar Suman, S., Bhagyalakshmi, L., and Poddar, H. (2025). Optimizing edge computing performance using machine learning for low-latency applications. In 2025 World Skills Conference on Universal Data Analytics and Sciences (WorldSUAS), pages 1–6.
Li, X., Wang, N., Li, D., Ruan, J., and Liu, H. (2025). A cloud-edge-devices computing power allocation algorithm based on intelligent collaborative computing. In 2025 IEEE 3rd International Conference on Image Processing and Computer Applications (ICIPCA), pages 157–161.
Oliveira, L. T., Bittencourt, L. F., Genez, T. A., de Lara, E., and Peixoto, M. L. (2024). Enhancing modular application placement in a hierarchical fog computing: A latency and communication cost-sensitive approach. Computer Communications, 216:95–111.
Peixoto, M. L. M., Genez, T. A. L., and Bittencourt, L. F. (2022). Hierarchical scheduling mechanisms in multi-level fog computing. IEEE Transactions on Services Computing, 15(5):2824–2837.
Rajagopal, S. M., Supriya, M., and Buyya, R. (2023). Resource provisioning using meta-heuristic methods for iot microservices with mobility management. IEEE Access, 11:60915–60938.
Reis, G., Oliveira, L., Prazeres, C., Veiga, L., and Peixoto, M. (2026). Elsa: Energy-aware and latency-sensitive resource allocation in edge-cloud continuum. Future Generation Computer Systems, 182:108506.
Ren, Z., Jiang, W., Liu, A., Huang, S., Mu, J., Liu, S., and Gu, W. (2025). Network resource optimization for mobile edge computing: A deep learning approach. In 2025 IEEE 34th Wireless and Optical Communications Conference (WOCC), pages 117–121.
Tran-Dang, H., Bhardwaj, S., Rahim, T., Musaddiq, A., and Kim, D.-S. (2022). Reinforcement learning based resource management for fog computing environment: Literature review, challenges, and open issues. Journal of Communications and Networks, 24(1):83–98.
Wang, C., Guo, R., Xiu, P., Li, X., and Wang, H. (2024). Research on resource scheduling algorithm optimization in cloud computing environment based on deep learning. In 2024 4th International Conference on Electronic Information Engineering and Computer Communication (EIECC), pages 918–922.
Yuan, X., Sun, M., and Lou, W. (2022). A dynamic deep-learning-based virtual edge node placement scheme for edge cloud systems in mobile environment. IEEE Transactions on Cloud Computing, 10(2):1317–1328.
Zhang, D.-G., Zhang, J., Zhu, X.-M., Zhang, T., Zheng, X.-M., and Jia, H.-J. (2025). Novel approach of computational resource allocation in fog computing based on deep reinforcement learning strategies. IEEE Internet of Things Journal, 12(20):43829–43841.
Atwal, S., Singh, D., and Chhabra, A. (2025). Resource allocation strategies for edge and fog computing in the cloud continuum. In 2025 International Conference on Intelligent Control, Computing and Communications (IC3), pages 208–213.
Bai, W. and Qian, C. (2021). Deep reinforcement learning for joint offloading and resource allocation in fog computing. In 2021 IEEE 12th International Conference on Software Engineering and Service Science (ICSESS), pages 131–134.
Goudarzi, M., Palaniswami, M., and Buyya, R. (2023). A distributed deep reinforcement learning technique for application placement in edge and fog computing environments. IEEE Transactions on Mobile Computing, 22(5):2491–2505.
Gupta, H., Vahid Dastjerdi, A., Ghosh, S. K., and Buyya, R. (2017). ifogsim: A toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments. Software: Practice and Experience, 47(9):1275–1296.
Huang, Y. and Xie, T. (2024). Edge computing resource allocation method based on federated reinforcement learning. In 2024 2nd International Conference on Signal Processing and Intelligent Computing (SPIC), pages 254–258.
Karthiga, M., Paramasivam, J., Raja, P. V., Kumar Suman, S., Bhagyalakshmi, L., and Poddar, H. (2025). Optimizing edge computing performance using machine learning for low-latency applications. In 2025 World Skills Conference on Universal Data Analytics and Sciences (WorldSUAS), pages 1–6.
Li, X., Wang, N., Li, D., Ruan, J., and Liu, H. (2025). A cloud-edge-devices computing power allocation algorithm based on intelligent collaborative computing. In 2025 IEEE 3rd International Conference on Image Processing and Computer Applications (ICIPCA), pages 157–161.
Oliveira, L. T., Bittencourt, L. F., Genez, T. A., de Lara, E., and Peixoto, M. L. (2024). Enhancing modular application placement in a hierarchical fog computing: A latency and communication cost-sensitive approach. Computer Communications, 216:95–111.
Peixoto, M. L. M., Genez, T. A. L., and Bittencourt, L. F. (2022). Hierarchical scheduling mechanisms in multi-level fog computing. IEEE Transactions on Services Computing, 15(5):2824–2837.
Rajagopal, S. M., Supriya, M., and Buyya, R. (2023). Resource provisioning using meta-heuristic methods for iot microservices with mobility management. IEEE Access, 11:60915–60938.
Reis, G., Oliveira, L., Prazeres, C., Veiga, L., and Peixoto, M. (2026). Elsa: Energy-aware and latency-sensitive resource allocation in edge-cloud continuum. Future Generation Computer Systems, 182:108506.
Ren, Z., Jiang, W., Liu, A., Huang, S., Mu, J., Liu, S., and Gu, W. (2025). Network resource optimization for mobile edge computing: A deep learning approach. In 2025 IEEE 34th Wireless and Optical Communications Conference (WOCC), pages 117–121.
Tran-Dang, H., Bhardwaj, S., Rahim, T., Musaddiq, A., and Kim, D.-S. (2022). Reinforcement learning based resource management for fog computing environment: Literature review, challenges, and open issues. Journal of Communications and Networks, 24(1):83–98.
Wang, C., Guo, R., Xiu, P., Li, X., and Wang, H. (2024). Research on resource scheduling algorithm optimization in cloud computing environment based on deep learning. In 2024 4th International Conference on Electronic Information Engineering and Computer Communication (EIECC), pages 918–922.
Yuan, X., Sun, M., and Lou, W. (2022). A dynamic deep-learning-based virtual edge node placement scheme for edge cloud systems in mobile environment. IEEE Transactions on Cloud Computing, 10(2):1317–1328.
Zhang, D.-G., Zhang, J., Zhu, X.-M., Zhang, T., Zheng, X.-M., and Jia, H.-J. (2025). Novel approach of computational resource allocation in fog computing based on deep reinforcement learning strategies. IEEE Internet of Things Journal, 12(20):43829–43841.
Publicado
25/05/2026
Como Citar
REIS, Giselly A.; FIGUEIREDO, Gustavo B.; SANTOS, Bruno; PRAZERES, Cassio; VEIGA, Luis; PEIXOTO, Maycon L. M..
CANOPY: Alocação Orientada por Predição Energética de Aplicações no Contínuo Computacional. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 10. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 71-84.
ISSN 2595-2706.
DOI: https://doi.org/10.5753/courb.2026.23223.
