Análise de Desempenho do Overhead Computacional de xApps Baseadas em Aprendizado por Reforço em Open-RAN
Resumo
A arquitetura Open Radio Access Network (Open-RAN) viabiliza a execução de aplicações inteligentes (xApps) no Near-Real-Time RAN Intelligent Controller (Near-RT RIC), propiciando a integração de técnicas de Aprendizado por Reforço Profundo (DRL) para a automação do controle da RAN. Este trabalho apresenta uma análise de desempenho do overhead computacional de xApps baseadas em DRL, comparando os algoritmos Deep Q-Network (DQN) e Proximal Policy Optimization (PPO) com uma política baseline. As simulações foram realizadas em um ambiente Open-RAN baseado no Blueprint Nori v1, considerando perfis de serviço eMBB e URLLC e diferentes níveis de carga computacional artificial. Os resultados indicam aumento consistente do tempo de decisão com a elevação da carga computacional avaliada, sendo mais elevado para algoritmos baseados em DRL, mas permanecendo compatível com os requisitos temporais do Near-RT RIC.Referências
Alam, K., Habibi, M. A., Tammen, M., Krummacker, D., Saad, W., Renzo, M. D., Melodia, T., Costa-Pérez, X., Debbah, M., Dutta, A., and Schotten, H. D. (2026). A comprehensive tutorial and survey of o-ran: Exploring slicing-aware architecture, deployment options, use cases, and challenges. IEEE Communications Surveys Tutorials, 28:1637–1678.
Bansbach, E.-M., Eliachevitch, V., and Schmalen, L. (2021). Deep reinforcement learning for wireless resource allocation using buffer state information. In 2021 IEEE Global Communications Conference (GLOBECOM), pages 1–6. IEEE Press.
Bordin, M., Lacava, A., Polese, M., Satish, S., Nittoor, M. A., Sivaraj, R., Cuomo, F., and Melodia, T. (2025). Design and evaluation of deep reinforcement learning for energy saving in open ran. In 2025 IEEE 22nd Consumer Communications Networking Conference (CCNC), pages 1–6.
Chen, G., Shao, R., Shen, F., and Zeng, Q. (2023). Slicing resource allocation based on dueling dqn for embb and urllc hybrid services in heterogeneous integrated networks. Sensors, 23(5):2518.
Hussien, O. and Jahankhani, H. (2025). Optimizing 5g resource allocation in pso with machine learning approach to open ran architectures. Journal of Next-Generation Research 5.0.
Menezes, D., Medeiros, D., Couto, R., Caminha, P., Souza, L., Táparo, F., Thomaz, G., Valle, J., Oliveira, F., Campista, M., Costa, L., and Moraes, I. (2023). Ameaças e Vulnerabilidades em Open RAN: Desafios e Soluções, pages 150–201.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540):529–533.
O-RAN Software Community (O-RAN SC) (2025). O-ran sc non-rt ric project – nonrtric master documentation. Available at: [link].
Park, H., Seol, K., Song, S., Lee, Y., and Park, L. (2024). Recent research on reinforcement learning for open ran. In 2024 15th International Conference on Information and Communication Technology Convergence (ICTC), pages 1744–1745.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., and Melodia, T. (2023). Colo-ran: Developing machine learning-based xapps for open ran closed-loop control on programmable experimental platforms. IEEE Transactions on Mobile Computing, 22(10):5787–5800.
Singh, S. K., Singh, R., and Kumbhani, B. (2020). The evolution of radio access network towards open-ran: Challenges and opportunities. In 2020 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), pages 1–6.
Sohaib, R. M., Shah, S. T., Jamshed, M. A., Onireti, O., and Yadav, P. (2025). Optimizing urllc in open ran: A deep reinforcement learning-based trade-off analysis. IEEE Communications Standards Magazine, 9(3):33–39.
Soltani, S., Amanloo, A., Shojafar, M., and Tafazolli, R. (2025). Intelligent control in 6g open ran: Security risk or opportunity? IEEE Open Journal of the Communications Society, 6:840–880.
Thieu, H.-T., Pham, V.-Q., Kak, A., and Choi, N. (2023). Demystifying the near-real-time ric: Architecture, operations, and benchmarking insights. In IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pages 1–8.
Tsampazi, M., D’Oro, S., Polese, M., Bonati, L., Poitau, G., Healy, M., and Melodia, T. (2023). A comparative analysis of deep reinforcement learning-based xapps in o-ran. In GLOBECOM 2023 - 2023 IEEE Global Communications Conference, pages 1638–1643.
Zheng, J. (2025). Research on deep reinforcement learning-based resource allocation strategies for wireless networks. In Proceedings of the 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI ’25, pages 170–176, New York, NY, USA. Association for Computing Machinery.
Bansbach, E.-M., Eliachevitch, V., and Schmalen, L. (2021). Deep reinforcement learning for wireless resource allocation using buffer state information. In 2021 IEEE Global Communications Conference (GLOBECOM), pages 1–6. IEEE Press.
Bordin, M., Lacava, A., Polese, M., Satish, S., Nittoor, M. A., Sivaraj, R., Cuomo, F., and Melodia, T. (2025). Design and evaluation of deep reinforcement learning for energy saving in open ran. In 2025 IEEE 22nd Consumer Communications Networking Conference (CCNC), pages 1–6.
Chen, G., Shao, R., Shen, F., and Zeng, Q. (2023). Slicing resource allocation based on dueling dqn for embb and urllc hybrid services in heterogeneous integrated networks. Sensors, 23(5):2518.
Hussien, O. and Jahankhani, H. (2025). Optimizing 5g resource allocation in pso with machine learning approach to open ran architectures. Journal of Next-Generation Research 5.0.
Menezes, D., Medeiros, D., Couto, R., Caminha, P., Souza, L., Táparo, F., Thomaz, G., Valle, J., Oliveira, F., Campista, M., Costa, L., and Moraes, I. (2023). Ameaças e Vulnerabilidades em Open RAN: Desafios e Soluções, pages 150–201.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540):529–533.
O-RAN Software Community (O-RAN SC) (2025). O-ran sc non-rt ric project – nonrtric master documentation. Available at: [link].
Park, H., Seol, K., Song, S., Lee, Y., and Park, L. (2024). Recent research on reinforcement learning for open ran. In 2024 15th International Conference on Information and Communication Technology Convergence (ICTC), pages 1744–1745.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., and Melodia, T. (2023). Colo-ran: Developing machine learning-based xapps for open ran closed-loop control on programmable experimental platforms. IEEE Transactions on Mobile Computing, 22(10):5787–5800.
Singh, S. K., Singh, R., and Kumbhani, B. (2020). The evolution of radio access network towards open-ran: Challenges and opportunities. In 2020 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), pages 1–6.
Sohaib, R. M., Shah, S. T., Jamshed, M. A., Onireti, O., and Yadav, P. (2025). Optimizing urllc in open ran: A deep reinforcement learning-based trade-off analysis. IEEE Communications Standards Magazine, 9(3):33–39.
Soltani, S., Amanloo, A., Shojafar, M., and Tafazolli, R. (2025). Intelligent control in 6g open ran: Security risk or opportunity? IEEE Open Journal of the Communications Society, 6:840–880.
Thieu, H.-T., Pham, V.-Q., Kak, A., and Choi, N. (2023). Demystifying the near-real-time ric: Architecture, operations, and benchmarking insights. In IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pages 1–8.
Tsampazi, M., D’Oro, S., Polese, M., Bonati, L., Poitau, G., Healy, M., and Melodia, T. (2023). A comparative analysis of deep reinforcement learning-based xapps in o-ran. In GLOBECOM 2023 - 2023 IEEE Global Communications Conference, pages 1638–1643.
Zheng, J. (2025). Research on deep reinforcement learning-based resource allocation strategies for wireless networks. In Proceedings of the 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI ’25, pages 170–176, New York, NY, USA. Association for Computing Machinery.
Publicado
19/07/2026
Como Citar
GONÇALVES, Robert V. O.; STANCANELLI, Elvis M. G.; COUTINHO, Emanuel F.; S. FILHO, Francisco Helder C. dos.
Análise de Desempenho do Overhead Computacional de xApps Baseadas em Aprendizado por Reforço em Open-RAN. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 25. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 46-57.
ISSN 2595-6167.
DOI: https://doi.org/10.5753/wperformance.2026.19621.
