CAONS: Controle de Admissão On-line para RAN Slicing Baseado na Convergência de Comunicação e Computação
Resumo
A implantação das redes móveis 5G têm alavancado o Network Slicing (NS), uma tecnologia disruptiva, que pode fornecer recursos dedicados nos sistemas móveis, auxiliando na rentabilização da infraestrutura física e lógica. Contudo, NS cria novos desafios, como: o (1) gerenciamento dinâmico e flexível de recursos da Radio Access Network (RAN), (2) a integração harmoniosa dos serviços em Multi Access Edge Computing (MEC), e (3) admissão de novos inquilinos na rede. Neste trabalho, propomos um algoritmo de controle de admissão para NS ciente de recursos da RAN, que utiliza a técnica de overbooking para aumentar a utilização da infraestrutura, penalizando a operadora em caso de violações. Avaliamos o modelo proposto e comparamos com soluções conhecidas, utilizando dados de diferentes aplicações.
Referências
Asawa, M. and Teneketzis, D. (1996). Multi-armed bandits with switching penalties. IEEE transactions on automatic control, 41(3):328-348.
Bega, D. et al. (2019). A machine learning approach to 5G infrastructure market optimization. IEEE Transactions on Mobile Computing, 19(3):498-512.
Black, P. E. (2005). Greedy algorithm. Dictionary of Algorithms and Data Structures, 2:62.
Chen, G., Liew, S. C., and Shao, Y. (2022). Uncertainty-of-information scheduling: A restless multi-armed bandit framework. IEEE Transactions on Information Theory.
Cominardi, L., Deiss, T., Filippou, M., Sciancalepore, V., Giust, F., and Sabella, D. (2020). Mec support for network slicing: Status and limitations from a standardization viewpoint. IEEE Communications Standards Magazine, 4(2):22-30.
Elayoubi, S. E. et al. (2019). 5G RAN slicing for verticals: Enablers and challenges. IEEE Communications Magazine, 57:28-34.
Gao, Z., Han, Y., Ren, Z., and Zhou, Z. (2019). Batched multi-armed bandits problem. Advances in Neural Information Processing Systems, 32.
Garivier, A. and Cappé, O. (2011). The kl-ucb algorithm for bounded stochastic bandits and beyond. In Kakade, S. M. and von Luxburg, U., editors, Proceedings of the 24th Annual Conference on Learning Theory, volume 19 of Proceedings of Machine Learning Research, pages 359-376, Budapest, Hungary. PMLR.
Guan, Z., Ji, K., Bucci Jr, D. J., Hu, T. Y., Palombo, J., Liston, M., and Liang, Y. (2020). Robust stochastic bandit algorithms under probabilistic unbounded adversarial attack. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 4036-4043.
Hwang, S. and Park, S. (2017). On the effects of resource usage ratio on data rate in LTE systems. In 2017 19th International Conference on Advanced Communication Technology (ICACT), pages 78-80.
Li, F., Yu, D., Yang, H., Yu, J., Karl, H., and Cheng, X. (2020). Multi-armed-bandit-based spectrum scheduling algorithms in wireless networks: A survey. IEEE Wireless Communications, 27(1):24-30.
Li, R. et al. (2018a). Deep reinforcement learning for resource management in network slicing. IEEE Access, 6:74429-74441.
Li, Z., Uusitalo, M. A., Shariatmadari, H., and Singh, B. (2018b). 5G urllc: Design challenges and system concepts. In 2018 15th international symposium on wireless communication systems (ISWCS), pages 1-6. IEEE.
Lima, H. V., Bruno, G. Z., Grings, F. H., Both, C. B., Alberti, A. M., Cardoso, K. V., and Correa, S. L. (2022). Controle de admissão para network slicing ciente de recursos de rede e de processamento.
Mahajan, A. and Teneketzis, D. (2008). Multi-armed bandit problems. In Foundations and applications of sensor management, pages 121-151. Springer.
Malandrino, F. et al. (2020). From megabits to cpu ticks: Enriching a demand trace in the age of mec. IEEE Transactions on Big Data, 6(1):43-50.
Ontanón, S. (2013). The combinatorial multi-armed bandit problem and its application to real-time strategy games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 9.
Rifai, B. and Supriyanto, E. (2017). Management system failover dengan routing dinamis open shortest path first dan border gateway protocol. Jurnal Ilmu Pengetahuan dan Teknologi Komputer, 3:39-46.
Sciancalepore, V., Zanzi, L., Costa-Perez, X., and Capone, A. (2021). Onets: online network slice broker from theory to practice. IEEE Transactions on Wireless Communications, 21(1):121-134.
Weisbecker, F. (2013). Status of Linux dynticks. In 9th annual workshop on Operating Systems Platforms for Embedded Real-Time applications.
Zhang, S. (2019). An overview of network slicing for 5G. IEEE Wireless Communications, 26(3):111-117.
Bega, D. et al. (2019). A machine learning approach to 5G infrastructure market optimization. IEEE Transactions on Mobile Computing, 19(3):498-512.
Black, P. E. (2005). Greedy algorithm. Dictionary of Algorithms and Data Structures, 2:62.
Chen, G., Liew, S. C., and Shao, Y. (2022). Uncertainty-of-information scheduling: A restless multi-armed bandit framework. IEEE Transactions on Information Theory.
Cominardi, L., Deiss, T., Filippou, M., Sciancalepore, V., Giust, F., and Sabella, D. (2020). Mec support for network slicing: Status and limitations from a standardization viewpoint. IEEE Communications Standards Magazine, 4(2):22-30.
Elayoubi, S. E. et al. (2019). 5G RAN slicing for verticals: Enablers and challenges. IEEE Communications Magazine, 57:28-34.
Gao, Z., Han, Y., Ren, Z., and Zhou, Z. (2019). Batched multi-armed bandits problem. Advances in Neural Information Processing Systems, 32.
Garivier, A. and Cappé, O. (2011). The kl-ucb algorithm for bounded stochastic bandits and beyond. In Kakade, S. M. and von Luxburg, U., editors, Proceedings of the 24th Annual Conference on Learning Theory, volume 19 of Proceedings of Machine Learning Research, pages 359-376, Budapest, Hungary. PMLR.
Guan, Z., Ji, K., Bucci Jr, D. J., Hu, T. Y., Palombo, J., Liston, M., and Liang, Y. (2020). Robust stochastic bandit algorithms under probabilistic unbounded adversarial attack. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 4036-4043.
Hwang, S. and Park, S. (2017). On the effects of resource usage ratio on data rate in LTE systems. In 2017 19th International Conference on Advanced Communication Technology (ICACT), pages 78-80.
Li, F., Yu, D., Yang, H., Yu, J., Karl, H., and Cheng, X. (2020). Multi-armed-bandit-based spectrum scheduling algorithms in wireless networks: A survey. IEEE Wireless Communications, 27(1):24-30.
Li, R. et al. (2018a). Deep reinforcement learning for resource management in network slicing. IEEE Access, 6:74429-74441.
Li, Z., Uusitalo, M. A., Shariatmadari, H., and Singh, B. (2018b). 5G urllc: Design challenges and system concepts. In 2018 15th international symposium on wireless communication systems (ISWCS), pages 1-6. IEEE.
Lima, H. V., Bruno, G. Z., Grings, F. H., Both, C. B., Alberti, A. M., Cardoso, K. V., and Correa, S. L. (2022). Controle de admissão para network slicing ciente de recursos de rede e de processamento.
Mahajan, A. and Teneketzis, D. (2008). Multi-armed bandit problems. In Foundations and applications of sensor management, pages 121-151. Springer.
Malandrino, F. et al. (2020). From megabits to cpu ticks: Enriching a demand trace in the age of mec. IEEE Transactions on Big Data, 6(1):43-50.
Ontanón, S. (2013). The combinatorial multi-armed bandit problem and its application to real-time strategy games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 9.
Rifai, B. and Supriyanto, E. (2017). Management system failover dengan routing dinamis open shortest path first dan border gateway protocol. Jurnal Ilmu Pengetahuan dan Teknologi Komputer, 3:39-46.
Sciancalepore, V., Zanzi, L., Costa-Perez, X., and Capone, A. (2021). Onets: online network slice broker from theory to practice. IEEE Transactions on Wireless Communications, 21(1):121-134.
Weisbecker, F. (2013). Status of Linux dynticks. In 9th annual workshop on Operating Systems Platforms for Embedded Real-Time applications.
Zhang, S. (2019). An overview of network slicing for 5G. IEEE Wireless Communications, 26(3):111-117.
Publicado
22/05/2023
Como Citar
LIMA, Henrique V.; CORREA, Sand L.; CARDOSO, Kleber V..
CAONS: Controle de Admissão On-line para RAN Slicing Baseado na Convergência de Comunicação e Computação. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 41. , 2023, Brasília/DF.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 393-406.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2023.517.
