Fair Max Rate: Um Escalonador de Recursos Baseado em Aprendizado por Reforc¸o para Redes 5G

• Diego Canizio Lopes IFAC / UFF http://orcid.org/0009-0007-9907-7727
• André Nasserala UFAC https://orcid.org/0000-0001-5852-5975
• Ian Vilar Bastos UERJ https://orcid.org/0000-0003-1000-5211
• Igor M. Moraes UFF https://orcid.org/0000-0002-5919-7923

DOI: https://doi.org/10.5753/sbrc.2025.6223

Abstract

This paper proposes a resource scheduler for 5G networks based on reinforcement learning that maximizes network throughput by allocating resources according to the spectral efficiency of each user device. The proposed scheduler ensures a minimum throughput for each device, balancing efficiency and fairness. The evaluation is conducted through simulations based on throughput and Jain’s Index metrics. The performance of the proposed scheduler is compared to the classic algorithms Round Robin (RR), Proportional Fair (PF), and Max Rate (MR), achieving an increase of up to 27.27% in throughput compared to RR and better fairness indices compared to MR.

Keywords: Escalonador, Inteligência Artificial, Aprendizado por Reforço, Redes Móveis, 5G

References

3GPP. (2020a). Physical channels and modulation (3GPP TS 38.211 Version 16.2.0 Release 16). ETSI. Sophia Antipolis, France.

3GPP. (2020b). Physical layer procedures for data (3GPP TS 38.214 Version 16.2.0 Release 16). ETSI. Sophia Antipolis, France.

Agiwal, M., Roy, A., & Saxena, N. (2016). Next generation 5G wireless networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 18(3), 1617–1655.

Al-Tam, F., Correia, N., & Rodriguez, J. (2020). Learn to schedule: LEASCH: A deep reinforcement learning approach for radio resource scheduling in the 5G MAC layer. IEEE Access, 8, 143063–143076.

Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C., & Zhang, J. C. (2014). What will 5G be? IEEE Journal on Selected Areas in Communications, 32(6), 1065–1082.

Bonati, L., D’Oro, S., Polese, M., Basagni, S., & Melodia, T. (2021). Intelligence and learning in O-RAN for data-driven nextG cellular networks. IEEE Communications Magazine, 59(10), 21–27.

Dahlman, E., Parkvall, S., & Skold, J. (2020). 5G NR: The next generation wireless access technology. Academic Press.

Gu, Z., She, C., Hardjawana, W., Lumb, S., McKechnie, D., Essery, T., & Vucetic, B. (2021). Knowledge-assisted deep reinforcement learning in 5G scheduler design: From theoretical framework to implementation. IEEE Journal on Selected Areas in Communications, 39(7), 2014–2028.

Holma, H., Toskala, A., & Reunanen, J. (2015). LTE small cell optimization: 3GPP evolution to Release 13. Wiley.

Huang, Q., & Kadoch, M. (2020). 5G resource scheduling for low-latency communication: A reinforcement learning approach. In 2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall) (pp. 1–5). IEEE.

Jain, R. K., Chiu, D.-M. W., & Hawe, W. R. (1984). A quantitative measure of fairness and discrimination. Eastern Research Laboratory, Digital Equipment Corporation, Hudson, MA, 21, 1.

Patriciello, N., Lagen, S., Bojovic, B., & Giupponi, L. (2019). An E2E simulator for 5G NR networks. Simulation Modelling Practice and Theory, 96, 101933.

Rodrigues, C. F. F., Lovisolo, L., & da Silva Mello, L. (2022). Alocação de recursos da interface aérea 5G a partir de um critério de utilidade. In Anais do XL Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT 2022).

Saraiva, J. V., Jr., I. M. B., Monteiro, V. F., Lima, F. R. M., Maciel, T. F., Jr., W. C. F., & Cavalcanti, F. R. P. (2020). Deep reinforcement learning for QoS-constrained resource allocation in multiservice networks.

Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.

Vihriala, J., Zaidi, A. A., Venkatasubramanian, V., He, N., Tiirola, E., Medbo, J., Lahetkangas, E., Werner, K., Pajukoski, K., & Cedergren, A. (2016). Numerology and frame structure for 5G radio access. In 2016 IEEE 27th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC) (pp. 1–5).

Yang, L., Jia, J., Lin, H., & Cao, J. (2022). Reliable dynamic service chain scheduling in 5G networks. IEEE Transactions on Mobile Computing, 22(8), 4898–4911.

You, X., Zhang, C., Tan, X., Jin, S., & Wu, H. (2019). AI for 5G: Research directions and paradigms. Science China Information Sciences, 62, 1–13.

Zhang, C., Ueng, Y.-L., Studer, C., & Burg, A. (2020). Artificial intelligence for 5G and beyond 5G: Implementations, algorithms, and optimizations. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 10(2), 149–163.