MPP-RAN: Posicionamento de funções de rede virtualizadas em redes de acesso de nova geração com divisão de fluxos
Abstract
Next Generation Radio Access Networks (NG-RAN) shall support eight functional splits combining placement into three nodes, i.e., Central Unit, Distributed Unit and Radio Unit. Furthermore, these nodes must work virtualized, resulting in a vNG-RAN solution. In this paper, an exact optimization model is proposed that aims to position VNFs for the planning of vNG-RAN with the possibility of splitting the routing flow into multiple paths. However, our tests show that this approach is complex for full-size vNG-RANs. Thus, we present a discussion of using deep reinforcement learning to solve this problem.References
3GPP (2017). Study on New Radio Access Technology; Radio Access Architecture and Interfaces (Release 14). Technical Recommendation (TR) 38.801, 3rd Generation Partnership Project (3GPP).
3GPP (2018). System Architecture for the 5G (Release 15). Technical Recommendation 23.501.
ITU-T, G.-T. (2018). Transport network support of IMT-2020/5G.
Marsch, P. et al. (2018). 5G system design: architectural and functional considerations and long term research. John Wiley & Sons.
Moerland, T. M., Broekens, J., and Jonker, C. M. (2020). Model-based reinforcement learning: A survey. arXiv preprint arXiv:2006.16712.
Morais, F. Z. et al. (2021). PlaceRAN: Optimal Placement for the Virtualized NextGeneration RAN. CoRR, abs/2102.13192.
Murti, F. W., Ali, S., and Latva-aho, M. (2021). Deep reinforcement based optimization of function splitting in virtualized radio access networks. arXiv preprint arXiv:2105.14731.
Murti, F. W. et al. (2020). On the optimization of multi-cloud virtualized radio access In ICC 2020 2020 IEEE International Conference on Communications networks. (ICC), pages 1–7.
3GPP (2018). System Architecture for the 5G (Release 15). Technical Recommendation 23.501.
ITU-T, G.-T. (2018). Transport network support of IMT-2020/5G.
Marsch, P. et al. (2018). 5G system design: architectural and functional considerations and long term research. John Wiley & Sons.
Moerland, T. M., Broekens, J., and Jonker, C. M. (2020). Model-based reinforcement learning: A survey. arXiv preprint arXiv:2006.16712.
Morais, F. Z. et al. (2021). PlaceRAN: Optimal Placement for the Virtualized NextGeneration RAN. CoRR, abs/2102.13192.
Murti, F. W., Ali, S., and Latva-aho, M. (2021). Deep reinforcement based optimization of function splitting in virtualized radio access networks. arXiv preprint arXiv:2105.14731.
Murti, F. W. et al. (2020). On the optimization of multi-cloud virtualized radio access In ICC 2020 2020 IEEE International Conference on Communications networks. (ICC), pages 1–7.
Published
2021-08-16
How to Cite
ALMEIDA, Gabriel M. F. de; LOPES, Victor Hugo L.; BOTH, Cristiano B.; CORRÊA, Sand; KLAUTAU, Aldebaro; CARDOSO, Kleber V..
MPP-RAN: Posicionamento de funções de rede virtualizadas em redes de acesso de nova geração com divisão de fluxos. In: WORKSHOP DE REDES 6G (W6G), 1. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 7-12.
DOI: https://doi.org/10.5753/w6g.2021.17228.
