Automating User Allocation in 5G Slices in Open RAN Architectures
Abstract
5G mobile networks have enabled new applications with different traffic characteristics. In this scenario, the adaptive allocation of a User Equipment (UE) to a network slice can be complex due to the various types of traffic generated by user applications. To address this challenge, this work proposes a solution called USAP-5G (UE Smart Allocation Platform in 5G Mobile Networks). The solution was developed considering the use of an LSTM (Long Short-Term Memory) machine learning model integrated with an Open RAN and 5G architecture. In tests conducted on the OpenRAN@Brasil testbed, the solution demonstrated effectiveness in reducing decision-making latency and improving the performance of the UE allocation scheme in 5G slices. As a result, the allocation of users in 5G slices was automated, contributing to the reduction of OPEX (Operational Expenditure) in network service management.
References
Afolabi, I., Taleb, T., Samdanis, K., Ksentini, A., & Flinck, H. (2018). Network slicing and softwarization: A survey on principles, enabling technologies, and solutions. IEEE Communications Surveys & Tutorials, 20(3), 2429–2453.
Ajibare, A. T., & Falowo, O. E. (2019). Resource allocation and admission control strategy for 5G networks using slices and users priorities. In 2019 IEEE AFRICON (pp. 1–6).
Alliance, O. (2023). O-RAN Specifications. [link]. [acessado: 30 de outubro de 2023].
Alliance, O.-R. (2025a). O-ran e2 application protocol (e2ap) 6.0. Relatório Técnico O-RAN.WG3.E2AP-R004-v06.00, O-RAN Alliance. Acessado em 13 de janeiro de 2025.
Alliance, O.-R. (2025b). O-ran e2 service model (e2sm) 6.0. Relatório Técnico O-RAN.WG3.E2SM-R004-v06.00, O-RAN Alliance. Acessado em 13 de janeiro de 2025.
Alliance, O.-R. (2025c). O-ran e2 service model (e2sm) kpm 5.0. Relatório Técnico O-RAN.WG3.E2SM-KPM-R003-v05.00, O-RAN Alliance. Acessado em 13 de janeiro de 2025.
Donatti, A., Correa, S. L., Martins, J. S. B., Abelem, A., Both, C. B., Silva, F., Suruagy, J. A., Pasquini, R., Moreira, R., Cardoso, K. V., & Carvalho, T. C. (2023). Survey on machine learning-enabled network slicing: Covering the entire life cycle. IEEE Transactions on Network and Service Management, 1–1.
Filali, A., Nour, B., Cherkaoui, S., & Kobbane, A. (2023). Communication and computation O-RAN resource slicing for URLLC services using deep reinforcement learning. IEEE Communications Standards Magazine, 7(1), 66–73.
Gorla, P., Chamola, V., Hassija, V., & Niyato, D. (2021). Network slicing for 5G with user equipment state-based allocation and blockchain approach. IEEE Network, 35(3), 184–190.
Labs, R. (2022). Quality of Service-based Resource Allocator xApp (QRAxApp). [link].
Li, L., Jamieson, K. G., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2016). Efficient hyperparameter optimization and infinitely many armed bandits. CoRR, abs/1603.06560.
Marinova, S., & Leon-Garcia, A. (2024). Intelligent O-RAN beyond 5G: Architecture, use cases, challenges, and opportunities. IEEE Access, 12, 27088–27114.
Mauricio, W., Costa Neto, F. H., Silva, M., Aoki, R. K. Y., Melao, E., Barros, S., Farias, F., Bondan, L., & Abinader, F. M. (2025). Assessing nationwide distributed Open RAN deployments with the OpenRAN@Brasil testbed. IEEE Communications Magazine, 63(2), 46–52.
Open5GS. (2025). Open source implementation for 5G Core and EPC, i.e., the core network of LTE/NR network (Release-17).
OSC (2025). About O-RAN Software Community (SC). O-RAN Alliance. Disponível no site oficial da O-RAN Alliance.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., & Melodia, T. (2022a). Colo-RAN: Developing machine learning-based xApps for Open RAN closed-loop control on programmable experimental platforms.
Polese, M., Bonati, L., D’Oro, S., Basagni, S., & Melodia, T. (2022b). Understanding O-RAN: Architecture, interfaces, algorithms, security, and research challenges.
RNP et al. (2025). OpenRAN@Brasil. [link].
SRS. (2025). Open-source and O-RAN-native 5G CU/DU with a complete stack from I/Q to IP from SRS.
