Abstract
5G networks will provide the platform for deploying large number of tenant-associated management, control and end-user applications having different resource requirements at the infrastructure level. In this context, the 5G infrastructure provider must optimize the infrastructure resource utilization and increase its revenue by intelligently admitting network slices that bring the most revenue to the system. In addition, it must ensure that resources can be scaled dynamically for the deployed slices when there is a demand for them from the deployed slices. In this paper, we present a neural networks-driven policy agent for network slice admission that learns the characteristics of the slices deployed by the network tenants from their resource requirements profile and balances the costs and benefits of slice admission against resource management and orchestration costs. The policy agent learns to admit the most profitable slices in the network while ensuring their resource demands can be scaled elastically. We present the system model, the policy agent architecture and results from simulation study showing an increased revenue for infra-structure provider compared to other relevant slice admission strategies.
Keywords
This work has received funding from the H2020-MSCA-ITN-2016 SPOTLIGHT project under grant number 722788.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
AT&T, BT, CenturyLink, Mobile, C., Colt, Telekom, D., KDDI, NTT, Orange, Italia, T., Telefonica, Telstra, Verizon: Network Functions Virtualisation. An Introduction, Benefits, Enablers, Challenges & Call for Action. Technical report, SDN and OpenFlow World Congress, October 2012. https://portal.etsi.org/nfv/nfv_white_paper.pdf
Bega, D., Gramaglia, M., Banchs, A., Sciancalepore, V., Samdanis, K., Costa-Perez, X.: Optimising 5G infrastructure markets: the business of network slicing. In: IEEE Conference on Computer Communications, IEEE INFOCOM 2017, pp. 1–9, May 2017. https://doi.org/10.1109/INFOCOM.2017.8057045
Caballero, P., Banchs, A., de Veciana, G., Costa-Perez, X., Azcorra, A.: Network slicing for guaranteed rate services: admission control and resource allocation games. IEEE Trans. Wirel. Commun. 17(10), 6419–6432 (2018). https://doi.org/10.1109/TWC.2018.2859918
Dahmen-Lhuissier, S.: Open Source MANO, December 2018. https://www.etsi.org/technologies-clusters/technologies/nfv/open-source-mano
Gomes, P., Vidal, A., Lins, S.: Next stop: zero-touch automation standardization, November 2018. https://www.ericsson.com/research-blog/next-stop-zero-touch-automation-standardization/
Han, B., Feng, D., Schotten, H.D.: A Markov model of slice admission control. IEEE Netw. Lett. 1 (2018). https://doi.org/10.1109/LNET.2018.2873978
Mao, H., Alizadeh, M., Menache, I., Kandula, S.: Resource management with deep reinforcement learning, pp. 50–56. ACM Press (2016). https://doi.org/10.1145/3005745.3005750
Oliva, A., et al.: 5G-TRANSFORMER: slicing and orchestrating transport networks for industry verticals. IEEE Comm. Mag. 56(8), 78–84 (2018). https://doi.org/10.1109/MCOM.2018.1700990
ONAP: ONAP Architecture Overview. Technical report, December 2018. https://www.onap.org/wp-content/uploads/sites/20/2018/06/ONAP_CaseSolution_Architecture_0618FNL.pdf
Raza, M.R., Natalino, C., Öhlen, P., Wosinska, L., Monti, P.: A slice admission policy based on reinforcement learning for a 5G flexible RAN. In: 2018 European Conference on Optical Communication (ECOC), pp. 1–3, September 2018. https://doi.org/10.1109/ECOC.2018.8535483
Raza, M.R., Rostami, A., Vidal, A., Santos, M.A.S., Wosinska, L., Monti, P.: Priority-aware service orchestration using big data analytics for dynamic slicing in 5G transport networks. In: 2017 European Conference on Optical Communication (ECOC), pp. 1–3, September 2017. https://doi.org/10.1109/ECOC.2017.8346133
Raza, M.R., Rostami, A., Wosinska, L., Monti, P.: Resource orchestration meets big data analytics: the dynamic slicing use case. In: 2018 European Conference on Optical Communication (ECOC), pp. 1–3. IEEE, Rome, September 2018. https://doi.org/10.1109/ECOC.2018.8535581
Samdanis, K., Costa-Perez, X., Sciancalepore, V.: From network sharing to multi-tenancy: the 5G network slice broker. IEEE Commun. Mag. 54(7), 32–39 (2016). https://doi.org/10.1109/MCOM.2016.7514161
Sciancalepore, V., Samdanis, K., Costa-Perez, X., Bega, D., Gramaglia, M., Banchs, A.: Mobile traffic forecasting for maximizing 5G network slicing resource utilization. In: IEEE Conference on Computer Communications, IEEE INFOCOM 2017, pp. 1–9, May 2017. https://doi.org/10.1109/INFOCOM.2017.8057230
Zheng, J., Caballero, P., de Veciana, G., Baek, S.J., Banchs, A.: Statistical multiplexing and traffic shaping games for network slicing. In: IEEE/ACM Transactions on Networking, pp. 1–14 (2018). https://doi.org/10.1109/TNET.2018.2870184
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Batista, P., Khan, S.N., Öhlén, P., Klautau, A. (2019). Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent. In: Kliks, A., et al. Cognitive Radio-Oriented Wireless Networks. CrownCom 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 291. Springer, Cham. https://doi.org/10.1007/978-3-030-25748-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-25748-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-25747-7
Online ISBN: 978-3-030-25748-4
eBook Packages: Computer ScienceComputer Science (R0)