Cognitive Radio-Oriented Wireless Networks. 14th EAI International Conference, CrownCom 2019, Poznan, Poland, June 11–12, 2019, Proceedings

Research Article

Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent

  • @INPROCEEDINGS{10.1007/978-3-030-25748-4_2,
        author={Pedro Batista and Shah Khan and Peter \O{}hl\^{e}n and Aldebaro Klautau},
        title={Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent},
        proceedings={Cognitive Radio-Oriented Wireless Networks. 14th EAI International Conference, CrownCom 2019, Poznan, Poland, June 11--12, 2019, Proceedings},
        proceedings_a={CROWNCOM},
        year={2019},
        month={8},
        keywords={Network slicing Reinforcement learning Resource management},
        doi={10.1007/978-3-030-25748-4_2}
    }
    
  • Pedro Batista
    Shah Khan
    Peter Öhlén
    Aldebaro Klautau
    Year: 2019
    Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent
    CROWNCOM
    Springer
    DOI: 10.1007/978-3-030-25748-4_2
Pedro Batista,*, Shah Khan1,*, Peter Öhlén1,*, Aldebaro Klautau2,*
  • 1: Ericsson Research
  • 2: Federal University of Pará
*Contact email: pedro.batista@ericsson.com, shah.khan@ericsson.com, peter.ohlen@ericsson.com, aldebaro@ufpa.br

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.