A Novel Approach for Dynamic Capacity Sharing in Multi-tenant Scenarios

Network slicing is included as a key feature of the 5G architecture in order to simultaneously support diverse service types with heterogeneous requirements. The deployment of network slicing in the Radio Access Network (RAN) needs mechanisms that allow the distribution of the available capacity in the system in an efficient manner while satisfying the requirements of the different services. In this paper, a capacity sharing function is proposed, which is approached as a multi-agent reinforcement learning based on the Deep Reinforcement Learning (DRL) algorithm Deep Q-Network (DQN). The proposed algorithm provides the capacity to be assigned to each RAN slice. Performance assessment reveals the promising behaviour of the proposed solution.

[1]  Wei Jiang,et al.  Autonomous Resource Provisioning and Resource Customization for Mixed Traffics in Virtualized Radio Access Network , 2019, IEEE Systems Journal.

[2]  Albert Banchs,et al.  Mobile network architecture evolution toward 5G , 2016, IEEE Communications Magazine.

[3]  Dusit Niyato,et al.  Deep Reinforcement Learning for Mobile 5G and Beyond: Fundamentals, Applications, and Challenges , 2019, IEEE Vehicular Technology Magazine.

[4]  Chen Qi,et al.  Deep Reinforcement Learning With Discrete Normalized Advantage Functions for Resource Management in Network Slicing , 2019, IEEE Communications Letters.

[5]  Oriol Sallent,et al.  Profit-Based Radio Access Network Slicing for Multi-tenant 5G Networks , 2019, 2019 European Conference on Networks and Communications (EuCNC).

[6]  Marc Peter Deisenroth,et al.  Deep Reinforcement Learning: A Brief Survey , 2017, IEEE Signal Processing Magazine.

[7]  Romano Fantacci,et al.  Highly Flexible RAN Slicing Approach to Manage Isolation, Priority, Efficiency , 2019, IEEE Access.

[8]  Nguyen H. Tran,et al.  Slicing the Edge: Resource Allocation for RAN Network Slicing , 2018, IEEE Wireless Communications Letters.

[9]  Antonio Capone,et al.  Dynamic Resource Trading in Sliced Mobile Networks , 2019, IEEE Transactions on Network and Service Management.

[10]  Oriol Sallent,et al.  On 5G Radio Access Network Slicing: Radio Interface Protocol Features and Configuration , 2018, IEEE Communications Magazine.

[11]  Xianfu Chen,et al.  Deep Reinforcement Learning for Resource Management in Network Slicing , 2018, IEEE Access.

[12]  Wei Jiang,et al.  Dynamic Reservation and Deep Reinforcement Learning Based Autonomous Resource Slicing for Virtualized Radio Access Networks , 2019, IEEE Access.

[13]  Hui Tian,et al.  Hierarchical Auction and Dynamic Programming Based Resource Allocation (HA&DP-RA) Algorithm for 5G RAN Slicing , 2018, 2018 24th Asia-Pacific Conference on Communications (APCC).

[14]  Vincenzo Sciancalepore,et al.  From network sharing to multi-tenancy: The 5G network slice broker , 2016, IEEE Communications Magazine.

[15]  Vasilis Friderikos,et al.  Optimal resource sharing in multi-tenant 5G networks , 2018, 2018 IEEE Wireless Communications and Networking Conference (WCNC).

[16]  Oriol Sallent,et al.  Self-optimized admission control for multitenant radio access networks , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[17]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[18]  Gyu Myoung Lee,et al.  An Efficient Resource Management Mechanism for Network Slicing in a LTE Network , 2019, IEEE Access.

[19]  Albert Banchs,et al.  Network Slicing Games: Enabling Customization in Multi-Tenant Mobile Networks , 2019, IEEE/ACM Transactions on Networking.