Markov Decision Process to Achieve Near-Optimal Admission Control Mechanism for 5G Cloud Radio Networks

Markov Decision Process to Achieve Near-Optimal Admission Control Mechanism for 5G Cloud Radio Networks

Fifth-generation radio access networks have been proposed as a cloud architecture to provide a common connected resource pool management. In this regard, efficiently and effectively managing radio resources and allocating perspectives on the rapidly changing traffic load is a challenge. Admission control mechanism is a key factor influencing the system performance with limited resource pools and call-blocking probability constraints. In this paper, a precise mathematical programming model of centralized management is formulated for the resource scheduling problem. Operators can manage resources according to the algorithms designed by Markov decision process (MDP) and Lagrangian relaxation (LR) method for various traffic types. They can create different business levels for resource priorities. The system revenue enhanced under call-blocking constraints and quality of service constraints. The management mechanism is flexible and scalable for pursuing the required objectives.