Resource Management Algorithm for Slicing Function in 5G Network Slicing

Abstract

In the case that multiple service types of slices are jointly carried on core network, a Resource Management Algorithms Oriented to Slicing Functions (RMOSF) is proposed for the processing efficiency of slice requests and the resource allocation of the substrate network. First, the incoming slice requests are input into the admission control module, and the pre-accepted slice requests are screened out through the deep reinforcement learning algorithm; secondly, the pre-accepted slice requests are brought into the resource allocation module, and slices with different type are brought into the corresponding constrained optimization problems for solution; finally, when the substrate physical network resources are sufficient, the slices are mapped to start their life cycle. The simulation results show that the algorithm effectively improves slice profit and request acceptance rate, and also improves resource utilization.