Inter-Slice Radio Resource Management via Online Convex Optimization

Radio access network (RAN) slicing is one of the key technologies in 5G and beyond mobile networks, where multiple logical RANs, also referred to as RAN slices, are allowed to run on top of the same physical infrastructure so as to provide slice-specific services. Due to the dynamic environments of wireless cells and the diverse requirements of RAN slices, inter-slice radio resource management (IS-RRM) is a highly challenging task. In this paper, we propose a novel online convex optimization (OCO) framework for the IS-RRM, where the instant resource allocation is learned by using historical data revealed from previous allocations. Compared with the existing methods, OCO is an online optimization process that can avoid sophisticated modeling and tuning in highly complicated and dynamic environments. Specifically, a low-complexity online ISRRM algorithm is proposed, which employs multiple expert-algorithms running parallelly to keep track of environmental changes. Simulation results show that the proposed method can provide efficient IS-RRM with a comparable performance to the optimal strategies in hindsight.