D-RAN: A DRL-Based Demand-Driven Elastic User-Centric RAN Optimization for 6G & Beyond

Abstract

With highly heterogeneous application requirements, 6G and beyond cellular networks are expected to be demand-driven, elastic, user-centric, and capable of supporting multiple services. A redesign of the one-size-fits-all cellular architecture is needed to support heterogeneous application needs. While several recent works have proposed user-centric cloud radio access network (UCRAN) architectures, these works do not consider the heterogeneity of application requirements or the mobility of users. Even though significant gains in performance have been reported, the inherent rigidity of these methods limits their ability to meet the quality of service (QoS) expected from future cellular networks. This paper addresses this need by proposing an intelligent, demand-driven, elastic UCRAN architecture capable of providing services to a diverse set of use cases including augmented/virtual reality, high-speed rails, industrial robots, E-health, and more applications. The proposed framework leverages deep reinforcement learning to adjust the size of a user-centered virtual cell based on each application's heterogeneous requirements. Furthermore, the proposed architecture is adaptable to varying user demands and mobility while performing multi-objective optimization of key network performance indicators (KPIs). Finally, numerical results are presented to validate the convergence, adaptability, and performance of the proposed approach against meta-heuristics and brute-force methods.