A deep reinforcement learning based 5G-RAN slicing strategy for V2X services

초록

Vehicular communication is a key technology in intelligent transportation systems which links vehicles, roadside units, and pedestrians. One of the key factor for providing design flexibility is Slicing of the Radio Access Network (RAN) which enables 5G systems to support heterogeneous services on one platform through a custom slice for each service. In this regard, this paper provides an overview of an RAN slicing strategy based on Deep Reinforcement Learning (DRL) for a heterogeneous network with two generic 5G services, such as enhanced mobile broadband (eMBB) and vehicle-to-everything (V2X).