Q-learning based Resource Allocation for hybrid Services with Self-similar Traffic

This paper investigates the resource allocation of 5G Centralized Radio Access Network (C-RAN) for hybrid services including enhanced mobile broadband (eMBB) and ultrareliable and low latency communications (URLLC) services, when the queueing delay in the base station (BS) is considered. In 5G C-RAN, considering the self-similar characteristics of eMBB user equipment (UE) traffic, we propose a dynamic network resource allocation framework based on q-learning. The results show that compared with traditional model, proposed method has better performance of latency Quality of Service (Qos) and energy consumption ratio.