A DRL-Based Joint Scheduling and Resource Allocation Scheme for Mixed Unicast–Broadcast Transmission in 5G

With the ever-increasing demand for data services, the spectrum becomes precious resource. The cooperative transmission mechanism, which allows broadcast and unicast to share the same spectrum, can effectively alleviate this situation. The success of LDM in ATSC 3.0 has inspired many scholars to superimpose broadcast and unicast services with a fixed power injection ratio. To further improve radio resource utilization, A flexible LDM scheme with a variable power injection ratio is proposed. The scheduling policy in Medium Access Control layer is formulated as a sequential decision problem, and it proved to have Markov property. A DRL-based algorithm is proposed to obtain the optimal scheduling scheme. Considering the requirements of broadcasting service and unicast services, the Lyapunov optimization method is used to convert the problem to the Lyapunov penalty form that is more conducive for the agent to learn the optimal strategy. Simulation results show that the proposed scheme can achieve much improved performance in system throughput when guaranteeing the quality of the broadcast service.