Resource Allocation for FeMBB and eURLLC Coexistence in RSMA-Based Cellular Networks

This paper studies the Joint Resource block (RB) allocation and Power control (JRP) problem for the coexistence of further enhanced mobile broadband (FeMBB) and extreme ultra-reliable low latency (eURLLC) services in rate splitting multiple access-based next-generation (e.g., 5G-Advanced and 6G) wireless networks. In the JRP problem, for each FeMBB user, a minimum data rate requirement is considered, and eURLLC users should meet their latency and reliability requirements. To address the JRP problem, we propose a hybrid deep reinforcement learning (HDRL-JRP) algorithm, in which a double dueling deep Q-network is employed for RB allocation and a deep deterministic policy gradient is used for power control. Via simulation results, the performance of the HDRL-JRP algorithm is demonstrated in terms of total data rate.