Throughput Maximization for RSMA-Empowered CRN under Short-Packet Communications: A DRL-Based Approach

This paper investigates the problem of spectral efficiency maximization in an underlay cognitive radio network (CRN) utilizing rate-splitting multiple access (RSMA) transmission for MISO downlink under short packet communications and imperfect channel estimation information. In particular, we focus on an effective transmit beamforming design at the cognitive base station while satisfying the requirements of ultra-reliable and low-latency communication (URLLC), interference temperature, power budget, and minimum throughput. We model the dynamic resource allocation problem as a Markov decision process (MDP) and employ deep reinforcement learning techniques, specifically the deep deterministic policy gradient (DDPG) and proximal policy optimization (PPO) algorithms, while taking into account the time-varying channel conditions. Simulation results demonstrate that the DDPG algorithm outperforms PPO at low interference temperatures for the primary receiver, while the opposite holds at high interference temperatures. Moreover, the considered RSMA system for CRN outperforms traditional multi-user linear precoding and power-domain multiple access schemes while maintaining small packet sizes and high reliability.

I. Introduction

Cognitive radio networks (CRNs) are an innovative solution to address the spectrum scarcity problem by accessing li-censed frequency bands opportunistically [1], [2]. Specifically, CRNs can improve spectral efficiency and optimize resource utilization without affecting the quality of service of the primary network. Nevertheless, ultra-reliable and low-latency communication (URLLC) remains a critical application in future wireless networks where massive throughput demands must be met while maintaining low latency under limited spectrum resources. To ensure reliable and spectral-efficient short-packet communication, cognitive radio networks (CRNs) can play a vital part in meeting these demands [3]. Another frontier technology, rate-splitting multiple access (RSMA), has recently gained significant attention due to its efficient spectrum utilization and effective power control [3]–[5]. Un-like non-orthogonal multiple access (NOMA) and multi-user linear precoding, i.e., space-division multiple access (SDMA), RSMA enables partial interference decoding and treats the partial interference as noise which exploits all the available degrees of freedom in power control and smart interference management for providing a better spectral efficiency (SE) to the multiple users [4]. Consequently, the RSMA and CRNs techniques are prominent candidates for enabling URLLC in sixth-generation (6G) networks to captivate spectral-limited and high data rate requirements. Moreover, their effective consolidation can bring new opportunities to enhance both the QoS and SE performance [3], [4].