Intelligent Resource Allocation for UAV-Enabled Spectrum Sharing Semantic Communication Networks

Abstract

Spectrum sharing technology has been widely used for better spectrum efficiency. However, the interference issue between the primary and secondary networks poses a significant concern. Semantic communication, being a pivotal technology for the sixth-generation (6G) wireless communication, exhibits remarkable interference robustness even under conditions of low signal-to-noise ratio (SNR). In this paper, intelligent resource allocation for unmanned aerial vehicle (UAV)-enabled spectrum sharing semantic communication networks with OFDM is investigated, where UAVs provide task-oriented semantic services to secondary users (SUs) in the non-line-of-sight range of the base station. To maximize the semantic spectrum efficiency (S-SE) of the secondary network, the subchannel assignment, the semantic symbols assignment, the transmit beamforming of the UAV and the trajectory of the UAV are jointly optimized. To construct a forward-looking intelligent communication network, a novel resource allocation algorithm using DDQN-DDPG approach is proposed to effectively address intricate non-convex optimization problems. Simulation results show that our proposed scheme outperforms the benchmark schemes in terms of S-SE, and our proposed intelligent resource allocation algorithm exhibits impeccable convergence behavior.