OFDM-Based NOMA-Enhanced Coexistence of SemCom and BitCom System

To facilitate the popularization and application of semantic communication, it is crucial to ensure its efficient coexistence with traditional digital communication networks. In this paper, we investigate a non-orthogonal multiple access (NOMA)-enabled heterogeneous semantic communication (SemCom) and bit communication (BitCom) coexistence system under an orthogonal frequency division multiplexing (OFDM) framework. The deployment of fluid antennas at the user side is treated as a crucial strategy to enhance system efficiency and mitigate interference. Within the above OFDM framework, we construct a frequency domain channel with multicarriers, based on the multipath channel characteristics exhibited by different fluid antenna ports. Subsequently, a sum semantic rate maximization problem is formulated by optimizing the subcarrier allocation, power allocation, and the fluid antenna port selection of the users. Note that the derived problem is challenging to solve through conventional methods due to the presence of highly coupled continuous and discrete variables. To address this challenge, we propose a dual proximal policy optimization (DPPO) algorithm as a solution for this problem, which divides the problem into two parts and leverages separate subnetworks to solve each part. Simulation results demonstrate the efficiency of the proposed algorithms in enhancing the sum semantic rate.