End-to-end training and adaptive transmission for OFDM-based semantic communication

This paper presents a semantic communication framework for orthogonal frequency division multiplexing (OFDM) systems. In this framework, we first introduce an end-to-end training strategy which leverages binary symmetric channels (BSCs) to model OFDM communication errors, thereby eliminating the need to specify channel distributions, modulation order, and transmission power during end-to-end training. We then propose a joint modulation order and power optimization scheme for OFDM systems designed for our end-to-end training strategy. Our optimization aims to maximize the transmission rate while satisfying target bit-error rate and power constraints. Through simulations, we demonstrate the superiority of our framework compared to existing schemes.