Deep-Learning-Based Waveform Design for Single-Carrier Satellite Communication Networks

This study introduces an innovative deep-learning-based waveform design approach for single-carrier (SC) satellite communication systems. Neural network (NN) models are used for comprehensive optimization to mitigate the nonlinearities introduced by high-power amplifiers (HPAs). We propose two distinct NN architectures: a convolutional autoencoder (CAE) for end-to-end joint optimization and a mutual information neural estimation (MINE)-based architecture designed to optimize the transmitter and receiver components independently. Both models simultaneously enhance spectral purity by improving the adjacent channel power ratio (ACPR), reducing the peak-to-average power ratio (PAPR), and optimizing the bit error rate (BER). A key feature of our approach is its ability to generalize across diverse HPA models, enabling quick and effective adaptation to previously unseen amplifiers through minimal retraining. Additionally, our use of gradual loss learning allows for the effective balancing of multiple optimization objectives across various signal-to-noise ratio (SNR) scenarios. Rigorous evaluations using realistic satellite terminal block upconverter (BUC) HPA models, demonstrate the robustness and adaptability of the proposed NN solutions. A comparative analysis against conventional PAPR reduction and digital predistortion techniques confirms that our NN-based approaches deliver superior performance, addressing contemporary satellite communication demands, particularly in high-order QAM applications requiring stringent spectral constraints.