In this paper, we adapt and analyze Neural Polar Decoders (NPDs) for end-to-end communication systems. While prior work demonstrated the effectiveness of NPDs on synthetic channels, this study extends the NPD to real-world communication systems. The NPD was adapted to complete OFDM and single-carrier communication systems. To satisfy practical system requirements, the NPD is extended to support any code length via rate matching, higher-order modulations, and robustness across diverse channel conditions. The NPD operates directly on channels with memory, exploiting their structure to achieve higher data rates without requiring pilots and a cyclic prefix. Although NPD entails higher computational complexity than the standard 5G polar decoder, its neural network architecture enables an efficient representation of channel statistics, resulting in manageable complexity suitable for practical systems. Experimental results over 5G channels demonstrate that the NPD consistently outperforms the 5G polar decoder in terms of BER, BLER, and throughput. These improvements are particularly significant for low-rate and short-block configurations, which are prevalent in 5G control channels. Furthermore, NPDs applied to single-carrier systems offer performance comparable to OFDM with lower PAPR, enabling effective single-carrier transmission over 5G channels. These results position the NPD as a high-performance, pilotless, and robust decoding solution.

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.