End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels
This addresses the challenge of deploying NOMA in fading environments with practical CSI constraints, representing an incremental improvement over prior works that assumed simpler channels or lacked full end-to-end learning.
The paper tackled the problem of designing downlink non-orthogonal multiple access (NOMA) for Rayleigh fading channels by developing an end-to-end autoencoder framework that learns interference-aware super-constellations, showing it outperforms existing analytical NOMA schemes with perfect CSI and that Lloyd-Max quantization achieves superior bit error rate performance compared to uniform quantization.
An end-to-end autoencoder (AE) framework is developed for downlink non-orthogonal multiple access (NOMA) over Rayleigh fading channels, which learns interference-aware and channel-adaptive super-constellations. While existing works either assume additive white Gaussian noise channels or treat fading channels without a fully end-to-end learning approach, our framework directly embeds the wireless channel into both training and inference. To account for practical channel state information (CSI), we further incorporate limited feedback via both uniform and Lloyd-Max quantization of channel gains and analyze their impact on AE training and bit error rate (BER) performance. Simulation results show that, with perfect CSI, the proposed AE outperforms the existing analytical NOMA schemes. In addition, Lloyd-Max quantization achieves superior BER performance compared to uniform quantization. These results demonstrate that end-to-end AEs trained directly over Rayleigh fading can effectively learn robust, interference-aware signaling strategies, paving the way for NOMA deployment in fading environments with realistic CSI constraints.