Robust SCMA Codebook Design: A Hardware-Aware Autoencoder Approach

2026-06-21

AI Summary

This work addresses the severe degradation in bit error rate performance caused by carrier frequency offset (CFO) and phase noise (PN) in OFDM-SCMA systems, which disrupt subcarrier orthogonality. The paper proposes a hardware-aware end-to-end autoencoder architecture that, for the first time, integrates a differentiable CFO model and a Wiener-process-based phase noise layer directly into the training process. By jointly optimizing codebook design with explicit modeling of these hardware impairments, the approach enhances robustness without requiring real-time phase tracking. The resulting codebooks effectively suppress the error floor induced by CFO and PN, achieving significant performance gains in high-impairment scenarios.

Abstract

Sparse code multiple access (SCMA) is a promising code-domain non-orthogonal multiple access scheme which is transmitted over orthogonal frequency division multiplexing (OFDM) to exploit multicarrier diversity. In practice, however, carrier frequency offset (CFO) and phase noise (PN) may disrupt the subcarrier orthogonality in OFDM-SCMA systems. Addressing this research problem from a new SCMA codebook design angle, we propose a hardware-aware end-to-end autoencoder that embeds differentiable CFO and Wiener PN layers into the training loop. Simulations show that the proposed codebook effectively suppresses the bit error floors caused by CFO and PN without requiring real-time phase tracking.

Problem

• SCMA
• carrier frequency offset
• phase noise
• OFDM
• codebook design

Innovation

• hardware-aware autoencoder
• SCMA codebook design
• carrier frequency offset
• phase noise
• differentiable channel layers