Dnn improves uplink scma codebooks for rician fading channels
DNN-Assisted Near-Optimal Codebook Design for Uplink SCMA Schemes over Rician Fading Channels
Information Theory
Summary
Modern communication systems need to connect many devices efficiently, and SCMA is one method for this. The authors use a deep neural network to design better codes that help signals be understood clearly even when the wireless channel is tricky, like in Rician fading environments. Their method does not require example answers to learn from, making it flexible. Tests show their design outperforms earlier methods, especially in very reliable communication settings.
What this means in practice
- •For telecom engineers: Design uplink SCMA systems that maintain low error rates across a variety of Rician fading conditions for future cellular networks.
- •For wireless device manufacturers: Produce devices that communicate reliably in wireless conditions prone to line-of-sight and multipath fading by using improved codebooks from the DNN framework.
Authors
Wasif Ali, Yen-Ming Chen, Fan-Shuo Tseng
Abstract
Sparse Code Multiple Access (SCMA) is a promising non-orthogonal multiplexing technique for enhancing connectivity and spectral efficiency in next-generation communication networks. This paper proposes near-optimal uplink SCMA codebook designs based on a novel deep neural network (DNN)-assisted framework. The DNN is trained in an unsupervised manner, with a loss function derived from the structural characteristics of the generated codebooks, thereby eliminating the need for labeled training data. Based on error-probability analysis, Rician-factor-dependent design criteria are derived for uplink Rician fading and used to formulate the loss function. The resulting criteria naturally encompass AWGN and Rayleigh fading as limiting cases, providing a unified framework for codebook design. Moreover, upper and lower bounds on the average mutual information (AMI) are derived, providing an information-theoretic interpretation of the PEP-based criterion and establishing its asymptotic consistency with the AMI-lower-bound-based criterion in the high-SNR regime. The analysis further reveals how the dominant design factors evolve as the channel transitions from Rayleigh fading to AWGN. Numerical results show that the proposed near-optimal codebooks achieve significant performance gains over representative benchmark schemes across a wide range of Rician factors and exhibit excellent error-rate performance in the error-floor region, making them particularly attractive for ultra-reliable applications.