TY - JOUR
T1 - Deep Learning-Based Codebook Design for Code-Domain Non-Orthogonal Multiple Access
T2 - Approaching Single-User Bit-Error Rate Performance
AU - Han, Minsig
AU - Seo, Hanchang
AU - Abebe, Ameha Tsegaye
AU - Kang, Chung G.
N1 - Funding Information:
This work was supported in part by Samsung Research, Samsung Electronics, and in part by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No.2020R1A2C100998412).
Publisher Copyright:
© 2015 IEEE.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - A general form of codebook design for code-domain non-orthogonal multiple access (CD-NOMA) can be considered equivalent to an autoencoder (AE)-based constellation design for multi-user multidimensional modulation (MU-MDM). Due to a constrained design space for optimal constellation, e.g., fixed resource mapping and equal power allocation to all codebooks, however, existing AE architectures produce constellations with suboptimal bit-error-rate (BER) performance. Accordingly, we propose a new architecture for MU-MDM AE and underlying training methodology for joint optimization of resource mapping and a constellation design with bit-to-symbol mapping, aiming at approaching the BER performance of a single-user MDM (SU-MDM) AE model with the same spectral efficiency. The core design of the proposed AE architecture is dense resource mapping combined with the novel power allocation layer that normalizes the sum of user codebook power across the entire resources. This globalizes the domain of the constellation design by enabling flexible resource mapping and power allocation. Furthermore, it allows the AE-based training to approach a global optimal MU-MDM constellations for CD-NOMA. Extensive BER simulation results demonstrate that the proposed design outperforms the existing CD-NOMA designs while approaching the single-user BER performance achieved by the equivalent SU-MDM AE within 0.3dB over the additive white Gaussian noise channel.
AB - A general form of codebook design for code-domain non-orthogonal multiple access (CD-NOMA) can be considered equivalent to an autoencoder (AE)-based constellation design for multi-user multidimensional modulation (MU-MDM). Due to a constrained design space for optimal constellation, e.g., fixed resource mapping and equal power allocation to all codebooks, however, existing AE architectures produce constellations with suboptimal bit-error-rate (BER) performance. Accordingly, we propose a new architecture for MU-MDM AE and underlying training methodology for joint optimization of resource mapping and a constellation design with bit-to-symbol mapping, aiming at approaching the BER performance of a single-user MDM (SU-MDM) AE model with the same spectral efficiency. The core design of the proposed AE architecture is dense resource mapping combined with the novel power allocation layer that normalizes the sum of user codebook power across the entire resources. This globalizes the domain of the constellation design by enabling flexible resource mapping and power allocation. Furthermore, it allows the AE-based training to approach a global optimal MU-MDM constellations for CD-NOMA. Extensive BER simulation results demonstrate that the proposed design outperforms the existing CD-NOMA designs while approaching the single-user BER performance achieved by the equivalent SU-MDM AE within 0.3dB over the additive white Gaussian noise channel.
KW - Autoencoder (AE)
KW - Codebook (CB) design
KW - Deep learning (DL)
KW - Multi-dimension modulation (MDM)
KW - Multi-user communication
KW - Non-orthogonal multiple access (NOMA)
UR - http://www.scopus.com/inward/record.url?scp=85120042887&partnerID=8YFLogxK
U2 - 10.1109/TCCN.2021.3130308
DO - 10.1109/TCCN.2021.3130308
M3 - Article
AN - SCOPUS:85120042887
VL - 8
SP - 1159
EP - 1173
JO - IEEE Transactions on Cognitive Communications and Networking
JF - IEEE Transactions on Cognitive Communications and Networking
SN - 2332-7731
IS - 2
ER -