Interference-Aware Super-Constellation Design for NOMA

2025-03-10

AI Summary

To address symbol ambiguity and degraded successive interference cancellation (SIC) performance in non-orthogonal multiple access (NOMA) systems under finite-input constellations—caused by inter-user interference—this paper proposes an autoencoder-based, interference-aware hyper-constellation design. The method jointly optimizes transmit constellation design and channel adaptation in an end-to-end manner, eliminating reliance on conventional SIC architectures and enabling maximum-likelihood detection. Notably, it is the first work to employ autoencoders for channel-agnostic hyper-constellation synthesis, leveraging a customized loss function and channel-adaptive training to ensure symbol-level distinguishability. Experimental results demonstrate substantial bit-error-rate (BER) reduction and strong robustness across diverse fading channels—including Rayleigh, Rician, and Nakagami-m—while exhibiting superior generalization to unseen channel conditions. This approach establishes a practical, SIC-free NOMA paradigm grounded in learned physical-layer signaling.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Non-orthogonal multiple access (NOMA) has gained significant attention as a potential next-generation multiple access technique. However, its implementation with finite-alphabet inputs faces challenges. Particularly, due to inter-user interference, superimposed constellations may have overlapping symbols leading to high bit error rates when successive interference cancellation (SIC) is applied. To tackle the issue, this paper employs autoencoders to design interference-aware super-constellations. Unlike conventional methods where superimposed constellation may have overlapping symbols, the proposed autoencoder-based NOMA (AE-NOMA) is trained to design super-constellations with distinguishable symbols at receivers, regardless of channel gains. The proposed architecture removes the need for SIC, allowing maximum likelihood-based approaches to be used instead. The paper presents the conceptual architecture, loss functions, and training strategies for AE-NOMA. Various test results are provided to demonstrate the effectiveness of interference-aware constellations in improving the bit error rate, indicating the adaptability of AE-NOMA to different channel scenarios and its promising potential for implementing NOMA systems

Problem

• Addresses high bit error rates in NOMA due to inter-user interference.
• Proposes autoencoder-based NOMA to design distinguishable super-constellations.
• Eliminates need for SIC, enabling maximum likelihood-based decoding.

Innovation

• Autoencoders design interference-aware super-constellations
• Eliminates need for successive interference cancellation
• Improves bit error rate across channel scenarios