AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload

2025-11-25

AI Summary

To address the performance degradation of conventional channel coding caused by non-uniform HARQ-ACK bit distributions in 5G NR uplink, and the risk of radio link failure due to NACK misclassification, this paper proposes an AI-driven joint source–channel coding scheme. The method innovatively employs a Transformer architecture trained via a “free lunch” algorithm, integrated with codeword-level power shaping and an enhanced Neyman–Pearson detection criterion to provide strong unequal error protection (UEP) specifically for NACK bits. A low-complexity coherent receiver is designed to enable efficient decoding. Experimental results demonstrate that, compared to the 5G NR baseline, the proposed scheme reduces average transmit power by 3–6 dB and peak power by 2–3 dB, while significantly improving coverage and energy efficiency under fading channel conditions.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Channel coding from 2G to 5G has assumed the inputs bits at the physical layer to be uniformly distributed. However, hybrid automatic repeat request acknowledgement (HARQ-ACK) bits transmitted in the uplink are inherently non-uniformly distributed. For such sources, significant performance gains could be obtained by employing joint source channel coding, aided by deep learning-based techniques. In this paper, we learn a transformer-based encoder using a novel "free-lunch" training algorithm and propose per-codeword power shaping to exploit the source prior at the encoder whilst being robust to small changes in the HARQ-ACK distribution. Furthermore, any HARQ-ACK decoder has to achieve a low negative acknowledgement (NACK) error rate to avoid radio link failures resulting from multiple NACK errors. We develop an extension of the Neyman-Pearson test to a coded bit system with multiple information bits to achieve Unequal Error Protection of NACK over ACK bits at the decoder. Finally, we apply the proposed encoder and decoder designs to a 5G New Radio (NR) compliant uplink setup under a fading channel, describing the optimal receiver design and a low complexity coherent approximation to it. Our results demonstrate 3-6 dB reduction in the average transmit power required to achieve the target error rates compared to the NR baseline, while also achieving a 2-3 dB reduction in the maximum transmit power, thus providing for significant coverage gains and power savings.

Problem

• HARQ-ACK bits are non-uniformly distributed unlike assumed in traditional coding
• Low NACK error rate is critical to avoid radio link failures
• Existing 5G NR coding lacks efficient joint source-channel coding for HARQ-ACK

Innovation

• Transformer-based encoder with free-lunch training
• Per-codeword power shaping for robustness
• Neyman-Pearson extension for unequal error protection