This document proposes a deep Q-learning approach called Q-SCMA to construct codebooks for sparse code multiple access (SCMA) in an adaptive manner. SCMA is a non-orthogonal multiple access technique that can achieve low latency and high reliability for ultra-reliable low latency communications (URLLC). However, existing SCMA approaches either manually design codebooks, resulting in high complexity, or use deep learning which requires extensive training. The proposed Q-SCMA approach uses deep Q-learning to learn codebook construction and decoding strategies to minimize bit error rate while satisfying latency and reliability constraints, making it suitable for real-time applications. Simulation results show Q-SCMA outperforms conventional SCMA and deep learning

Deep Q-Learning Based Sparse Code Multiple Access For Ultra Reliable Low Latency Communication in Industrial Wireless Networks PDF

The list of books you might like