Abstract This paper presents an intelligent decoding methodology for low-density parity-check (LDPC) and Polar codes (P-C) based on deep reinforcement learning (DRL+Soft) for modern 5G and emerging 6G communication systems. The proposed decoder adapts its decoding strategy in real-time, optimizing bit error rate (BER) performance under varying channel conditions. Evaluation is formulated through performance metrics including BER convergence, reward dynamics, computational complexity (FLOPs), and inference latency. Simulation results show that the DRL+Soft decoder achieves up to a 2.5-fold reduction in computational cost and decreases inference time from 4.8 ms (BP) to 1.6 ms per data block, while maintaining superior BER compared to classical belief propagation (BP) and cyclic redundancy check-aided successive cancellation list (CA-SCL) decoders. The decoder exhibits improved robustness against unpredictable interference and channel impairments, making it suitable for dense device deployments and ultra-reliable low-latency communication (URLLC) scenarios. The methodology also supports reprogramming or retraining of DRL agents without hardware changes, ensuring long-term adaptability for evolving 6G networks. These results demonstrate both theoretical novelty and practical value, providing a scalable and energy-efficient solution for future wireless communication systems.
Abstract This paper presents an intelligent decoding methodology for low-density parity-check (LDPC) and Polar codes (P-C) based on deep reinforcement learning (DRL+Soft) for modern 5G and emerging 6G communication systems. The proposed decoder adapts its decoding strategy in real-time, optimizing bit error rate (BER) performance under varying channel conditions. Evaluation is formulated through performance metrics including BER convergence, reward dynamics, computational complexity (FLOPs), and inference latency. Simulation results show that the DRL+Soft decoder achieves up to a 2.5-fold reduction in computational cost and decreases inference time from 4.8 ms (BP) to 1.6 ms per data block, while maintaining superior BER compared to classical belief propagation (BP) and cyclic redundancy check-aided successive cancellation list (CA-SCL) decoders. The decoder exhibits improved robustness against unpredictable interference and channel impairments, making it suitable for dense device deployments and ultra-reliable low-latency communication (URLLC) scenarios. The methodology also supports reprogramming or retraining of DRL agents without hardware changes, ensuring long-term adaptability for evolving 6G networks. These results demonstrate both theoretical novelty and practical value, providing a scalable and energy-efficient solution for future wireless communication systems.
With changing scenarios in Beyond 5G (B5G) systems, channel coding methods will be faced with stronger requirements for reliability, flexibility, and low latency.Conventional decoding algorithms such as Belief Propagation (BP) are efficient in structured contexts but not sufficiently flexible to respond effectively to dynamic and noisy channel conditions.In this study, we introduces a new Graph Neural Network (GNN)-based solution to decode Low-Density Parity-Check (LDPC) codes by taking advantage of the intrinsic bipartite graph representation of Tanner graphs.The proposed decoder learns a data-driven messagepassing algorithm that performs better than BP over a large range of signal-to-noise ratios (SNRs) and block lengths.The experimental results show that the GNN-based decoder yields much lower bit error rates (BER), faster convergence, and better resistance to noise variability than belief propagation, especially at medium to high SNR levels.Thus, our findings highlight the foundation for scalable, adaptive, and intelligent decoding systems in B5G and 6G architectures.
Next-generation communication systems face challenges in meeting the growing demand of ultra-reliable low-latency communications (URLLC), which require advanced physical-layer designs, especially in channel coding. To satisfy the strict reliability and latency constraints of URLLC in 5G and emerging 6G networks, it is essential to use short codes with robust error-correction capabilities. This thesis explores the application of deep learning methodologies to develop advanced channel coding frameworks for short linear block codes. First, I propose a novel decoding algorithm for short block codes based on an edge-weighted graph neural network (EW-GNN). The EW-GNN decoder operates on the Tanner graph with an iterative message-passing structure, algorithmically aligning with conventional belief propagation (BP) decoding. The decoder is characterized by scalability, with trainable parameters independent of codeword length, and outperforms BP and existing deep-learning-based methods. I present a novel auto-encoder integrating deep reinforcement learning (DRL) and graph neural networks (GNN) for end-to-end channel coding. Code generation is modeled as a Markov decision process to optimize error rates and algebraic properties. An iterative joint training of the DRL-based code designer and the EW-GNN decoder is performed to optimise the end-to-end encoding and decoding process. Simulation results show significant improvements over traditional coding schemes including LDPC and BCH codes. Finally, I design a supervised learning framework using an integrated auto-encoder architecture with a systematic code generator and matrix-based adaptive double-weighted (MA-DW) decoder. This approach achieves superior performance compared to conventional systems while reducing training complexity through joint optimization of code design and decoding parameters.
Abstract In the evolving landscape of wireless communication, particularly in Beyond 5G (B5G) systems, channel coding must meet increasingly demanding requirements for reliability, adaptability, and low latency. Traditional decoding algorithms such as Belief Propagation (BP), while effective in structured environments, lack the flexibility to adapt to dynamic and noisy channel conditions. This paper presents a novel Graph Neural Network (GNN)-based approach for decoding Low-Density Parity-Check (LDPC) codes, leveraging the inherent bipartite graph structure of Tanner graphs. The proposed decoder learns data-driven message-passing strategies that outperform BP across a wide range of signal-to-noise ratios (SNRs) and block lengths.Our implementation integrates Python-based GNN modeling with MATLAB-based LDPC encoding and benchmarks the decoding performance under additive white Gaussian noise (AWGN) channels. Experimental results demonstrate that the GNN-based decoder achieves significantly lower bit error rates (BER), faster convergence, and superior robustness to noise variability compared to BP, particularly at medium-to-high SNR levels. Furthermore, an ablation study validates the architectural efficiency of shallow GNNs with attention mechanisms and skip connections. This work highlights the potential of machine learning-enhanced decoders in redefining the physical layer of next-generation wireless networks and sets the foundation for scalable, adaptive, and intelligent decoding systems in B5G and 6G architectures.
In this paper, we propose a modified adaptive belief propagation (ABP) algorithm, which is referred to as the random ABP (R-ABP) algorithm, for decoding short channel codes adopted in the fifth generation (5G) New Radio (NR) wireless systems. Based on the cyclic redundancy check (CRC) concatenation structure of 5G channel codes, we can take partial or even all CRC bits into iterative R-ABP decoding to improve the error correction performance, while the error detection capability can still be guaranteed by the remaining CRC bits and a proposed threshold-based acceptance criterion. We call this improved R-ABP decoding the threshold-and-CRC-aided R-ABP (TCA-R-ABP) decoding. The simulation results show that our proposed TCA-R-ABP algorithm outperforms the state-of-the-art decoding algorithms for many 5G low-density parity-check (LDPC) and polar codes. Moreover, the proposed TCA-R-ABP algorithm leads to a unified decoder for LDPC and polar codes, which has the potential to be a lower-complexity decoder over the combination of the belief propagation (BP) and CRC-aided successive cancellation list (CA-SCL) decoders.
Ultra-reliable and low-latency communication (URLLC) in 6G networks is characterized by very high reliability and very low latency to enable mission-critical applications. The ability of a coding scheme to support diverse use cases requires flexibility on the part of the decoder. High reliability and low latency require decoders with improved error rate performance and reduced complexity. This article investigates candidate universal decoding algorithms for 6G communication scenarios. Universal decoders work on a wide range of error-correcting codes, making them scalable for different communication protocols. This article undertakes the comparative analysis and performance evaluation of the code-agnostic decoding schemes, including automorphism ensemble (AED), guessing random additive noise (GRAND), ordered statistics (OSD), belief propagation (BPD), bit flipping (BFD), and their variants. Simulations are carried out in MATLAB (R2024a) for the error rate performance of decoders, and plots are provided for the comparative analysis from the results of inferred data. The key findings in this paper highlight the competitive advantage of universal decoding techniques in comparison to the standardized CA-SCL decoding of polar code. Consequently, this work will help in identifying more efficient decoding algorithms for potential 6G URLLC applications. We aim to provide an insight into the scalability of universal decoding techniques by exploring their key performance metrics and comparing their performances.
This thesis investigates the optimization of Low-Density Parity-Check (LDPC) decoding through machine learning techniques, with a specific focus on 5G communication systems. Traditional LDPC decoding algorithms face a critical trade-off: Belief Propagation (BP) offers excellent error-correction performance but with high computational complexity, while Min-Sum (MS) reduces complexity at the cost of degraded performance. To address this limitation, a hybrid neural network architecture is proposed that incorporates learnable normalization and offset weights into the message-passing framework of LDPC decoders. This approach integrates multiplicative (normalization) and additive (offset) weights into the Tanner graph structure, allowing the decoder to adapt to specific channel conditions. A novel weighted binary cross-entropy loss function is developed that prioritizes entire block recovery by assigning different importance to information and parity bits during training. Experimental results demonstrate that ML-assisted decoder consistently outperforms conventional Min-Sum decoding, approaching the error-correction capability of Belief Propagation while maintaining comparable computational efficiency to Min-Sum. Comprehensive evaluations across different weight configurations (scalar and vector-based) reveal that increased parametrization generally improves decoding performance. Analysis of the impact of iteration counts shows that the optimal number of decoding iterations varies between different code configurations with studied Basegraph 1 case requiring 15 iterations for optimal performance while studied Basegraph 2 case benefits significantly from 20 iterations. The proposed ML-assisted LDPC decoder represents a significant advancement for 5G systems, offering improved error correction at lower signal strengths while balancing latency and computational requirements. This research contributes to the ongoing evolution of wireless technology by demonstrating how machine learning can effectively enhance traditional decoding algorithms, providing a practical pathway toward more efficient and adaptive error correction in modern communication systems.