Weak information signals can be detected with the assistance of stochastic perturbation, and nonlinear systems benefit from this phenomenon. Inspired by this, we propose a noise-assisted NMS list (Na-NMSL) algorithm for LDPC decoding. The algorithm consists of L independent NMS decoders, and the inputs of the NMS decoders are generated by adding artificial noise with different strengths to the received signal. When lifting size Z is small, list decoding is performed in the Na-NMSL decoder by utilizing the remaining hardware resources. Therefore, the Na-NMSL decoder enhances the decoding performance of NMS without additional hardware overhead. Simulation results show that the Na-NMSL decoder has a lower block error rate (BLER) and faster convergence than traditional NMS decoding.
Weak information signals can be detected with the assistance of stochastic perturbation, and nonlinear systems benefit from this phenomenon. Inspired by this, we propose a noise-assisted NMS list (Na-NMSL) algorithm for LDPC decoding. The algorithm consists of L independent NMS decoders, and the inputs of the NMS decoders are generated by adding artificial noise with different strengths to the received signal. When lifting size Z is small, list decoding is performed in the Na-NMSL decoder by utilizing the remaining hardware resources. Therefore, the Na-NMSL decoder enhances the decoding performance of NMS without additional hardware overhead. Simulation results show that the Na-NMSL decoder has a lower block error rate (BLER) and faster convergence than traditional NMS decoding.
In recent years, many communication standards have adopted the LDPC (Low-Density Parity Check) code due to its excellent error correction performance, but it also induces some problems. For example, the use of 5G in mobile phones dramatically reduces battery life. Therefore, it is particularly significant for LDPC code to design a decoding algorithm that does not increase hardware implementation complexity but has superior error correction performance and iteration speed faster than traditional decoding algorithms. Inspired by several network structures in artificial intelligence, bias is used to improve the performance and robustness of the network. In order to enhance decoding algorithm robustness and accuracy, a method is shown by changing the offset in OMSA to the bias and combining NMSA in the near-zero range in this paper. It significantly avoids the log-likelihood ratio information loss when less than the offset value and diminishes too quickly or sluggishly. A Segmented Bias/Normalize Min-Sum(SB/NMS) LDPC decoding algorithm is proposed with a layered structure. This algorithm can avoid the impact of the problems mentioned above and significantly improve the performance and iteration speed of the decoding process. Compared with the BLER (resp. BER) performance the traditional BP, NMS and OMS algorithm achieves a gain of 0.04, 0.11, and 0.15dB (resp. 0.035dB, 0.06, and 0.13dB). Meanwhile, the minimum SNR requirements of BLER =0.001 can be reduced by 0.02 dB compared with the BP algorithm. The parameters of SN/NMSA can be pre-processed on the computer, so there will be no additional increase in the overhead in resources and get better performance while getting faster iteration speed, while greatly guaranteeing the reliability and effectiveness of data transmission.
This paper presents the novel Stochastic decoding-convolutional neural network (SD-CNN) structure, with the goal of enhancing 5G LDPC code’s decoding efficiency in the presence of correlated noise of the channel. Applying the stochastic approach acts as an alternate technique to fixed-point LDPC decoding to enhance the decoder’s hardware efficiency. In order to improve the efficacy of the decoder, we adopted deep learning method such as Convolutional neural network (CNN). CNNs can be employed for denoising purposes in communication systems, where signals may be compromised by diverse forms of noise while being transmitted, with the aim of enhancing signal quality and dependability. The SD-CNN architecture combines a trained CNN with a stochastic decoder of 5G LDPC codes, thereby utilizing the CNN’s capability to accurately estimate channel noise and, consequently, enhance the error correction capabilities of the decoder. The generated output of the trained CNN is then fed back into the stochastic decoder, creating an iterative process between the SD and CNN that ultimately leads to superior decoding performance. For 5G LDPC code word lengthN=3808, with a base code rateR=1/3, the suggested SD-CNN architecture achieves a BER of10−6at 0.6 dB of SNR per bit in the strong correlation of channel noise condition, in comparison to SD, which achieves a BER of10−6at 3.5 dB of SNR per bit. The results demonstrate that there is a 2.9 dB improvement.
For recent years, deep learning has been studied and utilized among decoders in wireless and optical communication. For low density parity check (LDPC) codes, most works use neural network (NN) to implement the belief propagation (BP) decoder and unfold its iterations into layers activated by different functions. However, the whole decoder composed by neural network performs lots of non-linear operations, which are time consuming and unfriendly to hardware implementation. In this work, a neural network-aided normalized min-sum (NN-aided NMS) decoder for LDPC code is proposed, in which the normalization factors are inferred from input log likelihood ratio (LLR) by apre-trained NN, while maintaining check and variable nodes processing the same as in min-sum (MS) decoder. In order to test the proposed decoder with irregular LDPC code, a rate-7/8 one was constructed using progressive edge growth (PEG) algorithm, showing better error correction capability than the standard of consultative committee for space data systems (CCSDS) LDPC (8176,7154) code by 0.08 dB with the same rate. Simulation results show that, NN-aided NMS decoder outperforms MS decoder by 0.3 dB, and its performance approaches BP decoder with a gap of 0.02 dB, which is 50% closer than the best NMS decoder using 0.7 as the normalization factor. The proposed decoder has good performance for both regular and irregular LDPC codes, and needs much less computation complexity than BP decoder. It introduces more linear computation than NMS decoder but achieves better bit error rate (BER) performance, thus becoming a good complement between BP and NMS decoder when trading off among complexity, error correction performance and hardware implementation for wireless and satellite communication.
Low-density parity-check (LDPC) codes are of prime importance in achieving near-Shannon capacity in current communication systems. However, the optimal decoding process for LDPC codes is computationally intensive. This paper presents a neural normalized min-sum (NNMS) decoding network that improves error correction capabilities with minimal computational overhead. A weight-sharing approach is adopted in the NNMS model, in which the correction factors (α, β) are shared across nodes within a single layer. This approach decreases the total number of parameters in the model compared to traditional neural decoders, making it easier for hardware implementation. The NNMS model is tested using a (576, 432) LDPC code for an additive white Gaussian noise channel with binary phase shift keying modulation. Simulation results show that the NNMS model outperforms traditional normalized min-sum (NMS) decoders. At a signal-to-noise ratio of 5 dB, the NNMS model has a bit-error rate (BER) of 1.0 × 10−7, whereas traditional NMS models have a less steep slope. In particular, the NNMS model has a coding gain of 1.25 dB compared to the traditional NMS model at a BER threshold of 1.0 × 10−3. This shows that the NNMS model is an efficient solution for high-performance, real-time digital communication systems.
LDPC code is a widely-used high-performance error correction code. In recent years, LDPC decoding based on deep learning and neural networks becomes a research hotspot. Based on the (512,256) LDPC code of the CCSDS standard, this paper firstly studies the traditional decoding algorithms of SP, MS, NMS, and OMS, laying a foundation for the construction of neural networks. Then a data-driven (DD) decoding method is studied which adopts the information with its encoded, modulated and noise-added LDPC code as the training data within a Multi-layer Perceptron (MLP) neural network. In order to solve the problem of high bit error rate (BER) in data-driven method, the Neural Normalized Min-sum (NNMS) decoding in which the NMS algorithm is mapped to the neural network structure is proposed, achieving more excellent BER performance than that of NMS. The BER declines by 85.19% when channel SNR equals to 3.5 dB. Finally, improved training methods to enhance the SNR generalization ability of the NNMS network is studied.
Low-density parity-check (LDPC) codes have been selected as the channel coding scheme for 5G NR standard, which have excellent performance approaching the Shannon limit and are easy to implement in hardware. The decoding algorithm and scheduling scheme of LDPC codes have a significant impact on performance. The row degree (RD) and the number of punctured bits (PBs) are widely used to determine the update order of layers. In this letter, we used Matlab to simulate the error performance of the 5G LDPC codes. We completed the bit error rate and frame error rate simulations of six different decoding algorithms, including flooding LLR-BP, flooding NMS, layered LLR-BP, layered NMS, the lowest degree and least-punctured (LD-LP) layered LLR-BP and LD-LP layered NMS methods, for the 5G LDPC code with a base graph of size [46, 68], code rate 1/3, and code length of 1584.We further compared the performance of LD-LP layered decoding and LP-LD layered decoding. Moreover, we simulated the error performance of the core part of the LDPC code, which consists of four layers. We evaluated the effect of the update order of the four layers on the error performance of the code, and concluded that some update orders might give slightly better error performance than others.