A Neural Network Based Polar Code bp Decoding Method

Abstract

The invention discloses a neural network-based polar code BP decoding method, which belongs to the technical field of wireless communication. In the non-ideal channel environment, the deep learning technology is introduced into the existing polar code BP decoding to optimize the design, and the parallel computing and global feature extraction capabilities of the Transformer model are fully utilized to implement the rough estimation noise obtained by BP decoding. Further accurate estimation, then feed back the updated LLR value to the connected BP decoding to continue iteration, thereby reducing the impact of noise correlation on BP decoding performance, and achieving the purpose of improving the reliability of BP decoding; meanwhile, the present invention The proposed method can reduce the complexity of decoding while achieving similar decoding performance.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and relates to a neural network-based polar code BP decoding method. Background technique [0002] With the explosive growth of wireless traffic, 5G is facing increasingly diverse demand drivers. As one of the three major application scenarios of 5G, ultra-reliable low-latency communication (URLLC) has strict requirements on latency and reliability. Polar codes are a suitable choice for URLLC channel coding schemes, and their bit error rate performance depends largely on the decoding algorithm used, so polar code decoding methods have attracted attention in URLLC scenarios. [0003] The BP decoding algorithm is a commonly used polar code decoding algorithm, and the existing research mainly evaluates its performance under the ideal AWGN channel. However, in an actual communication system, this ideal assumption is not always accurate, and the channel will have noise correlation, mak...

AI Technical Summary

Problems solved by technology

However, in an actual communication system, this ideal assumption is not always accurate, and the channel will have noise correlation, making it in a non-ideal channel environment, affecting the received signal

Therefore, under non-ideal channel conditions, BP decoding will encounter difficulties in dealing with the correlation in channel noise. When the number of iterations is similar, the decoding performance of the algorithm will decrease, that is, the reliability will decrease, and as the noise correlation Enhanced performance and increased performance degradation, which is not conducive to the high reliability of URLLC

Images