基于外信息符号差的LT码串行译码算法

Serial decoding algorithm based on extrinsic information symbol difference for LT code

在无线通信系统中,LT码采用置信传播(BP)译码算法进行译码,缺少有效的迭代控制机制。针对这一问题,首先将串行置信传播(SBP)算法应用于LT码的译码,极大地提高了译码收敛速度。其次,通过对LT码在加性高斯白噪声(AWGN)信道下的外信息转移(EXIT)曲线的分析,提出了一种基于外信息符号差的串行置信传播(ESD-SBP)译码算法,即根据一次完整迭代前后符号节点译码器(SND)的外信息符号变化情况来快速判断译码收敛情况、控制迭代停止。最后对固定迭代次数、互熵算法(CE)、循环冗余校验(CRC)以及外信息符号差算法(ESD)进行了性能对比。仿真结果表明,在不降低串行译码(SBP)算法性能的前提下,可以有效减小迭代次数。

In the wireless communication system , BP （ belief propagation ） decoding algorithm is used for LT code ’ s decoding , which lacks of effective iterative control mechanism .For the problems existed , this paper first applies SBP （ serial belief propagation ） algorithm to the decoding of LT code , which greatly improves the decoding speed of convergence .Secondly , by the analysis of EXIT （ extrinsic information transfer ） curve of LT code in AWGN （ addi-tive white Gaussian noise ） channel , the paper puts forward a kind of SBP decoding algorithm based on the ESD （ extrinsic information symbols difference ） -SBP , which is to quickly judge the convergence condition and control the iteration according to the change of the extrinsic information symbol from SND （ symbol nodes decoder ） before and after a full iteration.Finally, a comparison is made between the performance of the fixed number of iterations , CE （ cross-entropy concept ） , CRC （ cyclic redundancy check ） and the algorithm ESD （ extrinsic information sym-bol difference ） .The experimental results show that , the algorithm presented in this paper can reduce the number of iterations effectively without reducing the performance of serial decoding algorithm .