基于BP译码算法的准循环低密度奇偶校验码量化问题研究

The research on quantization issues of quasi-cycle low-density parity check codes based on BP algorithm

基于改进的BP译码算法—LLR BP译码算法,在AWGN信道下,在量化范围、量化比特数、量化方式选择这三方面分别对输入信号和中间变量进行了性能仿真与对比,最后经过分析比较,提出了一种新型和有效的量化方案.笔者采用的奇偶校验码为基于802.16e标准的准循环低密度奇偶校验码(QC-LDPC).在假设输入信号为等概输入,且设置译码算法中最大迭代次数为10的前提下,通过MATLAB仿真,可发现准循环低密度奇偶校验码不但具有良好的性能,而且更有利于硬件的实现.与此同时,与未量化的LLR BP译码算法相比,文中提出的方案不但可以保持较低误码率,而且还极大的减小了硬件复杂度.

The quantization issues of the belief propagation （BP） algorithm for the quasi-cycle low-density parity code （QC-LDPC） of 802.16e standard are studied in this paper.We consider the quantization problem of input signal and mid-variables from the following three aspects：the variables range,bits and methods of the quantization and make a performance simulation and contrast..Then,a innovative and efficient scheme of quantization is proposed in this paper.The quasi-cycle low-density parity code （QC-LDPC） is used here.It has a better performance and it is beneficial for implementation of hardware.Assuming the input is equiprobable signal and the maximum number of iteration is 10,comparing to the standard （non-quantization） BP algorithm,the proposed scheme keeps the lower bit error rate （BER） by means of the MATLAB simulation meanwhile the hardware complexity is greatly reduced.