Performance Analysis of Probabilistic Shaped Polar Code in 5G

As a coding scheme in the scenario of enhanced mobile bandwidth in 5G communication, polar codes have been deeply studied due to its communication reliability. Probability shaping is an important method to approach the channel capacity limit. Therefore, it is necessary to study the combination of polar codes and probabilistic shaping. In this paper, we analyze the performance of the shaping systematic polar codes (SPC) and the shaping non-systematic polar codes (NSPC) in SC decoding algorithms. It is proposed to combine systematic polar codes with probabilistic shaping technology, hoping to induce a sub-optimization symbol probability distribution. We found that in the scheme of probabilistic shaping based on the source sequence, the non-systematic polar code encoding method will force the bit probability in the encoded codeword to be equal, which will greatly affect the performance gain brought by the probability shaping. Therefore, in this paper, we use systematic polar encoder to protect the unequal probability characteristics of 0 and 1 in the source sequence, so that the distribution of the channel input symbols tends to the Maxwell Boltzmann distribution and achieve a performance gain of 0.6 dB.