Polar code decoding algorithm, polar code decoding receiving end and polar code decoding system in low-signal-to-noise-ratio scene of low-orbit satellite

Abstract

The invention discloses a polar code decoding algorithm, a polar code decoding receiving end and a polar code decoding system in a low-signal-to-noise-ratio scene of a low-orbit satellite. The algorithm comprises the following steps: S1, demodulating a received polarization signal to obtain a signal flow, and calculating a likelihood value of the signal flow; S2, inputting the likelihood value into a decoder, and outputting a decoding result by the decoder; wherein the decoder comprises at least one decoding link, each decoding link is provided with M BP decoding network modules and M neural network modules, the BP decoding network modules and the neural network modules are alternately arranged, and data interaction branches are arranged between the BP decoding network modules corresponding to the positions of the different decoding links; and inputting the likelihood values into the BP decoding network module at the starting end of each decoding link in a blocking manner, and combining output signals of the neural network modules at the tail ends of all the decoding links to obtain a decoding result. Compared with a traditional SC algorithm, the invention has the advantages that decoding delay is reduced, decoding accuracy is improved, and neural network training speed is increased.

Description

technical field [0001] The present invention relates to the technical field of coding and decoding, in particular to a polar code decoding algorithm, a receiving terminal and a system in a scene of low signal-to-noise ratio of low-orbit satellites. Background technique [0002] Since Arikan proposed polar codes in 2009, polar codes, a new encoding and decoding method, have achieved great success. Regardless of the complexity of encoding and decoding or the bit error rate control of encoding and decoding, polar codes have shown considerable advantages. [0003] In the decoding algorithm part, the existing commonly used algorithms are mainly the Serial Elimination Algorithm (Successive Cancellation Algorithm, hereinafter referred to as the SC algorithm, derived algorithms such as SCL, etc.) and the Belief Propagation (BP) algorithm. Among them, the SC algorithm has the advantage of lower computational complexity (according to Arikan's analysis, the complexity of the SC decodi...

Images