Cyclic Group Projection for Enumerating Quasi-Cyclic Codes Trapping Sets
Vasiliy Usatyuk, Yury Kuznetsov, Sergey Egorov
TL;DR
This work addresses efficient enumeration and weighing of trapping sets in quasi-cyclic codes with composite circulant sizes. It introduces a cyclic-group projection framework that relates trapping sets across circulant sizes via projections $P_{z\to z_*}$ and lifting, leveraging $l$-coverings and the automorphism group $\mathcal{G}_{n,z}$. A tabular importance-sampling approach is developed to estimate pseudo-codeword weights, exploiting QC structure and orbit decompositions to reduce variance and computation. The combined method enables scalable TS analysis and error-floor estimation for QC codes used in standards, such as 5G QC-LDPC and DVB codes, enhancing decoding reliability in practical channels.
Abstract
This paper introduces a novel approach to enumerate and assess Trapping sets in quasi-cyclic codes, those with circulant sizes that are non-prime numbers. Leveraging the quasi-cyclic properties, the method employs a tabular technique to streamline the importance sampling step for estimating the pseudo-codeword weight of Trapping sets. The presented methodology draws on the mathematical framework established in the provided theorem, which elucidates the behavior of projection and lifting transformations on pseudo-codewords
