Design and Analysis of Polar Codes Based on Piecewise Gaussian Approximation

TL;DR

This paper introduces piecewise Gaussian approximation techniques for polar code construction, demonstrating improved performance over traditional methods for medium and long block codes in AWGN channels.

Contribution

It proposes novel PGA-based methods, APGA and SPGA, that enhance polar code performance and accuracy with low complexity, outperforming existing Gaussian approximation approaches.

Findings

APGA improves medium block polar code performance.

SPGA achieves high accuracy for long block codes.

Both methods outperform existing Gaussian approximation techniques.

Abstract

In this article, we propose the construction of polar codes based on piecewise Gaussian approximation (PGA) techniques. The PGA is first optimized and then compared to the Gaussian approximation (GA) construction method, showing performance gains for medium blocks and high precision for long blocks, in scenarios with successive cancellation (SC) decoding and additive white gaussian noise (AWGN) channel. Based on the PGA, we develop two approximations based on multi-segmented polynomials that are easy to implement. We present the Approximate PGA (APGA) that is optimized for medium blocks and provides a performance improvement without increasing complexity. Furthermore, we develop the simplified PGA (SPGA) as an alternative to the GA, which is optimized for long blocks and achieves high construction accuracy. Simulation results show that the APGA and SPGA construction methods outperform existing GA and competing approaches for medium and long block codes with notable performance improvement.