Neural Successive Cancellation Flip Decoding of Polar Codes
- PDF / 1,624,995 Bytes
- 12 Pages / 595.224 x 790.955 pts Page_size
- 3 Downloads / 222 Views
Neural Successive Cancellation Flip Decoding of Polar Codes Nghia Doan1
· Seyyed Ali Hashemi2 · Furkan Ercan1 · Thibaud Tonnellier1 · Warren J. Gross1
Received: 15 April 2020 / Revised: 13 August 2020 / Accepted: 23 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Dynamic successive cancellation flip (DSCF) decoding of polar codes is a powerful algorithm that can achieve the error correction performance of successive cancellation list (SCL) decoding, with an average complexity that is close to that of successive cancellation (SC) decoding at practical signal-to-noise ratio (SNR) regimes. However, DSCF decoding requires costly transcendental computations to calculate a bit-flipping metric, which adversely affect its implementation complexity. In this paper, we first show that a direct application of common approximation schemes on the conventional DSCF decoding results in a significant error-correction performance loss. We then introduce an additive perturbation parameter and propose an approximation scheme which completely removes the need to perform transcendental computations in DSCF decoding. Machine learning (ML) techniques are then utilized to optimize the perturbation parameter of the proposed scheme. Furthermore, a quantization scheme is developed to enable efficient hardware implementation. Simulation results show that when compared with DSCF decoding, the proposed decoder with quantization scheme only experiences a negligible errorcorrection performance degradation of less that 0.08 dB at a target frame-error-rate (FER) of 10−4 , for a polar code of length 512 with 256 information bits. In addition, the bit-flipping metric computation of the proposed decoder reduces up to around 31% of the number of additions used by the bit-flipping metric computation of DSCF decoding, without any need to perform costly transcendental computations and multiplications. Keywords 5G · Polar codes · Deep learning · SC flip
1 Introduction Polar codes are proven to achieve channel capacity for any binary symmetric channel under the low-complexity Nghia Doan
[email protected] Seyyed Ali Hashemi [email protected] Furkan Ercan [email protected] Thibaud Tonnellier [email protected] Warren J. Gross [email protected] 1
Department of Electrical and Computer Engineering, McGill University, Montreal, Canada
2
Department of Electrical Engineering, Stanford University, Stanford, USA
successive cancellation (SC) decoding as the code length increases towards infinity [3]. Recently, polar codes are selected for use in the enhanced mobile broadband (eMBB) control channel of the fifth generation of cellular mobile communications (5G standard), which requires codes of short length [1]. The error-correction performance of SC decoding for short polar codes does not satisfy the requirements of the 5G standard. A SC list (SCL) decoding was introduced in [22] to improve the error-correction performance of SC decoding for short to moderate polar codes by main
Data Loading...
