Neural Network Based Successive Cancellation Decoding Algorithm for Polar Codes in URLLC

Polar codes are considered as a competitive candidate for 5G ultra-reliable and low-latency communication (URLLC) channel codes, but its strict latency and reliability requirements pose signicant challenges to the existing decoding schemes, especially in terms of decoding latency. In this paper, we propose a neural network based successive cancellation (NN-SC) decoding algorithm. In the proposed algorithm, neural networks are used to replace the local decoders for rate-R constituent codes because of their one-shot decoding capacity, which greatly reduce the decoding latency and algorithmic complexity. The simulation results indicate that the NN-SC decoding algorithm can achieve comparable reliability performance against the successive cancellation (SC) decoding for a polar code of length 128 and rate 1/6, while reducing the decoding latency by 65.2% when compared with the simplified SC decoding. In addition, for two conventional decoding algorithms: SC and belief propagation (BP) decoding, the proposed algorithm can further reduce the decoding latency by 22.8% and 13.8%, respectively.

[1]  Warren J. Gross,et al.  Increasing the Throughput of Polar Decoders , 2013, IEEE Communications Letters.

[2]  Warren J. Gross,et al.  A Semi-Parallel Successive-Cancellation Decoder for Polar Codes , 2013, IEEE Transactions on Signal Processing.

[3]  Kai Chen,et al.  Polar codes: Primary concepts and practical decoding algorithms , 2014, IEEE Communications Magazine.

[4]  Branka Vucetic,et al.  Short Block-Length Codes for Ultra-Reliable Low Latency Communications , 2019, IEEE Communications Magazine.

[5]  Xiaohu You,et al.  Improved polar decoder based on deep learning , 2017, 2017 IEEE International Workshop on Signal Processing Systems (SiPS).

[6]  David Burshtein,et al.  Deep Learning Methods for Improved Decoding of Linear Codes , 2017, IEEE Journal of Selected Topics in Signal Processing.

[7]  Mohammad Salim,et al.  Polar Code: The Channel Code contender for 5G scenarios , 2017, 2017 International Conference on Computer, Communications and Electronics (Comptelix).

[8]  Mehdi Bennis,et al.  eMBB-URLLC Resource Slicing: A Risk-Sensitive Approach , 2019, IEEE Communications Letters.

[9]  Frank R. Kschischang,et al.  A Simplified Successive-Cancellation Decoder for Polar Codes , 2011, IEEE Communications Letters.

[10]  Yair Be'ery,et al.  Learning to decode linear codes using deep learning , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[11]  Cicek Cavdar,et al.  Risk-Aware Resource Allocation for URLLC: Challenges and Strategies with Machine Learning , 2018, IEEE Communications Magazine.

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Krzysztof Wesolowski,et al.  Channel Coding for Ultra-Reliable Low-Latency Communication in 5G Systems , 2016, 2016 IEEE 84th Vehicular Technology Conference (VTC-Fall).

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Huazi Zhang,et al.  Performance Evaluation of Channel Decoding with Deep Neural Networks , 2017, 2018 IEEE International Conference on Communications (ICC).

[16]  Stephan ten Brink,et al.  On deep learning-based channel decoding , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[17]  Keshab K. Parhi,et al.  Early Stopping Criteria for Energy-Efficient Low-Latency Belief-Propagation Polar Code Decoders , 2014, IEEE Transactions on Signal Processing.

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  Erdal Arikan,et al.  Channel Polarization: A Method for Constructing Capacity-Achieving Codes for Symmetric Binary-Input Memoryless Channels , 2008, IEEE Transactions on Information Theory.

[20]  Stephan ten Brink,et al.  Scaling Deep Learning-Based Decoding of Polar Codes via Partitioning , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[21]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[22]  Warren J. Gross,et al.  Neural Successive Cancellation Decoding of Polar Codes , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).