Premium
Probabilistic shaping communication system aided by neural network distribution matcher in data center optical network
Author(s) -
Jing Zexuan,
Tian Qinghua,
Xin Xiangjun,
Wang Yongjun,
Guo Dong,
Sheng Xia,
Yu Chao
Publication year - 2021
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/mop.32930
Subject(s) - transmitter , computer science , quadrature amplitude modulation , probabilistic logic , artificial neural network , signal (programming language) , gaussian , modulation (music) , genetic algorithm , encode , electronic engineering , algorithm , bit error rate , artificial intelligence , telecommunications , decoding methods , engineering , channel (broadcasting) , physics , machine learning , biochemistry , chemistry , quantum mechanics , acoustics , gene , programming language
Abstract A neural network (NN)‐assisted probabilistic shaping (PS) distribution matcher is proposed, in which the model is simplified by a structured optimization method. The NN algorithm can encode the information sequence, making the signal obey the Gaussian distribution, and can directly restore the received signal. In addition, the algorithm uses the novel training method at both ends of the transmitter and receiver so that the system performance is significantly improved. PS system verification experiments have been carried out under 16QAM‐DMT modulation format. Under the hard decision forward error correction (FEC) threshold of 3.8*10 −3 BER, the proposed system achieves 1.1 dB improvement compared to the traditional 16QAM‐DMT system.