Li, Y., Chang, H., Zhang, Q., Gao, R., Tian, F., Tian, Q., Wang, Y., Rao, L., Guo, D., Wang, F., Zhou, S., & Xin, X. (2024). DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system. Applied Optics, 63(7), 1881-1887. https://doi.org/10.1364/AO.517521
Li, Yuzhe ; Chang, Huan ; Zhang, Qi et al. / DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system. In: Applied Optics. 2024 ; Vol. 63, No. 7. pp. 1881-1887.
@article{f5c84827edcd43b896b2a49ea6959a29,
title = "DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system",
abstract = "The probabilistic shaping (PS) technique is a key technology for fiber optic communication systems to further approach the Shannon limit.To solve the problem that nonlinear equalizers are ineffective for probabilistic shaping optical communication systems with non-uniform distribution, a distribution alignment convolutional neural network (DACNN)-aided nonlinear equalizer is proposed. The approach calibrates the equalizer using the probabilistic shaping prior distribution, which reduces the training complexity and improves the performance of the equalizer simultaneously. Experimental results show nonlinear equalization of 120 Gb/s PS 64QAM signals in a 375 km transmission scenario. The proposed DACNN equalizer improves the receiver sensitivity by 2.6 dB and 1.1 dB over the Volterra equalizer and convolutional neural network (CNN) equalizer, respectively. Meanwhile, DACNN converges with fewer training epochs than CNN, which provides great potential for mitigating the nonlinear distortion of PS signals in fiber optic communication systems.",
author = "Yuzhe Li and Huan Chang and Qi Zhang and Ran Gao and Feng Tian and Qinghua Tian and Yongjun Wang and Lan Rao and Dong Guo and Fu Wang and Sitong Zhou and Xiangjun Xin",
note = "Publisher Copyright: {\textcopyright} 2024 Optica Publishing Group.",
year = "2024",
month = mar,
day = "1",
doi = "10.1364/AO.517521",
language = "English",
volume = "63",
pages = "1881--1887",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "Optica Publishing Group",
number = "7",
}
Li, Y, Chang, H, Zhang, Q, Gao, R, Tian, F, Tian, Q, Wang, Y, Rao, L, Guo, D, Wang, F, Zhou, S & Xin, X 2024, 'DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system', Applied Optics, vol. 63, no. 7, pp. 1881-1887. https://doi.org/10.1364/AO.517521
DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system. / Li, Yuzhe
; Chang, Huan; Zhang, Qi et al.
In:
Applied Optics, Vol. 63, No. 7, 01.03.2024, p. 1881-1887.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system
AU - Li, Yuzhe
AU - Chang, Huan
AU - Zhang, Qi
AU - Gao, Ran
AU - Tian, Feng
AU - Tian, Qinghua
AU - Wang, Yongjun
AU - Rao, Lan
AU - Guo, Dong
AU - Wang, Fu
AU - Zhou, Sitong
AU - Xin, Xiangjun
N1 - Publisher Copyright:
© 2024 Optica Publishing Group.
PY - 2024/3/1
Y1 - 2024/3/1
N2 - The probabilistic shaping (PS) technique is a key technology for fiber optic communication systems to further approach the Shannon limit.To solve the problem that nonlinear equalizers are ineffective for probabilistic shaping optical communication systems with non-uniform distribution, a distribution alignment convolutional neural network (DACNN)-aided nonlinear equalizer is proposed. The approach calibrates the equalizer using the probabilistic shaping prior distribution, which reduces the training complexity and improves the performance of the equalizer simultaneously. Experimental results show nonlinear equalization of 120 Gb/s PS 64QAM signals in a 375 km transmission scenario. The proposed DACNN equalizer improves the receiver sensitivity by 2.6 dB and 1.1 dB over the Volterra equalizer and convolutional neural network (CNN) equalizer, respectively. Meanwhile, DACNN converges with fewer training epochs than CNN, which provides great potential for mitigating the nonlinear distortion of PS signals in fiber optic communication systems.
AB - The probabilistic shaping (PS) technique is a key technology for fiber optic communication systems to further approach the Shannon limit.To solve the problem that nonlinear equalizers are ineffective for probabilistic shaping optical communication systems with non-uniform distribution, a distribution alignment convolutional neural network (DACNN)-aided nonlinear equalizer is proposed. The approach calibrates the equalizer using the probabilistic shaping prior distribution, which reduces the training complexity and improves the performance of the equalizer simultaneously. Experimental results show nonlinear equalization of 120 Gb/s PS 64QAM signals in a 375 km transmission scenario. The proposed DACNN equalizer improves the receiver sensitivity by 2.6 dB and 1.1 dB over the Volterra equalizer and convolutional neural network (CNN) equalizer, respectively. Meanwhile, DACNN converges with fewer training epochs than CNN, which provides great potential for mitigating the nonlinear distortion of PS signals in fiber optic communication systems.
UR - http://www.scopus.com/inward/record.url?scp=85186842616&partnerID=8YFLogxK
U2 - 10.1364/AO.517521
DO - 10.1364/AO.517521
M3 - Article
C2 - 38437294
AN - SCOPUS:85186842616
SN - 1559-128X
VL - 63
SP - 1881
EP - 1887
JO - Applied Optics
JF - Applied Optics
IS - 7
ER -
Li Y, Chang H, Zhang Q, Gao R, Tian F, Tian Q et al. DACNN-aided nonlinear equalizer for a probabilistic shaping coherent optical communication system. Applied Optics. 2024 Mar 1;63(7):1881-1887. doi: 10.1364/AO.517521