Wang, F., Gao, R., Li, Z., Liu, J., Cui, Y., Xu, Q., Pan, X., Zhu, L., Wang, F., Guo, D., Chang, H., Zhou, S., Dong, Z., Zhang, Q., Tian, Q., Tian, F., Huang, X., Yan, J., Jiang, L., & Xin, X. (2023). 400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer. Optics Express, 31(14), 22622-22634. https://doi.org/10.1364/OE.492795
Wang, Fei ; Gao, Ran ; Li, Zhipei et al. / 400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer. In: Optics Express. 2023 ; Vol. 31, No. 14. pp. 22622-22634.
@article{07d365e161da4672823da88405e9457f,
title = "400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer",
abstract = "Nonlinear impairment in a high-speed orbital angular momentum (OAM) mode-division multiplexing (MDM) optical fiber communication system presents high complexity and strong stochasticity due to the massive optoelectronic devices. In this paper, we propose an Affinity Network (AffinityNet) nonlinear equalizer for an OAM-MDM intensity-modulation direct-detection (IM/DD) transmission with four OAM modes. The labeled training and testing signals from the OAM-MDM system can be regarded as “small sample” and “large target”, respectively. AffinityNet can be used to build an accurate nonlinear model using “small sample” based on few-shot learning and can predict the stochastic characteristic nonlinearity of OAM-MDM with a high level of generalization. As a result, the AffinityNet nonlinear equalizer can effectively compensate the stochastic nonlinearity in the OAM-MDM system, despite the large difference between the training and testing signals due to the stochastic nonlinear impairment. An experiment was conducted on a 400 Gbit/s transmission with four OAM modes using a pulse amplitude modulation-8 (PAM-8) signal over a 2 km ring-core fiber (RCF). Our experimental results show that the proposed nonlinear equalizer outperformed the conventional Volterra equalizer with improvements in receiver sensitivity of 1.7, 1.8, 3, and 3.3 dB for the four OAM modes at the 15% forward error correction (FEC) threshold, respectively. In addition, the proposed equalizer outperformed a convolutional neural network (CNN) equalizer with improvements in receiver sensitivity of 0.8, 0.5, 0.9, and 1.4 dB for the four OAM modes at the 15% FEC threshold. In the experiment, a complexity reduction of 37% and 83% of the AffinityNet equalizer is taken compared to the conventional Volterra equalizer and CNN equalizer, respectively. The proposed equalizer is a promising candidate for a high-speed OAM-MDM optical fiber communication system.",
author = "Fei Wang and Ran Gao and Zhipei Li and Jie Liu and Yi Cui and Qi Xu and Xiaolong Pan and Lei Zhu and Fu Wang and Dong Guo and Huan Chang and Sitong Zhou and Ze Dong and Qi Zhang and Qinghua Tian and Feng Tian and Xin Huang and Jinghao Yan and Lin Jiang and Xiangjun Xin",
note = "Publisher Copyright: {\textcopyright} 2023 OSA - The Optical Society. All rights reserved.",
year = "2023",
month = jul,
day = "3",
doi = "10.1364/OE.492795",
language = "English",
volume = "31",
pages = "22622--22634",
journal = "Optics Express",
issn = "1094-4087",
publisher = "Optica Publishing Group",
number = "14",
}
Wang, F, Gao, R, Li, Z, Liu, J, Cui, Y, Xu, Q, Pan, X, Zhu, L, Wang, F, Guo, D, Chang, H, Zhou, S, Dong, Z, Zhang, Q, Tian, Q, Tian, F, Huang, X, Yan, J, Jiang, L & Xin, X 2023, '400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer', Optics Express, vol. 31, no. 14, pp. 22622-22634. https://doi.org/10.1364/OE.492795
400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer. / Wang, Fei
; Gao, Ran; Li, Zhipei et al.
In:
Optics Express, Vol. 31, No. 14, 03.07.2023, p. 22622-22634.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - 400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer
AU - Wang, Fei
AU - Gao, Ran
AU - Li, Zhipei
AU - Liu, Jie
AU - Cui, Yi
AU - Xu, Qi
AU - Pan, Xiaolong
AU - Zhu, Lei
AU - Wang, Fu
AU - Guo, Dong
AU - Chang, Huan
AU - Zhou, Sitong
AU - Dong, Ze
AU - Zhang, Qi
AU - Tian, Qinghua
AU - Tian, Feng
AU - Huang, Xin
AU - Yan, Jinghao
AU - Jiang, Lin
AU - Xin, Xiangjun
N1 - Publisher Copyright:
© 2023 OSA - The Optical Society. All rights reserved.
PY - 2023/7/3
Y1 - 2023/7/3
N2 - Nonlinear impairment in a high-speed orbital angular momentum (OAM) mode-division multiplexing (MDM) optical fiber communication system presents high complexity and strong stochasticity due to the massive optoelectronic devices. In this paper, we propose an Affinity Network (AffinityNet) nonlinear equalizer for an OAM-MDM intensity-modulation direct-detection (IM/DD) transmission with four OAM modes. The labeled training and testing signals from the OAM-MDM system can be regarded as “small sample” and “large target”, respectively. AffinityNet can be used to build an accurate nonlinear model using “small sample” based on few-shot learning and can predict the stochastic characteristic nonlinearity of OAM-MDM with a high level of generalization. As a result, the AffinityNet nonlinear equalizer can effectively compensate the stochastic nonlinearity in the OAM-MDM system, despite the large difference between the training and testing signals due to the stochastic nonlinear impairment. An experiment was conducted on a 400 Gbit/s transmission with four OAM modes using a pulse amplitude modulation-8 (PAM-8) signal over a 2 km ring-core fiber (RCF). Our experimental results show that the proposed nonlinear equalizer outperformed the conventional Volterra equalizer with improvements in receiver sensitivity of 1.7, 1.8, 3, and 3.3 dB for the four OAM modes at the 15% forward error correction (FEC) threshold, respectively. In addition, the proposed equalizer outperformed a convolutional neural network (CNN) equalizer with improvements in receiver sensitivity of 0.8, 0.5, 0.9, and 1.4 dB for the four OAM modes at the 15% FEC threshold. In the experiment, a complexity reduction of 37% and 83% of the AffinityNet equalizer is taken compared to the conventional Volterra equalizer and CNN equalizer, respectively. The proposed equalizer is a promising candidate for a high-speed OAM-MDM optical fiber communication system.
AB - Nonlinear impairment in a high-speed orbital angular momentum (OAM) mode-division multiplexing (MDM) optical fiber communication system presents high complexity and strong stochasticity due to the massive optoelectronic devices. In this paper, we propose an Affinity Network (AffinityNet) nonlinear equalizer for an OAM-MDM intensity-modulation direct-detection (IM/DD) transmission with four OAM modes. The labeled training and testing signals from the OAM-MDM system can be regarded as “small sample” and “large target”, respectively. AffinityNet can be used to build an accurate nonlinear model using “small sample” based on few-shot learning and can predict the stochastic characteristic nonlinearity of OAM-MDM with a high level of generalization. As a result, the AffinityNet nonlinear equalizer can effectively compensate the stochastic nonlinearity in the OAM-MDM system, despite the large difference between the training and testing signals due to the stochastic nonlinear impairment. An experiment was conducted on a 400 Gbit/s transmission with four OAM modes using a pulse amplitude modulation-8 (PAM-8) signal over a 2 km ring-core fiber (RCF). Our experimental results show that the proposed nonlinear equalizer outperformed the conventional Volterra equalizer with improvements in receiver sensitivity of 1.7, 1.8, 3, and 3.3 dB for the four OAM modes at the 15% forward error correction (FEC) threshold, respectively. In addition, the proposed equalizer outperformed a convolutional neural network (CNN) equalizer with improvements in receiver sensitivity of 0.8, 0.5, 0.9, and 1.4 dB for the four OAM modes at the 15% FEC threshold. In the experiment, a complexity reduction of 37% and 83% of the AffinityNet equalizer is taken compared to the conventional Volterra equalizer and CNN equalizer, respectively. The proposed equalizer is a promising candidate for a high-speed OAM-MDM optical fiber communication system.
UR - http://www.scopus.com/inward/record.url?scp=85165510662&partnerID=8YFLogxK
U2 - 10.1364/OE.492795
DO - 10.1364/OE.492795
M3 - Article
C2 - 37475368
AN - SCOPUS:85165510662
SN - 1094-4087
VL - 31
SP - 22622
EP - 22634
JO - Optics Express
JF - Optics Express
IS - 14
ER -
Wang F, Gao R, Li Z, Liu J, Cui Y, Xu Q et al. 400 Gbit/s 4 mode transmission for IM/DD OAM mode division multiplexing optical fiber communication with a few-shot learning-based AffinityNet nonlinear equalizer. Optics Express. 2023 Jul 3;31(14):22622-22634. doi: 10.1364/OE.492795