Xu, Q., Gao, R., Chang, H., Li, Z., Wang, F., Cui, Y., Liu, J., Guo, D., Pan, X., Zhu, L., Zhang, Q., Tian, Q., Huang, X., Yan, J., Jiang, L., & Xin, X. (2023). Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission. Optics Express, 31(24), 40508-40524. https://doi.org/10.1364/OE.502563
Xu, Qi ; Gao, Ran ; Chang, Huan et al. / Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission. In: Optics Express. 2023 ; Vol. 31, No. 24. pp. 40508-40524.
@article{7f1ea0812f104f3cadc5998926299147,
title = "Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission",
abstract = "Orbital angular momentum (OAM) mode division multiplexing (MDM) has emerged as a new multiplexing technology that can significantly increase transmission capacity. In addition, probabilistic shaping (PS) is a well-established technique that can increase the transmission capacity of an optical fiber to close to the Shannon limit. However, both the mode coupling and the nonlinear impairment lead to a considerable gap between the OAM-MDM channel and the conventional additive white Gaussian noise (AWGN) channel, meaning that existing PS technology is not suitable for an OAM-MDM intensity-modulation direct-detection (IM-DD) system. In this paper, we propose a Bayesian generative adversarial network (BGAN) emulator based on an end-to-end (E2E) learning strategy with probabilistic shaping (PS) for an OAM-MDM IM/DD transmission with two modes. The weights and biases of the BGAN emulator are treated as a probability distribution, which can be accurately matched to the stochastic nonlinear model of OAM-MDM. Furthermore, a BGAN emulator based on an E2E learning strategy is proposed to find the optimal probability distribution of PS for an OAM-MDM IM/DD system. An experiment was conducted on a 200 Gbit/s two OAM modes carrierless amplitude phase-32(CAP-32) signal over a 5 km ring-core fiber transmission, and the results showed that the proposed BGAN emulator outperformed a conventional CGAN emulator, with improvements in modelling accuracy of 29.3% and 26.3% for the two OAM modes, respectively. Moreover, the generalized mutual information (GMI) of the proposed E2E learning strategy outperformed the conventional MB distribution and the CGAN emulator by 0.31 and 0.33 bits/symbol and 0.16 and 0.2 bits/symbol for the two OAM modes, respectively. Our experimental results demonstrate that the proposed E2E learning strategy with the BGAN emulator is a promising candidate for OAM-MDM IM/DD optic fiber communication.",
author = "Qi Xu and Ran Gao and Huan Chang and Zhipei Li and Fei Wang and Yi Cui and Jie Liu and Dong Guo and Xiaolong Pan and Lei Zhu and Qi Zhang and Qinghua 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 = nov,
day = "20",
doi = "10.1364/OE.502563",
language = "English",
volume = "31",
pages = "40508--40524",
journal = "Optics Express",
issn = "1094-4087",
publisher = "Optica Publishing Group",
number = "24",
}
Xu, Q, Gao, R, Chang, H, Li, Z, Wang, F, Cui, Y, Liu, J, Guo, D, Pan, X, Zhu, L, Zhang, Q, Tian, Q, Huang, X, Yan, J, Jiang, L & Xin, X 2023, 'Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission', Optics Express, vol. 31, no. 24, pp. 40508-40524. https://doi.org/10.1364/OE.502563
Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission. / Xu, Qi
; Gao, Ran; Chang, Huan et al.
In:
Optics Express, Vol. 31, No. 24, 20.11.2023, p. 40508-40524.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission
AU - Xu, Qi
AU - Gao, Ran
AU - Chang, Huan
AU - Li, Zhipei
AU - Wang, Fei
AU - Cui, Yi
AU - Liu, Jie
AU - Guo, Dong
AU - Pan, Xiaolong
AU - Zhu, Lei
AU - Zhang, Qi
AU - Tian, Qinghua
AU - Huang, Xin
AU - Yan, Jinghao
AU - Jiang, Lin
AU - Xin, Xiangjun
N1 - Publisher Copyright:
© 2023 OSA - The Optical Society. All rights reserved.
PY - 2023/11/20
Y1 - 2023/11/20
N2 - Orbital angular momentum (OAM) mode division multiplexing (MDM) has emerged as a new multiplexing technology that can significantly increase transmission capacity. In addition, probabilistic shaping (PS) is a well-established technique that can increase the transmission capacity of an optical fiber to close to the Shannon limit. However, both the mode coupling and the nonlinear impairment lead to a considerable gap between the OAM-MDM channel and the conventional additive white Gaussian noise (AWGN) channel, meaning that existing PS technology is not suitable for an OAM-MDM intensity-modulation direct-detection (IM-DD) system. In this paper, we propose a Bayesian generative adversarial network (BGAN) emulator based on an end-to-end (E2E) learning strategy with probabilistic shaping (PS) for an OAM-MDM IM/DD transmission with two modes. The weights and biases of the BGAN emulator are treated as a probability distribution, which can be accurately matched to the stochastic nonlinear model of OAM-MDM. Furthermore, a BGAN emulator based on an E2E learning strategy is proposed to find the optimal probability distribution of PS for an OAM-MDM IM/DD system. An experiment was conducted on a 200 Gbit/s two OAM modes carrierless amplitude phase-32(CAP-32) signal over a 5 km ring-core fiber transmission, and the results showed that the proposed BGAN emulator outperformed a conventional CGAN emulator, with improvements in modelling accuracy of 29.3% and 26.3% for the two OAM modes, respectively. Moreover, the generalized mutual information (GMI) of the proposed E2E learning strategy outperformed the conventional MB distribution and the CGAN emulator by 0.31 and 0.33 bits/symbol and 0.16 and 0.2 bits/symbol for the two OAM modes, respectively. Our experimental results demonstrate that the proposed E2E learning strategy with the BGAN emulator is a promising candidate for OAM-MDM IM/DD optic fiber communication.
AB - Orbital angular momentum (OAM) mode division multiplexing (MDM) has emerged as a new multiplexing technology that can significantly increase transmission capacity. In addition, probabilistic shaping (PS) is a well-established technique that can increase the transmission capacity of an optical fiber to close to the Shannon limit. However, both the mode coupling and the nonlinear impairment lead to a considerable gap between the OAM-MDM channel and the conventional additive white Gaussian noise (AWGN) channel, meaning that existing PS technology is not suitable for an OAM-MDM intensity-modulation direct-detection (IM-DD) system. In this paper, we propose a Bayesian generative adversarial network (BGAN) emulator based on an end-to-end (E2E) learning strategy with probabilistic shaping (PS) for an OAM-MDM IM/DD transmission with two modes. The weights and biases of the BGAN emulator are treated as a probability distribution, which can be accurately matched to the stochastic nonlinear model of OAM-MDM. Furthermore, a BGAN emulator based on an E2E learning strategy is proposed to find the optimal probability distribution of PS for an OAM-MDM IM/DD system. An experiment was conducted on a 200 Gbit/s two OAM modes carrierless amplitude phase-32(CAP-32) signal over a 5 km ring-core fiber transmission, and the results showed that the proposed BGAN emulator outperformed a conventional CGAN emulator, with improvements in modelling accuracy of 29.3% and 26.3% for the two OAM modes, respectively. Moreover, the generalized mutual information (GMI) of the proposed E2E learning strategy outperformed the conventional MB distribution and the CGAN emulator by 0.31 and 0.33 bits/symbol and 0.16 and 0.2 bits/symbol for the two OAM modes, respectively. Our experimental results demonstrate that the proposed E2E learning strategy with the BGAN emulator is a promising candidate for OAM-MDM IM/DD optic fiber communication.
UR - http://www.scopus.com/inward/record.url?scp=85178332597&partnerID=8YFLogxK
U2 - 10.1364/OE.502563
DO - 10.1364/OE.502563
M3 - Article
C2 - 38041350
AN - SCOPUS:85178332597
SN - 1094-4087
VL - 31
SP - 40508
EP - 40524
JO - Optics Express
JF - Optics Express
IS - 24
ER -
Xu Q, Gao R, Chang H, Li Z, Wang F, Cui Y et al. Bayesian generative adversarial network emulator based end-to-end learning strategy of the probabilistic shaping for OAM mode division multiplexing IM/DD transmission. Optics Express. 2023 Nov 20;31(24):40508-40524. doi: 10.1364/OE.502563