Nonlinear equalization method based on Gaussian mixture model clustering algorithm for a coherent optical OFDM communication system

Tian Wang; Qinghua Tian; Qi Zhang; Yongjun Wang; Feng Tian; Xishuo Wang; Leijing Yang; Yunxiao Zu; Xiangjun Xin

doi:10.1117/12.2580152

5 November 2020 Nonlinear equalization method based on Gaussian mixture model clustering algorithm for a coherent optical OFDM communication system

Tian Wang, Qinghua Tian, Qi Zhang, Yongjun Wang, Feng Tian, Xishuo Wang, Leijing Yang, Yunxiao Zu, Xiangjun Xin

Author Affiliations +

Proceedings Volume 11569, AOPC 2020: Optical Information and Network; 115690K (2020) https://doi.org/10.1117/12.2580152
Event: Applied Optics and Photonics China (AOPC 2020), 2020, Beijing, China

Abstract

In this paper, an unsupervised clustering algorithm based on the Gaussian Mixture Model (UCGMM algorithm) for the coherent optical OFDM communication system is proposed to determine the constellation diagram. The purpose of nonlinear equalization of communication systems is achieved. In a back to back transmission system, compared to the Kmeans algorithm and the without any clustering algorithm, the UCGMM algorithm can obtain gains of approximately 0.6dB and 2dB respectively. For the cases of simulation in optical fiber transmission, the transmission distance of UCGMM algorithm is extended by 45km relative to the K-means algorithm, and 75km relative to without any clustering algorithm. In both cases, the effectiveness of the proposed UCGMM algorithm in nonlinear equilibrium is proved.

Citation Download Citation

Tian Wang, Qinghua Tian, Qi Zhang, Yongjun Wang, Feng Tian, Xishuo Wang, Leijing Yang, Yunxiao Zu, and Xiangjun Xin "Nonlinear equalization method based on Gaussian mixture model clustering algorithm for a coherent optical OFDM communication system", Proc. SPIE 11569, AOPC 2020: Optical Information and Network, 115690K (5 November 2020); https://doi.org/10.1117/12.2580152

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available