Share Email Print
cover

Proceedings Paper • new

A new method of using deep neural network to compensate PDL
Author(s): Kan Li; Danshi Wang; Shengchen Li
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We proposed a new method using DNN to compensate the damage caused by PDL. The scenario this experiment used is 16-QAM signals transmitted at 2x28 GBaud rate in a polarization-division multiplexing system. A DNN is proposed to compensate for the damage caused by PDL. The result shows that, BER of the system is reduced to 1e-3, and the damage caused by PDL can be minimized in the polarization multiplexed optical fiber communication system within 600 km.

Paper Details

Date Published: 14 February 2019
PDF: 4 pages
Proc. SPIE 11048, 17th International Conference on Optical Communications and Networks (ICOCN2018), 110481T (14 February 2019); doi: 10.1117/12.2522573
Show Author Affiliations
Kan Li, Beijing Univ. of Posts and Telecommunications (China)
Danshi Wang, Beijing Univ. of Posts and Telecommunications (China)
Shengchen Li, Beijing Univ. of Posts and Telecommunications (China)


Published in SPIE Proceedings Vol. 11048:
17th International Conference on Optical Communications and Networks (ICOCN2018)
Zhaohui Li, Editor(s)

© SPIE. Terms of Use
Back to Top