Combatting nonlinear phase noise in coherent optical systems with an optimized decision processor based on machine learning
详细信息 查看全文
- 作者：Danshi Wang ; wang_danshi@163.com" class="auth_mail" title="E-mail the corresponding author ; Min Zhang ; mzhang@bupt.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Zhongle Cai ; Yue Cui ; Ze Li ; Huanhuan Han ; Meixia Fu ; Bin Luo
- 关键词：Digital signal processing ; Machine learning ; Fiber nonlinearity ; Coherent detection
- 刊名：Optics Communications
- 出版年：2016
- 出版时间：15 June 2016
- 年：2016
- 卷：369
- 期：Complete
- 页码：199-208
- 全文大小：3942 K
文摘
- •
An effective machine learning algorithm, SVM, is presented to mitigate the NLPN.
- •
Compared with conventional method, the larger launch power and longer distance are achieved.
- •
One parameter optimization scheme is proposed for the 16QAM-based system.
- •
SVM is also effective in combating the laser phase noise combined with I/Q imbalance.
- •
The relatively low complexity makes it possible for SVM to implement the real-time processing.