光学学报, 2018, 38 (9): 0906002, 网络出版: 2019-05-09
基于广义回归神经网络的CO-OFDM系统非线性均衡 
下载： 1165次
Nonlinear Equalizer Based on General Regression Neural Network in Coherent Optical OFDM System
图 & 表
图 1. QAM CO-OFDM系统中GRNN-NLE结构图
Fig. 1. Architecture of the proposed GRNN-NLE for QAM CO-OFDM system
图 3. (a) 16QAM和 (b) 32QAM CO-OFDM系统在不同线宽下,GRNN-NLE的Q因子随平滑因子σo变化时的关系曲线; (c)不同目标误差rg下,BPNN-NLE的Q因子随激光器线宽的变化时的关系曲线
Fig. 3. Q factor versus σo in CO-OFDM system with (a) 16QAM and (b) 32QAM at different laser linewidths; (c) Q factor versus laser linewidth in the CO-OFDM system with different errors rg of objective function
图 4. (a)没有非线性均衡(W/O NLE)以及用BPNN-NLE和GRNN-NLE得到的系统Q因子随激光器线宽的变化曲线; (b)用BPNN-NLE和GRNN-NLE在MATLAB中训练运行时间随激光器线宽变化的关系曲线
Fig. 4. (a) Q factor versus laser linewidth using W/O-NLE, BPNN-NLE and GRNN-NLE; (b) training running time of BPNN-NLE and GRNN-NLE versus laser linewidth
图 5. 对本文仿真的CO-OFDM系统,使用GRNN-NLE(蓝色)与没有非线性均衡(红色)时接收端接收到的32QAM信号星座图。 (a)激光器线宽为0.3 MHz; (b)激光器线宽为0.7 MHz
Fig. 5. For the proposed CO-OFDM system, 32QAM constellation diagrams at the receiver after using GRNN-NLE (blue) and without nonlinear equalizer (red). (a) Laser linewidth ν=0.3 MHz; (b) ν=0.7 MHz
吴金达, 卢瑾, 任宏亮, 覃亚丽, 郭淑琴, 胡卫生. 基于广义回归神经网络的CO-OFDM系统非线性均衡[J]. 光学学报, 2018, 38(9): 0906002. Jinda Wu, Jin Lu, Hongliang Ren, Yali Qin, Shuqin Guo, Weisheng Hu. Nonlinear Equalizer Based on General Regression Neural Network in Coherent Optical OFDM System[J]. Acta Optica Sinica, 2018, 38(9): 0906002.
PDF全文
