Fiber nonlinearity-induced penalty reduction in CO-OFDM by ANN-based nonlinear equalization
Fiber nonlinearity-induced penalty reduction in CO-OFDM by ANN-based nonlinear equalization
复制标题
DOI：
10.1364/ol.40.005113
复制
发表时间：
2015-11-01
期刊：
影响因子：
3.6
通讯作者：
Eggleton, Benjamin J.
中科院分区：
文献类型：
--
作者：
Giacoumidis, Elias;Le, Son T.;Eggleton, Benjamin J.
我们的实验表明，类似于2 dB的质量（Q）因子的提高方面的光纤非线性补偿40 Gb/s的16正交幅度调制相干光正交频分复用在2000公里，使用非线性均衡器（NLE）基于人工神经网络（ANN）。非线性缓解取决于ANN训练开销和信号比特率的升级，报告类似于在70 Gb/s的4 dB Q因子增强，而ANN神经元数量的减少会消除NLE性能。与逆Volterra级数传递函数NLE相比，其Q因子的性能提高了约2 dB，这使得ANN在效率上取得了突破。（C）2015年美国光学学会
We experimentally demonstrate similar to 2 dB quality (Q)-factor enhancement in terms of fiber nonlinearity compensation of 40 Gb/s 16 quadrature amplitude modulation coherent optical orthogonal frequency-division multiplexing at 2000 km, using a nonlinear equalizer (NLE) based on artificial neural networks (ANN). Nonlinearity alleviation depends on escalation of the ANN training overhead and the signal bit rate, reporting similar to 4 dB Q-factor enhancement at 70 Gb/s, whereas a reduction of the number of ANN neurons annihilates the NLE performance. An enhanced performance by up to similar to 2 dB in Q-factor compared to the inverse Volterra-series transfer function NLE leads to a breakthrough in the efficiency of ANN. (C) 2015 Optical Society of America