Abstract
We experimentally demonstrated a photoelectric nonlinear compensation scheme of optical phase conjugation (OPC) with complex-valued deep neural network (CVDNN) to mitigate fiber nonlinearity in wavelength division multiplexing (WDM) 64-QAM coherent optical transmission system. The factors to affect the performance of OPC and CVDNN are comprehensively considered. OPC in WDM system is experimentally optimized to alleviate the deployment requirements of strict symmetrical distributed power and chromatic dispersion. The performance penalty caused by the simplification of the OPC is further compensated by the CVDNN. The selections of the input neurons’ number and the optimization algorithm are also considered to design a simple two-hidden-layer-structure CVDNN. The proposed method is experimentally verified and evaluated in a 12.5-GBd 4-channel WDM 64-QAM 160-km standard single-mode fiber (SSMF) transmission system with channel spacing of 50-GHz. The experimental results show that the proposed nonlinear equalizer based on the OPC with CDVNN has a strong robustness to the input signal power and wavelength, which can not only improve the Q factor of the signal by 1.5-dB, but also greatly increase the total launched signal power.
Highlights
THE capacity crunch has been exacerbated by the demand for real-time data with high bandwidth and high connectivity [1]
In long distance and high bandwidth backbone optical networks, the nonlinearity mainly comes from the fiber nonlinearity caused by Kerr effects in the form of self-phase modulation (SPM), cross-phase modulation (XPM), four-wave mixing (FWM), the crosstalk between them and amplified spontaneous emission (ASE) noise of Erbium-doped fiber amplifiers (EDFAs) employed in the system, which degrades the signal in the fiber transmission [6,7]
Various digital nonlinear compensation (NLC) methods based on the digital signal processing (DSP) of digital coherent receivers have been proposed to surpass the nonlinear Shannon limit such as digital back-propagation (DBP) [8], Volterra series based nonlinear equalizer (VNLE) [9] and nonlinear symbol decision based on machine learning (ML), i.e., Kmeans [10], support vector machine (SVM) [11] and neural networks (NNs) [12,13]
Summary
THE capacity crunch has been exacerbated by the demand for real-time data with high bandwidth and high connectivity [1]. The high-performance OPC usually requires the strict symmetric power and chromatic dispersion (CD) profile between the two optical links because the mid-link OPC conjugates the optical field of the signals at the mid-point of the transmission link to obtain the idlers [24] Such a requirement is quite challenging in the practical fiber transmission system, which increases the complexity of deployment. In the back-to-back (BTB) WDM wavelength conversion system, high-quality idlers at low pump power are obtained by adjusting the input total power of WDM signals to achieve the optimized OPC, where the power and CD profiles of the fiber links are not symmetrically distributed It can simplify the deployment requirements, the performance of compensation is limited.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
