Experimental demonstration of SPM compensation based on digital signal processing using a three-layer neural-network for 40-Gbit/s optical 16QAM signal

Abstract

We experimentally demonstrated a novel nonlinearity mitigation scheme based on digital signal processing using a three-layer neural network (NN). 40-Gbit/s optical 16QAM signal distorted by SPM was compensated, improving EVM values by about 15%. We also performed numerical simulation of the proposed scheme, and confirmed that the experiment agrees with the results of the simulation. We performed 100 times of learning processes to find weight and bias of each neuron. However, we did not observe any serious local minimum. We also investigated the effect of the number of neurons of the NN on the compensation performance. Keywords: digital signal processing, nonlinear distortion, SPM, neural network Classification: Fiber-Optic Transmission for Communications , vol. 46, no. 16, pp. 1140-1141, Aug. 2010. DOI:10.1049/el.2010.1444 L. Liu, L. Li, Y. Huang, K. Cui, Q. Xiong, and F. N. Hauske, "Intrachannel nonlinearity compensation by inverse volterra series transfer function," J. References

Experimental demonstration of SPM compensation using a complex-valued neural network for 40-Gbit/s optical 16QAM signals

“…In optical communication systems, the nonlinear equalizers based on RVNN have been used in frequency domain for optical orthogonal frequency division multiplexing (OFDM) systems [3,4]. We have proposed a novel nonlinear equalization method using an RVNN to compensate optical multi-level signals distorted by the nonlinearity of optical fibers [5,6,7]. On the other hand, complex-valued neural networks (CVNNs) are being investigated in the field of machine learning as a scheme that can accelerate the learning process compared with RVNNs [8,9].…”

Size of an artificial neural-network for simultaneous compensation of linear and nonlinear optical waveform distortion

“…Recently, ANNbased frequency-domain digital signal processing was used for compensating for nonlinearity in optical fiber transmission [7,8]. We proposed a novel nonlinear compensation method using a time-domain ANN to compensate optical multi-level signals distorted by SPM and XPM [9,10,11]. In this ANN based processing, the number of neurons was decided empirically or by trial and error.…”

“…where η is the learning rate. The waveform distortions caused by SPM and dispersion were simultaneously compensated for by one ANN [10]. Here, we explain how the neurons work to compensate the linear and nonlinear distortion.…”

Polarization demultiplexing and optical nonlinearity compensation based on artificial neural networks

“…However, one drawback is the enormous amount of calculations required, which causes time delays and increases the power consumption at the receiver. Artificial neural networks (ANNs) have been investigated as another candidate which can realize digital nonlinear equalizers to compensate for optical nonlinear effects [5,6,7,8]. One important merit of using an ANN is its ability to decrease the computational complexity of the nonlinear equalizer [9].…”