Journal
JOURNAL OF LIGHTWAVE TECHNOLOGY
Volume 39, Issue 19, Pages 6085-6096Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JLT.2021.3096286
Keywords
Artificial neural networks; Equalizers; Computer architecture; Logic gates; Computational complexity; Nonlinear optics; Convolution; Neural network; nonlinear equalizer; computational complexity; Bayesian optimizer; coherent detection; optical communications; digital signal processing
Funding
- EU Horizon 2020 program under the Marie Sklodowska-Curie Grant [813144]
- SMARTNET EMJMD programme [586686-EPP-1-2017-1-U.K.-EPPKA1-JMDMOB]
- Leverhulme Trust [RP-2018-063]
- EPSRC project TRANSNET
Ask authors/readers for more resources
The study compared the performance and complexity of different artificial neural networks for nonlinear channel equalization in coherent optical communication systems. The CNN+biLSTM architecture showed the largest Q-factor improvement and was the best option when computational complexity was not constrained. However, when complexity was restricted to lower levels, the three-layer perceptron performed best.
We present the results of the comparative performance-versus-complexity analysis for the several types of artificial neural networks (NNs) used for nonlinear channel equalization in coherent optical communication systems. The comparison is carried out using an experimental set-up with the transmission dominated by the Kerr nonlinearity and component imperfections. For the first time, we investigate the application to the channel equalization of the convolution layer (CNN) in combination with a bidirectional long short-term memory (biLSTM) layer and the design combining CNN with a multi-layer perceptron. Their performance is compared with the one delivered by the previously proposed NN-based equalizers: one biLSTM layer, three-dense-layer perceptron, and the echo state network. Importantly, all architectures have been initially optimized by a Bayesian optimizer. First, we present the general expressions for the computational complexity associated with each NN type; these are given in terms of real multiplications per symbol. We demonstrate that in the experimental system considered, the convolutional layer coupled with the biLSTM (CNN+biLSTM) provides the largest Q-factor improvement compared to the reference linear chromatic dispersion compensation (2.9 dB improvement). Then, we examine the trade-off between the computational complexity and performance of all equalizers and demonstrate that the CNN+biLSTM is the best option when the computational complexity is not constrained, while when we restrict the complexity to some lower levels, the three-layer perceptron provides the best performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available