Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems
This work addresses signal distortion in optical communications, offering a practical hardware implementation that could enhance data transmission efficiency, though it appears incremental as it builds on existing neural network methods.
The paper tackled the problem of nonlinearity compensation in coherent optical transmission systems by implementing neural network-based equalizers on an FPGA, demonstrating that they outperform a 1 step-per-span digital backpropagation method.
For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1 step-per-span DBP.