Application of Transformers for Nonlinear Channel Compensation in Optical Systems
This work addresses nonlinear distortion in long-haul optical transmission, offering a data-driven solution that is incremental in applying Transformers to this domain.
The paper tackles nonlinear channel compensation in optical systems by introducing a Transformer-based equalizer, achieving efficient nonlinear equalization with reduced computational complexity through a physics-informed mask and showing flexibility compared to digital back-propagation.
In this paper, we introduce a new nonlinear optical channel equalizer based on Transformers. By leveraging parallel computation and attending directly to the memory across a sequence of symbols, we show that Transformers can be used effectively for nonlinear compensation (NLC) in coherent long-haul transmission systems. For this application, we present an implementation of the encoder part of the Transformer and analyze its performance over a wide range of different hyper-parameters. It is shown that by proper embeddings and processing blocks of symbols at each iteration and also carefully selecting subsets of the encoder's output to be processed together, an efficient nonlinear equalization can be achieved for different complexity constraints. To reduce the computational complexity of the attention mechanism, we further propose the use of a physic-informed mask inspired by nonlinear perturbation theory. We also compare the Transformer-NLC with digital back-propagation (DBP) under different transmission scenarios in order to demonstrate the flexibility and generalizability of the proposed data-driven solution.