Machine learning for long-haul optical systems
Kapitel i bok, 2022

In this chapter, machine learning (ML) algorithm is introduced in single-step perturbation and multi-step digital back-propagation methods to compensate for intra-channel fiber nonlinearity. A wide & deep neural network is first introduced to use intra-channel cross-phase modulation and intra-channel four-wave mixing triplets as input features to predict the fiber nonlinearity at symbol rate. In the second part, a parameterized physics-based ML model is reviewed by emulating linear dispersion step as the weight matrices in a neural network and nonlinear phase shift as element-wise nonlinearities in the activation functions. The chapter concludes by a short summary outlook of ML in long-haul systems.

Deep neural network

Nonlinearity compensation

Learned digital backpropagation

Model-based neural network

Perturbation triplets

Författare

Shaoliang Zhang

Acacia Communications Inc.

Christian Häger

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

Machine Learning for Future Fiber-Optic Communication Systems

43-64
9780323852272 (ISBN)

Ämneskategorier

Telekommunikation

Reglerteknik

Signalbehandling

DOI

10.1016/B978-0-32-385227-2.00009-7

Mer information

Senast uppdaterat

2023-10-27