Anti-mode-coupling few-mode signal complex format analysis method and device

Abstract

The invention discloses an anti-mode-coupling few-mode signal complex format analysis method and device, and aims to solve the problems of poor modulation format identification effect and high training cost of an elastic optical network based on few-mode optical fibers; a wavelength division multiplexing technology is taken as a source domain and a mode division multiplexing technology is taken as a target domain through a domain self-adaption theory. The stimulated Raman scattering effect is analogous to the mode coupling effect, so that the neural network learns the law of energy migration. Compared with a retrained network model, the method can realize modulation format identification of the few-mode signal only by using a small amount of few-mode data, significantly reduces the training cost of the neural network, accelerates the convergence rate of the network model, and reduces the model training time and calculation complexity. Meanwhile, by means of the theoretical advantages of transfer learning, the network has better generalization ability and recognition performance, can adapt to the influence of mode coupling in the few-mode optical fiber on the modulation format, and achieves the modulation format recognition task of the few-mode optical network.

Description

technical field [0001] The invention belongs to the technical field of optical communication, and in particular relates to an anti-mode coupling few-mode signal complex format analysis method and device. Background technique [0002] In recent years, the rapid development of information technology and data applications has brought many new challenges and limitations to optical transmission networks based on single-mode fibers. In order to meet the growing bandwidth demands of data centers, cloud services, 5G, Internet of Things, virtual reality and other emerging services, the existing optical fiber communication system urgently needs an effective expansion method. At present, most physical dimensions of light waves such as amplitude, phase, time slot, and polarization in single-mode fiber systems have been utilized to a large extent. In order to improve the spectral efficiency of the signal, some high-order modulation formats have also been proposed. However, limited by t...

AI Technical Summary

Problems solved by technology

However, the neural network has many parameters, and the training and learning process is relatively long. If the optimization method is improper, it is easy to fall into the local optimum.

Moreover, these algorithms do not take into account the identification of signal modulation formats based on few-mode fibers, because there are multiple transmission modes in few-mode fibers

Once the channel parameters are changed, the neural network based on the deep learning method needs to be retrained in order to obtain a more ideal recognition performance, which greatly increases the training cost and training time.

At the same time, compared with single-mode fiber, there are inherent link damages such as mode coupling in few-mode fiber. These link damages will reduce the accuracy of modulation format identification, and then affect the monitoring performance of the optical performance monitoring system.

Images