eduzhai > Applied Sciences > Engineering >

Deep-learning Autoencoder for Coherent and Nonlinear Optical Communication

  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: Motivated by the recent success of end-to-end training of communications inthe wireless domain, we strive to adapt the end-to-end-learning idea from thewireless case (i.e., linear) to coherent optical fiber links (i.e., nonlinear).Although, at first glance, it sounds like a straightforward extension, it turnsout that several pitfalls exist - in terms of theory but also in terms ofpractical implementation. This paper analyzes the potential of an autoencoderand limitations for the optical fiber under the influence of Kerr-nonlinearityand chromatic dispersion. As there is no exact capacity limit known and, hence,no analytical perfect system solution available, we set great value to theinterpretability on the learnings of the autoencoder. Therefore, we design itsarchitecture to be as close as possible to the structure of a classiccommunication system, knowing that this may limit its degree of freedom and,thus, its performance. Nevertheless, we were able to achieve an unexpected highgain in terms of spectral efficiency compared to a conventional referencesystem.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×