Artículo

Enhanced approach for artificial neural network-based optical fiber channel modeling: Geometric constellation shaping WDM system as a case study

Abbass, A. M.; Fyath, R. S.

Instituto de Ciencias Aplicadas y Tecnología, UNAM, publicado en Journal of Applied Research and Technology ( (Revistas UNAM)

Licencia de uso

La titularidad de los derechos patrimoniales de esta obra pertenece a las instituciones editoras. Su uso se rige por una licencia Creative Commons BY-NC-SA 4.0 Internacional, https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode.es, para un uso diferente consultar al responsable jurídico del repositorio por medio del correo electrónico gabriel.ascanio@icat.unam.mx. Ver términos de la licencia

Procedencia del contenido

Cita

Abbass, A. M., et al. (2024). Enhanced approach for artificial neural network-based optical fiber channel modeling: Geometric constellation shaping WDM system as a case study. Journal of Applied Research and Technology; Vol. 22 Núm. 6, 2024; 768-780. Recuperado de https://repositorio.unam.mx/contenidos/4161392

Descripción del recurso

Autor(es)
Abbass, A. M.; Fyath, R. S.
Tipo
Artículo de Investigación
Área del conocimiento
Ingenierías
Título
Enhanced approach for artificial neural network-based optical fiber channel modeling: Geometric constellation shaping WDM system as a case study
Fecha
2024-12-11
Resumen
Recently, there has been increasing interest in applying machine learning (ML) approaches to enhance the performance of optical communication systems. This paper applies some of these approaches to design advanced wavelength-division multiplexed (WDM)-coherent optical fiber communication (OFC) systems assisted by the constellation shaping technique. A theoretical design and performance investigation are reported assuming end-to-end deep learning (E2EDL) autoencoder (AE)-assisted system configuration. A flexible artificial neural network (ANNs)-based optical fiber channel modeling approach suitable for different multi-span transmission links in OFCs is presented. This approach is applied to E2EDL-based geometric constellation shaping WDM systems and the results reveal that using a bi-directional gated recurrent unit (Bi-GRU)-neural network (NN) gives the best modeling that tracks the numerical nonlinear interference noise fiber model with much less computation time(~7%). This work is implemented using the Python programming language and utilizing the TensorFlow framework to develop the simulation models.
Tema
End-to-end deep learning; coherent optical fiber communication; autoencoder; GCS-WDM system; ANN-fiber channel modeling
Idioma
eng
ISSN
ISSN electrónico: 2448-6736; ISSN: 1665-6423
DOI
https://doi.org/10.22201/icat.24486736e.2024.22.6.2490

Enlaces