Autoencoder-Optimized Geometric Constellation Shaping for Unamplified Coherent Optical Links
Beatriz M. Oliveira, M. S. Neves, Fernando P. Guiomar, Maria C. R. Medeiros, Paulo P. Monteiro · Conference on Lasers and Electro-Optics · 2022
Using end-to-end deep learning, we experimentally demonstrate the optimized design of geometric constellation shaping for coherent unamplified links. A power budget gain of more than 2 dB is demonstrated for 8-ary constellations.