Abstract
We investigate the robustness of our spectral data driven machine learning based QoT estimator by artificially noising the input features. The estimator shows superior robustness against feature changes compared to a non-spectral estimator. We validate its generalization ability and robustness on an unseen experimental dataset.
© 2022 The Author(s)
PDF ArticleMore Like This
Lars E. Kruse, Sebastian Kühl, and Stephan Pachnicke
Th1C.1 Optical Fiber Communication Conference (OFC) 2022
Omran Ayoub, Andrea Bianco, Davide Andreoletti, Sebastian Troia, Silvia Giordano, and Cristina Rottondi
M3F.5 Optical Fiber Communication Conference (OFC) 2022
Giacomo Borraccini, Stefano Straullu, Alessio Giorgetti, Rocco D’Ingillo, Davide Scano, Andrea D’Amico, Emanuele Virgillito, Antonino Nespola, Nicola Sambo, Filippo Cugini, and Vittorio Curri
M4F.5 Optical Fiber Communication Conference (OFC) 2022