We develop and test several machine-learning methods to perform detection and identification of equipment failures in optical networks. Results, obtained over real BER traces, show above 98% accuracy in most cases with reasonable algorithm complexity.
Machine-learning-based soft-failure detection and identification in optical networks
SHAHKARAMI, SHAHIN;Musumeci, Francesco;Tornatore, Massimo
2018-01-01
Abstract
We develop and test several machine-learning methods to perform detection and identification of equipment failures in optical networks. Results, obtained over real BER traces, show above 98% accuracy in most cases with reasonable algorithm complexity.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
ml_OFC2018_v08.pdf
accesso aperto
:
Pre-Print (o Pre-Refereeing)
Dimensione
202.72 kB
Formato
Adobe PDF
|
202.72 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
