We propose a data-driven approach based on Machine Learning (ML) to predict control signals of a photonic switching system. The proposed ML agent is trained and tested in a completely topological and technological agnostic way and we envision its application in real-time control-planes.

A Data-Driven Approach to Autonomous Management of Photonic Switching System / Khan, Ihtesham; Masood, Muhammad Umar; Tunesi, Lorenzo; Ghillino, Enrico; Bardella, Paolo; Carena, Andrea; Curri, Vittorio. - ELETTRONICO. - (2021), pp. 1-2. (Intervento presentato al convegno IEEE Photonics Society Summer Topicals Meeting Series (SUM) tenutosi a Cabo San Lucas, Mexico nel 19-21 July 2021) [10.1109/SUM48717.2021.9505780].

A Data-Driven Approach to Autonomous Management of Photonic Switching System

Khan, Ihtesham;Masood, Muhammad Umar;Tunesi, Lorenzo;Bardella, Paolo;Carena, Andrea;Curri, Vittorio
2021

Abstract

We propose a data-driven approach based on Machine Learning (ML) to predict control signals of a photonic switching system. The proposed ML agent is trained and tested in a completely topological and technological agnostic way and we envision its application in real-time control-planes.
2021
978-1-6654-1600-9
File in questo prodotto:
File Dimensione Formato  
A_Data-Driven_Approach_to_Autonomous_Management_of_Photonic_Switching_System.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 878.28 kB
Formato Adobe PDF
878.28 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
C_IEEE_summer_topicals_A_Data_Driven_Approach_to____V1_02032021.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 599.26 kB
Formato Adobe PDF
599.26 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2917842