Meeting 5G high bandwidth rates, ultra-low latencies, and high reliabilities requires of network infrastructures that automatically increase/decrease the resources based on their customers' demand. An autonomous and dynamic management of a 5G network infrastructure represents a challenge, as any solution must account for the radio access network, data plane traffic, wavelength allocation, network slicing, and network functions' orchestration. Furthermore, federation among administrative domains (ADs) must be considered in the network management. Given the increased dynamicity of 5G networks, artificial intelligence/machine learning (AI/ML) solutions are strong candidates able to learn, and take quick provisioning decisions upon fast changes in network conditions. Therefore, this chapter presents an analysis of the state-of-the-art solutions for 5G networks' management, where AI/ML solutions are discussed and compared with traditional methods. Additionally, the chapter provides a technology overview of both standards, and existing solutions regarding the 5G network management, and directions toward the integration of AI/ML in 5G networks.

Self-Managed 5G Networks / Martin-Perez, Jorge; Antevski, Kiril; Guimaraes, Carlos; Bernardos, C. J.; Papagianni, Chrysa; de Vleeschauwe, Danny; Magoula, Lina; Barmpounakis, Sokratis; Kontopoulos, Panagiotis; Koursioumpas, Nikolaos; Sgambelluri, Andrea; Paolucci, Francesco; Valcarenghi, Luca; Garcia-Saavedra, Andres; Li, Xi; Puligheddu, Corrado; Chiasserini, Carla Fabiana; Casetti, CLAUDIO ETTORE; Mangues-Bafalluy, J.; Martínez, J. Baranda R.; Zeydan, Engin - In: Communications Network and Service Management In the Era of Artificial Intelligence and Machine Learning / Zincir-Heywood N., Mellia M., Diao Y.. - STAMPA. - [s.l] : John Wiley & Sons, Inc., 2021. - ISBN 9781119675501. - pp. 69-100 [10.1002/9781119675525.ch4]

Self-Managed 5G Networks

Corrado Puligheddu;Carla Fabiana Chiasserini;Claudio Ettore Casetti;
2021

Abstract

Meeting 5G high bandwidth rates, ultra-low latencies, and high reliabilities requires of network infrastructures that automatically increase/decrease the resources based on their customers' demand. An autonomous and dynamic management of a 5G network infrastructure represents a challenge, as any solution must account for the radio access network, data plane traffic, wavelength allocation, network slicing, and network functions' orchestration. Furthermore, federation among administrative domains (ADs) must be considered in the network management. Given the increased dynamicity of 5G networks, artificial intelligence/machine learning (AI/ML) solutions are strong candidates able to learn, and take quick provisioning decisions upon fast changes in network conditions. Therefore, this chapter presents an analysis of the state-of-the-art solutions for 5G networks' management, where AI/ML solutions are discussed and compared with traditional methods. Additionally, the chapter provides a technology overview of both standards, and existing solutions regarding the 5G network management, and directions toward the integration of AI/ML in 5G networks.
2021
9781119675501
9781119675525
Communications Network and Service Management In the Era of Artificial Intelligence and Machine Learning
File in questo prodotto:
File Dimensione Formato  
IEEE_BookChapter_VNF_Placement_SoTA_.pdf

Open Access dal 04/09/2022

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 205.92 kB
Formato Adobe PDF
205.92 kB Adobe PDF Visualizza/Apri
Chiasserini-Self-managed.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 503.88 kB
Formato Adobe PDF
503.88 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2863452