Machine Learning-Based, Networking and Computing Infrastructure Resource Management - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2021

Machine Learning-Based, Networking and Computing Infrastructure Resource Management

Abstract

5G mobile networks will be soon available to handle all types of applications and to provide service to massive numbers of users. In this complex and dynamic network ecosystem, end-to-end performance analysis and optimization will be key features in order to effectively manage the diverse requirements imposed by multiple vertical industries over the same shared infrastructure. To enable such a vision, the MARSAL project [1] targets the development and evaluation of a complete framework for the management and orchestration of network resources in 5G and beyond by utilizing a converged optical-wireless network infrastructure in the access and fronthaul/midhaul segments. At the network design domain, MARSAL targets the development of novel cell-free-based solutions. Namely, scalable and cost-efficient wireless access points deployment will be achieved by exploiting the distributed cell-free concept combined with wireless and wired serial fronthaul approaches. We will target the inclusion of these innovative functionalities in the O-RAN project. In parallel, in the fronthaul/midhaul segments MARSAL aims to radically increase the flexibility of optical access architectures for Beyond-5G cell site connectivity via different levels of fixed-mobile convergence. In the network and service management domain, the design philosophy of MARSAL is to provide a comprehensive framework for the management of the entire set of communication and computational network resources by exploiting novel ML-based algorithms of both edge and midhaul data centers, by incorporating the Virtual Elastic Data Centers/Infrastructures paradigm. Finally, at the network security domain, MARSAL aims to introduce mechanisms that provide privacy and security to application workload and data, targeting to allow applications and users to maintain control over their data when relying on the deployed shared infrastructures, while AI and Blockchain technologies will be developed in order to guarantee a secured multi-tenant slicing environment.
Fichier principal
Vignette du fichier
517424_1_En_8_Chapter.pdf (216.43 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03789008 , version 1 (27-09-2022)

Licence

Attribution

Identifiers

Cite

Ioannis P. Chochliouros, Alexandros Kostopoulos, Miquel Payaró, Christos Verikoukis, Sabrina Vimercati, et al.. Machine Learning-Based, Networking and Computing Infrastructure Resource Management. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.85-94, ⟨10.1007/978-3-030-79157-5_8⟩. ⟨hal-03789008⟩
26 View
6 Download

Altmetric

Share

Gmail Facebook X LinkedIn More