MARSAL
Machine learning-based, networking and computing infrastructure resource
management of 5G and beyond intelligent networks
(01/2021 – 12/2023)
Aim: The development and evaluation of a complete framework for the management and orchestration of network resources in 5G and beyond.
MARSAL targets the development and evaluation of a complete framework for the management and orchestration of network resources in 5G and beyond, by utilising a converged optical-wireless network infrastructure in the access and fronthaul/midhaul segments.
MARSAL proposes a new paradigm of elastic virtual infrastructures that integrate – in a transparent manner – a variety of novel radio access, networking, management and security technologies, which will be developed to deliver end-to-end transfer, processing and storage services in an efficient and secured way. MARSAL focuses on three pillars to enable a new generation of ultra-dense, cost-efficient, flexible and secure networks, that is: network design pillar, virtual elastic infrastructure pillar, and network security pillar.
For the network design pillar, MARSAL pushes cell-free networking towards the distributed processing cell-free concept, and enables wireless mmWave solutions, which will be implemented and integrated with existing vRAN elements, while being in-line with the O-RAN Alliance. 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.
MARSAL’s second pillar is built based on the Elastic Edge Computing notion, targeting to optimize the functionality of the Mobile Edge Computing (MEC) and the network slicing management systems via a hierarchy of analytic and decision engines. The aim is to provide a comprehensive framework for the management of the entire set of communication and computational network resources.
Under its third pillar, MARSAL will develop novel Machine Learning (ML) based mechanisms that guarantee privacy and security in multi-tenancy environments, targeting both end-users and tenants. This will allow applications and users to maintain control over their data when relying on the deployed shared infrastructures, while AI (Artificial Intelligence) and Blockchain technologies will be developed, to guarantee a secured multi-tenant slicing environment.
For more information you may visit the project website: https://www.marsalproject.eu/
