MonB5G: AI/ML-Capable Distributed Orchestration and Management Framework for Network Slices

Abstract

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Melding Fog Computing and IoT for Deploying Secure, Response-Capable Healthcare Services in 5G and Beyond

“…In the runtime state, user requests are accommodated by already-allocated resources shaped into a slice. Slicing renders operators capable of providing new services and applications only by activating a fraction of their existing infrastructure instead of rolling out a new network, an approach which reduces capital expenditure and deployment time while simplifying the creation, configuration and operation of network services in general [21][22][23][24][25].…”

In-Slice Management Decomposition and Implementation Issues

“…The distributed approach provides a good separation of concerns and isolation between slices. Presented In [8], [17], the MonB5G approach defines the AIdriven architecture of the overall NS system with ISM. The ISM, called Slice MonbB5G Layer, comprises the Monitoring…”

“…Therefore, the operations related to its deployment and termination will be barely touched only. Moreover, we address single domain operations only, and the presented in [8] approach to multidomain slicing is also applicable in the presented case. However, a single management domain complexity is still very high, and to cope with it; we propose decomposing ISM into a set of Management Services (MS).…”

“…There is, therefore, a need to look for a new that is free from the mentioned in [5] issues. A new approach to network slicing has already been proposed in [6] detailed in [7] and enhanced in [8]. In this concept, called in the paper In-Slice Management (ISM), the NS management becomes part of the NS template and may send orchestration requests.…”

AI-driven Orchestration for 6G Networking: the Hexa-X vision

“…A ML-driven Management and Orchestration (M&O) framework is expected to improve the efficiency of the operations in Sixth-Generation (6G) mobile networks. The potential gains of using AI/ML have been recently addressed in studies such as [1], [2]. AI/ML is also expected to enhance the lifecycle management of Network Functions (NFs), which could be placed anywhere in the network based on performance requirements, resource availability, or load change predictions, among other factors.…”