The Learning of Centralised and Federated approaches for Predictive VNF Autoscaling in 5G networks
Updated: Feb 6
Recent paper – ‘Centralized and Federated Learning for Predictive VNF Autoscaling in Multi-domain 5G Networks and Beyond,’ describes how two technologies in ‘Network Function Virtualisation (NFV) and Multi-access Edge Computing (MEC) are expected to play a vital role in 5g and beyond networks.
Particularly in multi-domain scenarios, the additional challenge of isolation and data privacy among domains needs to be tackled. To this end, centralized and distributed Artificial Intelligence (AI)-driven resource orchestration techniques (e.g., virtual network function (VNF) autoscaling) are foreseen as the main enabler.
In this article, deep learning models, both centralized and federated approaches, that can perform horizontal and vertical autoscaling in multi-domain networks are proposed. The performance of various deep learning models trained over a commercial network operator dataset are evaluated and the pros and cons of federated learning over centralized learning approaches are investigated.
Find out more here: https://ieeexplore.ieee.org/document/9319704/keywords#keywords