A Preliminary Study on the Power Consumption of Virtualized Edge 5G Core Networks

Abstract

Other than pure performance and cybersecurity, a value that is becoming increasingly important for a mobile network is its power consumption. In fact, the transition from legacy network deployments tightly coupled with the underlying hardware towards fully virtualized ones yields distinct options based on the adopted virtualization technology, each of which deserve appropriate evaluation in terms of energy efficiency. In this paper, we aim at providing a preliminary assessment of the realistic power consumption of a fifth-generation core network deployed in a network edge environment leveraging bare metal, containers, and virtual machines. The results are based on a testbed consisting of commercial off-the-shelf hardware and open-source software, and show that the deployment based on virtual machines is the first one that saturates the power consumption, thus reducing the maximum achievable throughput. These preliminary insights show the feasibility of a real-time power monitoring system that can condition the dynamic policies applied by the 5G network orchestrator.