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.

Multi-access edge computing (MEC) represents an emerging solution to improve the performance of mobile networks by bringing computing resources closer to the edge of the network. However, MEC requires the implementation of virtualization and can be deployed using different hardware platforms, including COTS devices. In this highly heterogeneous scenario, the digital twin (DT), assisted by proper AI/ML solutions, is envisioned to play a crucial role in automated network management, operating as an intermediate and collaborative layer enabling the orchestration layer to better understand network behavior before making changes to the physical network. In this paper, we aim to develop a DT model that captures the behavior of a MEC node supporting services with varying workloads. In pursuit of this objective, we adopt a data-driven methodology that effectively learn a model predicting three critical key performance indicators (KPIs): throughput, computational load, and power consumption. To demonstrate the viability and potential of such approach, a measurement campaign is conducted on MEC nodes deployed with different virtualization environments (bare metal, virtual machine, and containerized), and the results are used to build the DT of each node. Furthermore, machine learning models, including k-nearest neighbors (KNN), support vector regression (SVR), and polynomial fitting (PF), are used to understand the amount of actual measurements required to achieve a suitably low KPI prediction error. The results of this study provide a basis for further research in the field of MEC DT models and carbon footprint-aware orchestration.

The management of a 5G system comprises Operation and Management aspects defined by 3GPP, including Network Slicing, and the Management and Orchestration aspects specified in ETSI’s Network Function Virtualization framework. Our Proof-of-Concept demonstrates the implementation of an on-demand provisioning procedure of a Network Slice Subnet composed of Virtual Network Functions from potentially different vendors. The demonstration includes a Network Management System conforming to the 3GPP Service-Based Management Architecture, an ETSI MANO orchestrator, and a Network Function Virtualization Infrastructure.