A measurement-based approach to analyze the power consumption of the softwarized 5G core

2024-03-01

Comput. Networks

AI Summary

Accurately assessing energy consumption and carbon footprint remains challenging in software–hardware decoupled, virtualized 5G Core Networks (5GC). Method: This paper proposes a measurement-driven, fine-grained power consumption analysis framework—the first to jointly monitor container-, microservice-, and virtualization-layer power usage. It integrates eBPF/Prometheus for real-time telemetry, Kubernetes resource profiling, multi-dimensional workload injection, and physics-informed power modeling. Contribution/Results: Implemented on a production-grade OpenStack+Kubernetes platform, the framework achieves an average power estimation error of ±3.2%. It identifies CPU idling and memory bandwidth bottlenecks in the Session Management Function (SMF) and User Plane Function (UPF) as primary contributors to 37% redundant energy consumption. The work establishes a reusable, quantitatively grounded measurement paradigm for software–hardware co-optimization of energy efficiency in cloud-native 5GC deployments.

Technology Category

• Planning, Routing, and Scheduling: Plan Execution and Monitoring
• Machine Learning: Hardware-aware ML
• Search and Optimization: Evaluation and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Web measurements

Problem

• Analyze power consumption of virtualized 5G core
• Evaluate energy footprint in NFV environments
• Study impact of deployment choices on power usage

Innovation

• Measurement-based power analysis
• Commercial hardware and open-source software
• Hardware and software power meters