Directives for Function Offloading in 5G Networks Based on a Performance Characteristics Analysis

2025-08-05

AI Summary

The performance characteristics of vehicular functional cloud offloading over non-standalone (NSA) 5G networks remain poorly understood. Method: We deployed emotion and object recognition AI algorithms in real-world road environments to systematically evaluate latency, round-trip time (RTT), and packet transmission efficiency. Leveraging empirically measured NSA-5G performance metrics, we formulated a function offloading decision criterion. We implemented containerized microservices orchestrated via Kubernetes to conduct comparative experiments across centralized cloud and cloud-edge architectures. Contribution/Results: We identify RTT ≥ 150 ms as the critical feasibility threshold for cloud offloading—first reported in this context. Field measurements demonstrate an average signal quality of 84%, packet loss rate < 0.1%, and zero service interruptions throughout testing. These results empirically validate the engineering feasibility of stable, low-latency cloud offloading over NSA-5G networks across diverse vehicular scenarios.

Technology Category

• Application Domains: Mobility, Driving & Flight
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Evaluation and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Cloud-based offloading helps address energy consumption and performance challenges in executing resource-intensive vehicle algorithms. Utilizing 5G, with its low latency and high bandwidth, enables seamless vehicle-to-cloud integration. Currently, only non-standalone 5G is publicly available, and real-world applications remain underexplored compared to theoretical studies. This paper evaluates 5G non-standalone networks for cloud execution of vehicle functions, focusing on latency, Round Trip Time, and packet delivery. Tests used two AI-based algorithms -- emotion recognition and object recognition -- along an 8.8 km route in Baden-Württemberg, Germany, encompassing urban, rural, and forested areas. Two platforms were analyzed: a cloudlet in Frankfurt and a cloud in Mannheim, employing various deployment strategies like conventional applications and containerized and container-orchestrated setups. Key findings highlight an average signal quality of 84 %, with no connectivity interruptions despite minor drops in built-up areas. Packet analysis revealed a Packet Error Rate below 0.1 % for both algorithms. Transfer times varied significantly depending on the geographical location and the backend servers' network connections, while processing times were mainly influenced by the computation hardware in use. Additionally, cloud offloading seems only be a suitable option, when a round trip time of more than 150 ms is possible.

Problem

• Evaluates 5G non-standalone networks for vehicle cloud offloading
• Analyzes latency and packet delivery in real-world 5G scenarios
• Assesses cloud offloading feasibility based on round trip time

Innovation

• Cloud-based offloading for vehicle algorithms
• 5G enables seamless vehicle-to-cloud integration
• Tested AI algorithms in diverse environments