Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

6G Infrastructures for Edge AI: An Analytical Perspective

Kurt Horvath, Shpresa Tuda, Blerta Idrizi, Stojan Kitanov, Fisnik Doko, Dragi Kimovski

TL;DR

The paper addresses the gap between AI-driven edge applications and current 5G performance by analyzing 6G network characteristics and conducting a real-world latency evaluation in central Europe. It demonstrates RTLs of $61$–$110 \mathrm{ms}$ in 5G, corresponding to about $270\%$ of latency targets, underscoring routing and edge integration inefficiencies. To bridge this gap, it proposes three actionable strategies—local peering optimization, User Plane Function (UPF) integration, and control plane functionality enhancements—along with an edge-aware Open RAN/Near-RT RIC framework and network slicing to enable scalable, low-latency AI at the edge. The work offers a practical roadmap for transitioning toward 6G-enabled edge AI, guiding deployment choices and future research to achieve sub-millisecond edge latency and terabit-capable networks.

Abstract

The convergence of Artificial Intelligence (AI) and the Internet of Things has accelerated the development of distributed, network-sensitive applications, necessitating ultra-low latency, high throughput, and real-time processing capabilities. While 5G networks represent a significant technological milestone, their ability to support AI-driven edge applications remains constrained by performance gaps observed in real-world deployments. This paper addresses these limitations and highlights critical advancements needed to realize a robust and scalable 6G ecosystem optimized for AI applications. Furthermore, we conduct an empirical evaluation of 5G network infrastructure in central Europe, with latency measurements ranging from 61 ms to 110 ms across different close geographical areas. These values exceed the requirements of latency-critical AI applications by approximately 270%, revealing significant shortcomings in current deployments. Building on these findings, we propose a set of recommendations to bridge the gap between existing 5G performance and the requirements of next-generation AI applications.

6G Infrastructures for Edge AI: An Analytical Perspective

TL;DR

The paper addresses the gap between AI-driven edge applications and current 5G performance by analyzing 6G network characteristics and conducting a real-world latency evaluation in central Europe. It demonstrates RTLs of – in 5G, corresponding to about of latency targets, underscoring routing and edge integration inefficiencies. To bridge this gap, it proposes three actionable strategies—local peering optimization, User Plane Function (UPF) integration, and control plane functionality enhancements—along with an edge-aware Open RAN/Near-RT RIC framework and network slicing to enable scalable, low-latency AI at the edge. The work offers a practical roadmap for transitioning toward 6G-enabled edge AI, guiding deployment choices and future research to achieve sub-millisecond edge latency and terabit-capable networks.

Abstract

The convergence of Artificial Intelligence (AI) and the Internet of Things has accelerated the development of distributed, network-sensitive applications, necessitating ultra-low latency, high throughput, and real-time processing capabilities. While 5G networks represent a significant technological milestone, their ability to support AI-driven edge applications remains constrained by performance gaps observed in real-world deployments. This paper addresses these limitations and highlights critical advancements needed to realize a robust and scalable 6G ecosystem optimized for AI applications. Furthermore, we conduct an empirical evaluation of 5G network infrastructure in central Europe, with latency measurements ranging from 61 ms to 110 ms across different close geographical areas. These values exceed the requirements of latency-critical AI applications by approximately 270%, revealing significant shortcomings in current deployments. Building on these findings, we propose a set of recommendations to bridge the gap between existing 5G performance and the requirements of next-generation AI applications.

Paper Structure

This paper contains 18 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. 6G Network Infrastructure Characteristics
  3. Communication latency
  4. Network capacity
  5. Network scalability
  6. Application Requirements
  7. Communication requirements
  8. Bandwidth Requirements
  9. Scalability requirements
  10. Current Infrastructure Evaluation
  11. Use-case application
  12. Testbed and scenario
  13. Evaluation results
  14. 6G Infrastructure Recommendations for Edge AI
  15. Local Peering Optimization
  16. ...and 3 more sections

Figures (4)

  • Figure 1: Mobile evaluation scenario using grid segmentation
  • Figure 2: Urban Mean Round-trip Time Latency
  • Figure 3: Standard Deviation Latency
  • Figure 4: Data Trace of Local Service Request