Empirical Benchmarking of a Low-Latency Cloud-Native Testbed for High-Complexity AI-Enabled Network Functions in B5G Edge
Bibliographic record
Abstract
Software-defined networking (SDN) architectures in edge networks often face limitations due to centralized bottlenecks and rigid Northbound Interfaces (NBIs), hindering scalability and responsiveness. This paper proposes a cloud-native framework that enables decentralized agent communications with machine learning servers for real-time, context-aware clustering of user equipment (UE) at the edge. This facilitates dynamic assignment of service-level priorities for downstream tasks. The framework utilizes cloud-native network functions (CNFs) to deploy edge-native modules that trigger classification services based on contextual metadata. Further, the approach utilizes service mesh technologies to support decentralized agent-model interactions, and Redis publish/subscribe (Pub/Sub) patterns enable event-driven updates without polling or traditional APIs. The architecture reduces latency, minimizes control overhead, and enhances adaptability in multi-slice environments. By integrating graph autoencoders into edge microservices, agents can respond to dynamic user behavior and environmental changes with minimal reliance on centralized controllers. Experimental results show up to 60% reduction in end-to-end response time and 35% reduction in CPU overhead, demonstrating the efficiency of the proposed approach. This work contributes to the development of scalable, intelligent edge networks for beyond 5G (B5G) systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".