ML-Based Strategies to Optimize O-RAN VNFs for Latency and Reliability
Bibliographic record
Abstract
The Open Radio Access Network (O-RAN) combines the benefits of virtualization and Machine Learning (ML) to enhance Radio Access Networks (RANs), providing advanced automation, self-organization, and closed-loop optimization across the RAN architecture. This approach efficiently manages the sharply rising network traffic in RANs and introduces open interfaces that enable the virtual hosting of its components on the O-Cloud, as well as hosting ML training and inference modules. This transition to a virtualized environment and an ML-supportive architecture paves the way for applying advanced ML-assisted solutions to dynamically optimize, oversee, and monitor the O-RAN. In this study, we begin by offering a straightforward overview of how to implement an ML pipeline in O-RAN. Next, we explore latency and reliability challenges in two O-RAN deployment use cases, suggesting ML-assisted solutions for each. Lastly, we detail our implementation of a deep reinforcement learning solution to boost O-RAN's availability by optimizing the placement of its units. Our proposed solution showcases the effectiveness of ML-assisted solutions by maximizing the availability of a large-scale Critical Internet of Things O-RAN deployment in a reasonable time frame.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 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) | 0.003 | 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".