ALAP: Availability- and Latency-Aware Protection for O-RAN: A Deep <i>Q</i>-Learning Approach
Bibliographic record
Abstract
Ultra-Reliable Low Latency Communications (URLLC) is a critical use case in 5G and B5G networks enabling applications such as Augmented Reality (AR)-assisted surgery, vehicle-to-everything communications, and smart grids to consistently deliver the promised Quality of Service to the end-users. The intelligence of the 5G core has made such applications possible, and the O-Radio Access Network (O-RAN) has extended this intelligence to Radio Access Networks (RANs) through its openness, cloudification, and ability to host machine learning models at every layer. However, the cloudification of O-RAN introduces challenges, such as securing availability and ensuring latency for URLLC. In this work, we propose an Availability- and Latency-Aware O-RAN Virtual Network Function (VNF) Protection (ALAP) solution. ALAP offers a shared VNF protection scheme based on deep Q-learning, efficiently providing this protection while minimizing the number of VNF backup components compared to dedicated protection schemes. Our solution protects against resource blockages and alleviates operational costs for network service providers. In addition to these objectives, ALAP ensures that the network meets URLLC’s strict availability and end-to-end latency constraints. ALAP has shown promising results in how quickly it can learn to optimize these objectives and in its capability to achieve its goals on large-scale O-RAN deployments.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".