BOLT: A Bayesian Online Learning Framework for Time Sensitive Networks in Metaverse
Bibliographic record
Abstract
Efficient load balancing in wireless networks is a critical challenge that directly impacts resource utilization and user experience for time-sensitive networks in the Metaverse. This paper addresses this challenge by proposing a Bayesian online learning approach, enhanced by Software-Defined Networking (SDN) principles and the OpenFlow API. The objective is to dynamically optimize traffic distribution across multiple access points (APs) in wireless networks using real-time observations. The proposed solution integrates SDN concepts and leverages the OpenFlow API to enable centralized control and dynamic configuration of network elements. By employing Bayesian online learning, the load-balancing policy is continuously updated based on real-time observations and historical data. This approach minimizes total load imbalance across APs, accounting for uncertainties inherent in network dynamics. The Bayesian online learning framework incorporates proba-bilistic models to capture load fluctuations and estimation errors. By utilizing historical data and observed network behavior, the model refines its load-balancing decisions over time. MATLAB is utilized for simulations, demonstrating the effectiveness of the proposed approach in achieving load-balancing objectives for time-sensitive networks in the Metaverse. The results underscore the adaptability and robustness of the system in managing load variations while leveraging the power of SDN and Bayesian learning.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 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".