Work in Progress: Congestion Control in mmWave Fluctuating Scenarios in 5G-A/6G
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The development of the next generation of cellular networks, 5G-Advanced and 6G (5G-A/6G), offers higher speeds, sub-millisecond latency, and providing wider coverage, which are key to meeting the requirements of new and demanding applications. As such, there are several challenges in managing and leveraging this opportunity to ensure that channel conditions do not impact the application due to mobility and obstructions. 5G introduces the use of millimeter wave (mmWave), and the commercial deployment of this technology brings to light the issues related to propagation and mobility in high-frequency bands, and their impact on applications has begun to be studied by exploring the response of the congestion control algorithms (CCAs) in representative scenarios. However, the highly variable channel conditions in mmWave require that they be defined as fluctuating bandwidth scenarios. It is necessary to determine how the transport layer can take advantage of the maximum available capacity and not affect the applications, and whether the network promises are fulfilled. This work aims to design and evaluate a CCA capable of efficiently adapting to the fluctuating bandwidth of extreme condition scenarios of 5G-A/6G mobile networks and to compare it with the state-of-the-art algorithms. As a first result, a set of simulation-based evaluation using 5GLENA was discussed. A combination of CCAs and different radio link control (RLC) buffer sizes allows us to highlight the importance of defining appropriate metrics and including convergence times as part of the evaluation performance of the algorithms. Algorithms such as HighSpeed and New Reno are among the slowest to converge, while BBR is the fastest. The analysis and characterization of the algorithms will allow us to define the requirements for designing an Machine Learning (ML) based algorithm with optimal performance and better convergence times.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it