Achieving Low Delay & High Rate in 802.11ac Edge Networks
Bibliographic record
Abstract
Provision of connections with low end-to-end latency is one of the most challenging requirements in 5G. In most use cases the target is for < 100ms latency, while for some applications it is < 10ms. In part, this reflects the fact that low latency is already coming to the fore in network services, but the requirement for low latency also reflects the needs of next generation applications such as augmented reality, virtual reality and the tactile internet.\n\nIn this thesis we analyze the end-to-end latency in an edge network where an 802.11ac wireless hop is the bottleneck and queueing delay at the AP is the main source of latency. We demonstrate that queueing delay is coupled to the aggregation level in 802.11ac WLANs and that we can manage the delay by controlling the aggregation level. We implement this algorithm with a simple feedback loop on Linux using MAC timestamps. We also propose and implement a machine learning technique to infer aggregation level from kernel timestamps on Android OS where we do not have access to MAC timestamps. We demonstrate that the aggregation-based rate control policy selects a rate between that of Cubic and BBR. Importantly, the end-to-end one-way delay is more than 20 times lower than that with Cubic and BBR while it induces very few losses. We also propose a passive technique using logistic regression to detect the location of the path bottleneck, i.e. whether the bottleneck is the backhaul link or the wireless hop, and show how measurement of the aggregation level can be used for this purpose. We show that this approach has more than 90% accuracy across a range of different network configurations.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.004 |
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".