Using machine learning to find the hidden relationship between RTT and TCP throughput in WiFi
Bibliographic record
Abstract
Abstract Is it possible to find hidden relationships among variables in WiFi network usingmachine learning(ML)? Can we use ML to find a variable that significantly affects the TCP throughput in WiFi? In this work, we employ a publicly available WiFi dataset to investigate these questions. We use ML techniques, includingprincipal component analysis (PCA),linear regression(LR), andrandom forest(RF), to study the effect of link speed, received signal strength,round-trip time(RTT), and number of available access points on TCP throughput in WiFi. More specifically, we are interested in employing ML to find the variable that most accurately predicts and thereby most significantly affects the throughput. Simple correlation analysis indicates that a combination of multiple variables is more likely to act as a reasonable predictor of the throughput, whereas a single variable, such as RTT, alone is not likely to predict the throughput with reasonable accuracy. From PCA, thefirst principal component(PC1) is seen as highly correlated to RTT. During predictive analysis, it is observed that the LR model is unable to find any hidden relationship between throughput and other variables. However, the RF model discovers that RTT explains the variation in throughput more closely and as such it predicts the throughput more accurately compared to other variables. PC1 captures nearly all of the variation in throughput with the RF model and predicts throughput with very high accuracy, which indirectly confirms RTT as the variable that most significantly affects the TCP throughput in WiFi. Consequently, we discover a very close relationship between RTT and TCP throughput using appropriate ML techniques, and these results can be helpful in developing a better understanding of the relationship between latency and throughput for designing future low-latency networks.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".