A Multimodal Deep Learning-Based Distributed Network Latency Measurement System
Bibliographic record
Abstract
Network latency plays an important role in the server-selection process as well as real-time applications. Depending on the network system size, network latency can be either explicitly measured or predicted. While for small-scale systems explicit delay measurements can be performed between any pair of network nodes, this method is not feasible for large-scale networks due to the tremendous traffic and processing overhead. As a result, networking companies as well as researchers use the estimation methods for round-trip time (RTT) in large-scale networks. In such methods, network latency estimation is based on performing a small set of actual RTT measurements and predicting the rest of latencies among all network nodes. However, they suffer from several drawbacks such as poor performance, long convergence duration, or lack of convergence. In this article, we present a novel method of large-scale network latency estimation using artificial intelligence (AI). Our system uses a multimodal deep learning algorithm for high accuracy and computing speed. The proposed AI-based system is trained and evaluated using the well-known KING data set derived from the measurements of a real large-scale network. Performance evaluations show that our proposed approach significantly outperform existing techniques, achieving the 90th percentile relative error of 0.25 and an average accuracy of 96.1%, and 76.4% of the measurements are within 20% estimation error.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.003 | 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".