On minimizing flow monitoring costs in large‐scale software‐defined network networks
Bibliographic record
Abstract
Summary Recent years have witnessed the rise of novel network applications such as telesurgery, telepresence, and holoportation. As such applications have stringent performance requirements, timely and accurate traffic monitoring becomes of paramount importance to be able to react in a timely and efficient manner, and swiftly adjust the network configuration to achieve the sought‐after requirements. However, existing monitoring schemes are either incurring high cost (e.g., high bandwidth consumption) due to the large number of monitoring messages or inefficient when they incur high reporting delay (i.e., the time needed for a monitoring message to reach the controller) making the collected statistics obsolete. In this paper, we address this problem and propose monitoring mechanisms for software defined networks that minimize the monitoring cost while satisfying an upper bound on the reporting delay of the statistics. Our solutions allow to carefully select the switch that should report the statistics about each flow crossing the network taking into consideration the available bandwidth and the capacity of the switch (i.e., the maximum number of flows that it can monitor). In particular, we formulate the switch‐to‐flow selection problem as an integer linear program and propose two heuristic algorithms to cope with large‐scale instances of the problem. We consider the scenario where a single controller is collecting statistics and another where statistics are collected by multiple controllers. Simulation results show that the proposed algorithms provide near‐optimal solutions with minimal computation time and outperform existing monitoring strategies in terms of monitoring cost and reporting delay.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".