Link-Weight Adjustment for Efficient Link-State Multicast Routing with MARL
Bibliographic record
Abstract
Along with the rapid increase of new applications involving multiple participants, such as metaverse, multicast traffic engineering (TE) has recently attracted significant attention. The optimal multicast TE for offered traffic can be obtained using link-state routing protocols with a proper link weight setting. However, optimizing the link weights for such link-state multicast routing protocols according to the offered traffic in real-time is a very challenging problem. In this paper, we provide an Integer Linear Programming (ILP) formulation for finding the link metrics that allow link-state multicast routing protocols to achieve optimal traffic engineering. To meet the real-time requirement, we propose a Multi-Agent Reinforcement Learning (MARL) solution to the problem of link weights adjustment to achieve efficient multicast routing in a distributed fashion. In our design, the agents collaborate and communicate with the others in the local region and learn from their experiences to determine the best action to minimize the overall network cost. Our proposed solution is evaluated on a simulation of various traffic profiles and compared with the traditional manually configured link weights and a Genetic Algorithm (GA)-based heuristic solution. Experimental results show the advantages of our solutions in reducing network cost, and suggest the potential of using MARL in achieving efficient multicast traffic engineering.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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 | 0.000 |
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".