MARINA: Multi-Agent Reinforcement Learning-Based Routing with Intelligent Network Adaptation in SDN
Bibliographic record
Abstract
Optimizing routing in Software-Defined Networks (SDNs) to meet Quality of Service (QoS) demands presents notable challenges, particularly with traditional methods that struggle with the dynamic nature of SDNs. Existing techniques often fail to adapt efficiently to varying traffic patterns, resulting in suboptimal network performance. Furthermore, the existing routing methods typically prioritize either the infrastructure provider or service provider benefits, neglecting a balanced approach that ensures efficient utilization of network resources while meeting QoS metrics for clients, such as guaranteed latency and throughput. This paper proposes a multi-agent Deep Reinforcement Learning (DRL)-based QoS-aware routing solution in SDN environments with intelligent network adaptation, called MARINA. MARINA dynamically adjusts routing paths for both existing and new incoming traffic flows in the network. Moreover, MARINA simultaneously optimizes network resource usage and meets QoS constraints such as latency and guaranteed throughput in an SDN. MARINA is extensively evaluated on real-world GEANT2 network topology. The results indicate that our algorithm outperforms Open Shortest Path First (OSPF), Equal Cost Multiple Path (ECMP), and single-agent DRL in key performance metrics. Specifically, MARINA meets 51.4%, 29.4%, and 11.1% more QoS requirements than OSPF, ECMP, and single-agent DRL-based approaches, respectively.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".