Optimizing WDM Network Restoration with Deep Reinforcement Learning and Graph Neural Networks Integration
Bibliographic record
Abstract
Network survivability is a major and critical con-cern in the design and operation of Wavelength Division Multi-plexing (WDM) networks. The vulnerability of these networks to various external (e.g. natural disaster, human accidents) or internal (e.g. equipment aging, power failure) disruptions necessitates effective mechanisms for quick service restoration. To efficiently restore the affected services has been a major research problem for many years. Several solutions such as pre-computed restoration paths or using heuristic algorithms have been proposed. These approaches have limitations in terms of adaptability to unforeseen network topologies and prolonged outages. In this paper, we introduce an approach to improve resilience in WDM networks by integrating Deep Reinforcement Learning (DRL) with Graph Neural Networks (GNN). Our proposed DRL+GNN-based solution leverages the capabilities of DRL in decision-making and the inherent ability of GNNs to generalize over graphs of varying sizes and structures. By considering the current and future state of the network, our solution intelligently selects pre-computed restoration paths that is viable. The results demonstrate the superior performance of our DRL+GNN agent in comparison to existing algorithms across a wide range of failure scenarios and network loading.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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".