Unlocking Reconfigurability for Deep Reinforcement Learning in SFC Provisioning
Bibliographic record
Abstract
Network function virtualization (NFV) is a key foundational technology for 5G and beyond networks, wherein to offer network services, execution of Virtual Network Functions (VNFs) in a defined sequence is crucial for high-quality Service Function Chaining (SFC) provisioning. To provide fast, reliable, and automatic VNFs placement, Machine Learning (ML) algorithms such as Deep Reinforcement Learning (DRL) are widely being investigated. However, due to the requirement of fixed-size inputs in DRL models, these algorithms are highly dependent on network configuration such as the number of data centers (DCs) where VNFs can be placed and the logical connections among DCs. In this study, a novel approach using the DRL technique is proposed for SFC provisioning which unlocks the reconfigurability of the networks i.e. the same proposed model can be applied in different network configurations without additional training. Moreover, an advanced Deep Neural Network (DNN) architecture is constructed for DRL with an attention layer that improves the performance of SFC provisioning while considering the efficient resource utilization and the End-to-End (E2E) delay of SFC requests by looking up their priority points. Numerical results demonstrate that the proposed model surpasses the baseline heuristic method with an increase in the overall SFC acceptance ratio by 20.3% and a reduction in resource consumption and E2E delay by 50% and 42.65%, 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 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".