A Generative Model-Guided Distributed DRL Framework for Scalable and Efficient SFC Orchestration in Future Network Architectures
Bibliographic record
Abstract
Service Function Chain (SFC) provisioning plays a crucial role in 5 G and next-generation networks. It involves coordinating Virtual Network Functions (VNFs) in a predefined order to accommodate various SFC requests. Achieving optimal SFC provisioning necessitates advanced decision-making that can adapt to dynamic network conditions. While Artificial Intelligence (AI) modules and Deep Reinforcement Learning (DRL) algorithms have been extensively studied in the literature for this purpose, two critical factors must be considered: the algorithm's efficiency in large-scale networks and the model's ability to comprehensively capture environmental variations. Therefore, this paper introduces a novel Generative Model-Driven Distributed DRL framework for SFC provisioning, where the network is divided into multiple clusters, and each cluster is managed by a dedicated local agent equipped with a Generative-Assisted DRL module, enabling efficient handling of SFC provisioning within its respective region. Also, there is a general agent that can monitor and communicate with local agents to handle requests beyond their capacity. In this proposed approach, a distributed design reduces the workload of the centralized design, while a generative model, which is a Dreaming Variational Autoencoder, assists the DRL model in finding the proper data center for VNF placement by estimating the future state of the network. The proposed model is compared with a distributed DRL model to emphasize the impact of generative assistance under different network configurations. Results show that generative model-driven distributed DRL outperforms the distributed DRL in terms of SFC provisioning and improves SFCs' acceptance ratio from 4% to 11% under different network scale environments.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".