Adaptive RAN Slicing for Diffusion-based AIGC Services in Mobile Edge Networks
Bibliographic record
Abstract
In this paper, we propose an adaptive radio access network (RAN) slicing scheme to support diversified artificial intelligence generated content (AIGC) services in mobile edge networks. Specifically, multiple diffusion-based AIGC models are deployed on different network slices, thereby facilitating AIGC services with varying generation qualities. The text-to-image requests from mobile users are processed using diffusion models, and then the generated images are delivered to users via wireless communication links. In addition, we formulate a joint Slice Access, Denoising step selection, and bAndwidth allocaTion (SA-DAT) optimization problem to maximize generation quality while minimizing service delay. Moreover, to solve the problem, we first decouple it into two sub-problems and then propose a two-layer algorithm to achieve the balance between generation quality and service delay. In the inner layer, the optimal bandwidth allocation is determined by a convex optimization algorithm using a Lagrange multiplier method. In the outer layer, the optimal slice access and denoising steps decisions are determined using a Gibbs sampling method. Extensive simulation results demonstrate that the proposed SADAT scheme can averagely reduce service delay by 14.84% and improve image generation quality score by 2.53, as compared with benchmark schemes in the scenarios with limited computing resources.
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 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 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".