Dynamic Neural Network-Based Resource Management for Mobile Edge Computing in 6G Networks
Bibliographic record
Abstract
Mobile edge computing (MEC) can be used to reduce the task delay for users with limited computing resources. However, in 6G networks, the diversity of tasks is greatly increased. For those extremely delay-sensitive small-size computing tasks, the inference delay of neural network (NN)-based algorithms such as resource allocation and task offloading cannot be ignored. As a hyperparameter, the inference cost of NN is usually difficult to adjust. Dynamic neural network (DyNN) is an emerging technique that improves the model efficiency by adjusting the network architecture on-demand according to the sample characteristics during inference. In this paper, we propose a DyNN-based resource management method for MEC that dynamically adjusts the depth and width of the NN according to the features of the task, improving computational efficiency and achieving a balance between inference delay and the management performance of computational and communication resources. Furthermore, to reduce the training cost of DyNN, a new training method is proposed in this paper, where all the blocks in DyNN are gradually trained in the order of size. Simulation results demonstrate that the proposed DyNN-based resource management method outperforms the traditional optimization algorithm and the static-NN-based method.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| 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".