QoE-Guaranteed Optimization in MEC-Enabled Metaverse: An Active Inference Deep Reinforcement Learning Approach
Bibliographic record
Abstract
In this paper, we consider a MEC-enabled metaverse scenario which consists of a remote metaverse server and an edge server that cooperates to provide services to mobile users. The edge server is deployed at the base station (BS), serves a dual role: augmenting computational capabilities for user equipment (UE) and pre-caching a portion of the metaverse service contents before each time slot. Moreover, the foreground information and the requested contents generated by the UEs can also be cached to the BS. We formulate a problem to maximize the cache hit number by jointly optimizing contents pre-caching and resource allocation at the BS while considering UEs preference and reducing the UEs total energy consumption, essential for the efficient delivery of services in dynamic MEC environments. To solve this problem, we reformulate it as a partially observable markov decision process and propose an active inference enabled deep reinforcement learning algorithm, which combines active inference with deep reinforcement learning to select the optimal strategy by minimizing the expected free energy. Simulations show that the proposed algorithm can effectively improve the total quality of experience and the cache hit number of UEs, while minimizing the UEs total energy consumption compared with other baseline algorithms.
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 | 0.003 |
| 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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".