A Deep Reinforcement Learning Approach for Dynamic Contents Caching in HetNets
Bibliographic record
Abstract
The recent development in Internet of Things necessitates caching of dynamic contents, where new versions of contents become available around-the-clock and thus timely update is required to ensure their relevance. The age of information (AoI) is a performance metric that evaluates the freshness of contents. Existing works on AoI-optimization of cache content update algorithms focus on minimizing the long-term average AoI of all cached contents. Sometimes user requests that need to be served in the future are known in advance and can be stored in user request queues. In this paper, we propose dynamic cache content update scheduling algorithms that exploit the user request queues. We consider a special use case where the trained neural networks (NNs) from deep learning models are being cached in a heterogeneous network. A queue-aware cache content update scheduling algorithm based on Markov decision process (MDP) is developed to minimize the average AoI of the NNs delivered to the users plus the cost related to content updating. By using deep reinforcement learning (DRL), we propose a low complexity suboptimal scheduling algorithm. Simulation results show that, under the same update frequency, our proposed algorithms outperform the periodic cache content update scheme and reduce the average AoI by up to 35%.
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) | 0.002 | 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".