Federated Learning for Scalable Edge Caching in Dynamic D2D Communication Networks
Bibliographic record
Abstract
Device-to-device (D2D) communication networks face significant challenges due to their dynamic nature, including limited bandwidth, high latency, and frequent disruptions. These factors complicate content caching and timely user request fulfillment. To address these issues, we propose a federated learning (FL)-based edge caching framework that utilizes density-based spatial clustering of applications with noise (DBSCAN) to cluster devices based on content similarity and Euclidean distance. Within each cluster, a master user equipment is selected based on the signal-to-noise ratio, willingness, and battery level, while slave user equipment devices share content based on popularity. A graph neural network (GNN) is employed for local caching prediction, effectively capturing complex spatiotemporal dependencies. FL enables global model training without centralizing raw data, improving scalability and privacy. Additionally, deep Q-learning (DQL) optimizes caching decisions for each device. Simulation results demonstrate the effectiveness of the proposed framework, achieving a high cache hit ratio of 94.6%, an average delay of 33ms for 100 clusters, and energy consumption between 1.727 to 1.746 bit/J. These results highlight the framework’s efficiency in reducing delay and power consumption, outperforming existing techniques in terms of these performance metrics.
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 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 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".