A GCN and Recommender Based Approach for Optimizing Edge Caching Performance in IoV
Bibliographic record
Abstract
Edge Caching for Internet of Vehicles (IoV) is considered as one of the most active academic topics in green computing, which shifts the content caching and computation capacities to Roadside Units (RSU) to alleviate unprecedented network traffic demand. Due to the high mobility of vehicles and limited computing resources of RSU, a strategy that can cache accurate contents under limited cache capacity of RSU is necessary. To cope with these difficulties, we propose a novel proactive caching strategy named Graph Convolutional Network (GCN)-based Recommender System and Deep Reinforcement Learning Caching (GCNRDRL). Moreover, GC-NRDRL is lightweight enough to run on RSUs with modest processing power, making it suitable for cost-sensitive or rural deployments. GCNRDRL dynamically manages cache content at RSUs by the GCN-based recommender to predict vehicles’ content demands and a Proximal Policy Optimization (PPO) [1] based Deep Reinforcement Learning (DRL) agent deployed in RSUs to optimize caching decisions in the dynamic vehicular environment. The DRL agent with GCN [2] preserves the complex relationships between content items generated from the recommender system and the temporal dynamics of vehicles and executes accurate cache replacement actions. Comprehensive experimental results show that GCNRDRL can achieve a 93% higher cache hit ratio and 10% lower latency than the state-of-the-art caching strategies at best.
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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| 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".