Adaptive Prioritization and Task Offloading in Vehicular Edge Computing Through Deep Reinforcement Learning
Bibliographic record
Abstract
Vehicular edge computing enables real-time decision-making by offloading vehicular computation tasks to edge servers along roadways. This paper focuses on optimizing offloading and scheduling these tasks, with an emphasis on task prioritization to maximize task completion within deadlines while minimizing latency and energy consumption across all priority levels. We propose a prioritized Deep Q-Network (DQNP) that optimizes long-term rewards through a priority-scaled reward system for each priority level, guiding the deep reinforcement learning (DRL) agent to select optimal actions. The model dynamically adjusts task selection based on environmental conditions, such as prioritizing tasks with higher deadlines in poor channel states, ensuring balanced and efficient offloading across all priority levels. Simulation results demonstrate that DQNP outperforms existing baseline algorithms, increasing task completion by 14%, particularly for high-priority tasks, while reducing energy consumption by 8% and maintaining similar latency. Additionally, the model mitigates resource starvation for lower-priority tasks, achieving task selection rates of 27%, 32%, and 42% for low-, medium-, and high-priority tasks, with completion ratios of 88%, 87%, and 86%, respectively, reflecting balanced resource allocation across priority classes.
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) | 0.001 | 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".