A Deep Reinforcement Learning Approach for Efficient Image Processing Task Offloading in Edge-Cloud Collaborative Environments
Bibliographic record
Abstract
In the wake of the burgeoning Internet of Things (IoT) era and the increasing prevalence of image-based applications on mobile platforms, a significant demand for computing resources has been witnessed.While traditional cloud computing has been limited by substantial transmission distances and notable response delays, mobile edge computing, where communication, computation, and storage resources are situated on edge devices, has emerged as a superior alternative.In this context, the challenge of offloading image processing tasks for multiple users, especially considering the collaboration of edge servers under computational and communication resource constraints, is investigated.A primary objective is to strike a balance between energy consumption and task delays, thereby aiming to curtail the total associated costs.The novel framework introduced, termed as Image Collaborative Task Offloading System using Deep Reinforcement Learning (I-CTOS-DRL), is specifically designed for image processing tasks in edge-cloud collaborative scenarios.Through the integration of a set updating mechanism, complications arising from interactions with neighboring edge servers are effectively diminished.Simultaneously, a heuristic algorithm was constructed to identify the most viable servers for task offloading purposes.Building on this foundation, a pioneering methodology for image processing task offloading was devised, leveraging fully connected neural network training.Evaluations conducted extensively indicate that the proposed strategy outperforms established benchmarks in terms of efficiency.
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 | 0.001 |
| 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".