Energy Efficient and Resilient Task Offloading in UAV-Assisted MEC Systems
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Unmanned aerial vehicle (UAV)-assisted Mobile Edge Computing (MEC) presents a critical trade-off between minimizing user equipment (UE) energy consumption and ensuring high task execution reliability, especially for mission-critical applications. While many frameworks focus on either energy efficiency or resiliency, few address both objectives simultaneously with a structured redundancy model. To bridge this gap, this paper proposes a novel reinforcement learning (RL)-based framework that intelligently distributes computational tasks among UAVs and base stations (BSs). We introduce an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(h+1)$</tex-math></inline-formula>-server permutation strategy that redundantly assigns tasks to multiple edge servers, guaranteeing execution continuity even under partial system failures. An RL agent optimizes the offloading process by leveraging network state information to balance energy consumption with system robustness. Extensive simulations demonstrate the superiority of our approach over state-of-the-art benchmarks. Notably, our proposed framework sustains average UE energy levels above 75% under high user densities, exceeds 95% efficiency with more base stations, and maintains over 90% energy retention when 20 or more UAVs are deployed. Even under high computational loads, it preserves more than 50% of UE energy, outperforming all benchmarks by a significant margin—especially for mid-range task sizes where it leads by over 15–20% in energy efficiency. These findings highlight the potential of our framework to support energy-efficient and failure-resilient services for next-generation wireless networks.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it