Minimizing Delay in Queuing-based UAV-aided Federated Learning with Straggling IoT Devices
Bibliographic record
Abstract
The Internet of Things (IoT) generates large volumes of data that need secure, reliable, and timely processing to enable effective decision-making. However, the limited processing capabilities of IoT devices often create a bottleneck. To address this, we propose a queuing-based uncrewed aerial vehicle (UAV)-aided edge federated learning (FL) (QUAFL) framework. The proposed framework uses UAVs as mobile edge computing (MEC) servers to process portions of data from the queues of straggling IoT devices that are unable to meet processing deadlines, thereby reducing system delay. We formulate an optimization problem that minimizes system delay by considering UAV-MEC computation power, IoT device computation and communication power, and the capacities of various queues (incoming, offloading, and local processing at IoT devices; incoming and local at UAV-MEC), along with quality-of-service and delay constraints. The problem is reformulated as a Lyapunov-based formulation and then decomposed into three subproblems, which are solved iteratively using closed-form solutions and the sequential quadratic programming (SQP) algorithm. Simulation results demonstrate the impact of various system components on overall delay.
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 | 0.001 | 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".