Delay Optimization in Hierarchical UAV-Aided Federated Learning for Straggling IoT Devices
Bibliographic record
Abstract
The Internet of things (IoT) devices generate large volumes of data that require secure, reliable, and low-latency processing to support time-sensitive decision-making. However, the limited computational capabilities of IoT devices often lead to processing delays and performance bottlenecks. We propose a hierarchical queuing-based uncrewed aerial vehicle (UAV)-aided edge federated learning (FL) framework to address these challenges. In our proposed framework, UAVs are organized into multiple layers to provide on-demand computational resources for straggling IoT devices (i.e., devices that struggle to process their local dataset within the required time constraints) by processing offloaded data segments that cannot be handled locally within the time constraints. We formulate a system delay minimization problem that considers computation and communication capabilities of IoT devices, follower UAVs, and leader UAVs. Our model incorporates a queueing system at each node, including integration, offloading, and local processing queues, and enforces quality of service (QoS) and delay constraints. We apply a Lyapunov-based approach and decompose the problem into three subproblems to solve it efficiently. The sub-problems are then solved using the proposed solution based on sequential quadratic programming (SQP) method. Simulation results demonstrate that the proposed framework significantly reduces system delay and improves resource utilization compared to traditional FL and existing schemes.
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 | 0.000 |
| 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".