Federated Learning in UAV-Assisted MEC Systems: A Comprehensive Survey
Bibliographic record
Abstract
In recent years, the integration of Uncrewed Aerial Vehicles (UAVs) into Multi-Access Edge Computing (MEC) systems has emerged as a transformative paradigm revolutionizing the landscape of data processing and analysis. By leveraging UAVs as MEC platforms, computing and storage capabilities are extended closer to data sources, thus facilitating real-time data processing and enabling smooth decision-making. This synergy between UAVs and MEC not only enhances the efficiency of data-intensive applications but also unlocks new possibilities for innovative services across various domains such as environmental monitoring, urban planning, and emergency response. The escalating demand to harness big data for several applications, empowered by Artificial Intelligence (AI), heralds a new era of ubiquitous data-driven intelligent services. Traditionally, Machine Learning (ML) approaches involve aggregating datasets and training models centrally, which poses several security risks. Alternatively, Federated Learning (FL), as a decentralized ML method, enables users to collaboratively train their ML models without compromising the privacy of their data. This paper comprehensively overviews UAV-assisted MEC systems, which rely on ML for several services, by shedding light on the vast opportunities it presents and discussing how to tackle its related key challenges. Subsequently, we provide an in-depth survey of the fundamentals and enabling technologies of FL, a pioneering technique poised to democratize ML at the edge of wireless networks such as those supported by UAVs. Also, we conduct an extensive analysis to identify the various applications of FL in UAV-assisted MEC systems, along with a nuanced examination of their associated challenges and limitations. Finally, we discuss some of the most important future research directions.
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 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 | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".