UAV-enabled federated learning framework improves IoT network reliability

Researchers have developed a new transmission control framework for UAV-enabled federated learning in IoT networks to address unreliable uplink updates. This framework models buffer overflows, delay violations, and transmission errors to represent partial-update reception. An optimization strategy called FCB (fairness-consensus bilevel) is proposed to jointly control transmission thresholds and powers, aiming to maximize packet delivery ratio and ensure fairness among IoT learners. Numerical results indicate that this approach enhances federated learning aggregation and training performance compared to existing policies. AI

IMPACT Enhances the efficiency and reliability of federated learning in resource-constrained IoT environments.

RANK_REASON This is a research paper detailing a new framework and optimization strategy for a specific technical problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• CNN
• federated learning
• Internet of Things
• unmanned aerial vehicle

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →