Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks

2026-08-01

AI Summary

This work addresses the challenge of unreliable uplink transmission in drone-assisted federated learning over unlicensed spectrum, where interference coupling frequently causes model update loss and degrades training performance. To mitigate this issue, the authors propose a group-level transmission framework that, for the first time, models partial observability as a Bernoulli-masked aggregation process. They introduce a fairness-consensus bi-level optimization mechanism featuring a Consensus Threshold Controller (CTC) and a Fairness-aware Power Controller (FPC), which jointly optimize transmission thresholds and power allocation to balance aggregation consensus and user fairness. Experimental results on CNN-based tasks demonstrate that the proposed method significantly enhances model accuracy and training stability, outperforming existing strategies in both packet delivery ratio and worst-case user performance.

Abstract

Uncrewed aerial vehicle (UAV)-enabled federated learning (FL) can provide flexible, on-demand edge intelligence for large-scale IoT deployments, but operating in shared unlicensed bands makes uplink update delivery interference-coupled and unreliable. In this paper, we develop a packet-level transmission framework that captures buffer overflow, delay violations, and transmission errors, and uses the resulting packet delivery ratio (PDR) to represent partial-update reception through a packetized, Bernoulli-masked FL aggregation process. We then formulate a fairness-consensus bilevel (FCB) optimization that jointly controls (i) transmission thresholds to maximize the average PDR while reaching consensus under partial observability and (ii) transmission powers to improve the worst PDR and enforce fairness across IoT learners. To solve this problem, we propose an alternating FCB optimizer composed of a consensus-based threshold controller (CTC), which drives the IoT learners toward a PDR-efficient consensus on transmission thresholds, and a fairness-based power controller (FPC), which updates transmission powers to improve the worst PDR and ensure fairness under the resulting consensus thresholds. Numerical results on CNN-based FL tasks show that the FCB optimizer improves FL aggregation and training performance by enhancing packet-level update delivery, consistently outperforming baseline transmission policies.

Problem

• Partially-Observable
• UAV-Enabled Federated Learning
• IoT Networks
• Interference-Coupled Transmission
• Packet Delivery Ratio

Innovation

• federated learning
• UAV-enabled IoT
• packet delivery ratio
• fairness-consensus bilevel optimization
• partial observability