Energy-efficient Federated Learning for UAV Communications

2025-08-05

AI Summary

This paper addresses energy-efficient design in unmanned aerial vehicle (UAV)-assisted federated learning (UAV-FL) systems. We jointly optimize UAV trajectory, user participation selection, uplink power allocation, and local data volume control to minimize total system energy consumption. To overcome the limitations of conventional decoupled designs, we propose a holistic co-optimization framework—first establishing a theoretical linkage between model accuracy and user participation strategies under multi-round local updates, and integrating convergence analysis to jointly optimize energy efficiency and learning performance. Leveraging alternating optimization and successive convex approximation (SCA), we decompose the original non-convex problem into tractable subproblems and devise an efficient iterative algorithm, ECO. Simulation results demonstrate that ECO consistently reduces system energy consumption by over 30% on average across diverse scenarios, while ensuring model convergence and maintaining high prediction accuracy.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

In this paper, we propose an unmanned aerial vehicle (UAV)-assisted federated learning (FL) framework that jointly optimizes UAV trajectory, user participation, power allocation, and data volume control to minimize overall system energy consumption. We begin by deriving the convergence accuracy of the FL model under multiple local updates, enabling a theoretical understanding of how user participation and data volume affect FL learning performance. The resulting joint optimization problem is non-convex; to address this, we employ alternating optimization (AO) and successive convex approximation (SCA) techniques to convexify the non-convex constraints, leading to the design of an iterative energy consumption optimization (ECO) algorithm. Simulation results confirm that ECO consistently outperform existing baseline schemes.

Problem

• Optimize UAV trajectory and FL parameters for energy efficiency
• Analyze FL convergence under user participation and data volume
• Develop iterative algorithm for non-convex energy consumption optimization

Innovation

• UAV-assisted FL framework optimizes multiple parameters
• AO and SCA techniques convexify non-convex constraints
• ECO algorithm minimizes overall system energy consumption