Age‐Aware Energy and Resource Optimization for Federated Air Quality Monitoring With UAVs

Abstract

ABSTRACT Reliable air quality monitoring in Internet of Things (IoT) systems requires a synergy between energy‐efficient data collection, data freshness and scalable learning across geographically distributed sensors. We propose AERO‐Air (Age‐aware Energy and Resource Optimization), a novel hierarchical framework that jointly optimizes Unmanned Aerial Vehicle (UAV) trajectories, Age‐of‐Information (AoI)‐aware client scheduling and hierarchical federated aggregation. By focusing on the temporal relevance of environmental data, AERO‐Air improves prediction accuracy, information freshness and UAV energy efficiency. The framework leverages lightweight local neural models at ground sensors, performs intermediate aggregations at follower UAVs, and utilizes a leader UAV to coordinate global updates via hierarchical Federated Learning (FL). The optimization problem, which jointly considers UAV mobility, AoI constraints and federated learning objectives, is addressed through a hybrid solution combining offline successive convex approximation (SCA) and online reinforcement learning (RL). Simulation results on the University of California Irvine (UCI) Air Quality dataset confirm that AERO‐Air significantly reduces AoI, accelerates learning convergence, and maintains high energy efficiency compared to existing baselines.