An Option-Based Hierarchical Approach for Dynamic Mobile Crowdsensing Over Edge-Assisted UAV Networks

Abstract

With the rapid advancement of edge computing and uncrewed aerial vehicle (UAV) technologies, edge-assisted UAV networks have emerged as a promising solution for efficient data collection in mobile crowdsensing (MCS). This paper addresses the problem of decentralized dynamic data collection in UAV networks supported by edge systems. In this setting, UAVs autonomously collect data from ground sensor nodes (SNs), using shared task state information (TSI) exchanged through the edge system to enhance cooperation and improve overall efficiency. However, two key challenges arise in such dynamic environments: 1) Continuous data generation at SNs requires timely and non-redundant collection under limited UAV communication and energy constraints; and 2) UAVs face a fundamental trade-off between collecting fresh data at SNs and updating TSI via the edge system. To address the unique challenges posed by such dynamic environments, we propose the weighted age of data queue (WAoDQ), a novel data freshness indicator that quantitatively captures the time-varying nature of data freshness. Building upon WAoDQ, we further develop Fresh-DCEA, an option-based hierarchical multi-agent deep reinforcement learning (HMADRL)-based algorithm that integrates high-level strategic planning (e.g., data collection or TSI update decisions) with low-level action execution (e.g., UAV trajectory adjustments), enabling efficient and adaptive dynamic task assignment. Simulation results demonstrate that Fresh-DCEA outperforms benchmark methods in terms of data freshness, collection effectiveness, and energy efficiency, thereby validating its scalability and adaptability in dynamic MCS environments.