Energy-Aware and Loss-Resilient Data Collection for AAV-Assisted Unbalanced IoT Networks

In infrastructure-limited Internet of Things (IoTs) networks, sensing devices are sparsely and irregularly distributed, with limited or intermittent access. Transmiting the data to cloud in real-time is unreliable due to constrained connectivity, harsh environmental conditions, or the energy limitations of nodes. Unmanned Aerial Vehicles (UAVs) offer an energy-efficient solution by periodically collecting sensing data via short-range communication. To address energy constraints and data loss in unbalanced IoTs networks, we proposeDQGDC, an energy-aware and loss-resilient UAV data collection framework.DQGDCjointly optimizes hovering point deployment, flight trajectory, and missing data recovery to improve efficiency under energy limitations. Firstly, a clustering and particle swarm optimization-based hovering point design minimizes the number of UAV hover points and redundantly covered nodes. Secondly, a graph convolutional network and double deep Q-Network-based trajectory planner enables adaptive, energy-efficient flight paths. Thirdly, to enhance resilience against sensing loss from inaccessible or unvisited nodes, we develop a Q-learning driven deep nonnegative matrix factorization model for reconstructing missing sensing data. Extensive experiments on realistic and simulated IoTs scenarios demonstrate thatDQGDCeffectively balances UAV energy consumption and data collection completion.