Two-Timescale Optimization Framework for IAB-Enabled Heterogeneous UAV Networks
Jikang Deng, Hui Zhou, Mohamed-Slim Alouini
TL;DR
The study targets emergency communications in post-disaster zones by designing an IAB-enabled heterogeneous UAV network that leverages a stationary T-UAV for robust backhaul and multiple mobile U-UAVs for cell-edge coverage. It introduces a two-timescale, CTDE-based MADDPG framework (TTS-MADDPG) to jointly optimize user scheduling (short timescale) and UAV trajectory (long timescale), addressing mobility and asymmetric traffic demands. The approach is cast as a POMDP with problem decomposition and demonstrates that TTS-MADDPG outperforms benchmarks (e.g., TTS-MAPPO, MADDPG scheduling) in downlink throughput, achieving up to 12.2% average gains and robust convergence in simulations. The work highlights the practical impact of coordinated scheduling and trajectory control in IAB UAV networks for resilient disaster-response communications and points to future extensions with additional NTN platforms.
Abstract
In post-disaster scenarios, the rapid deployment of adequate communication infrastructure is essential to support disaster search, rescue, and recovery operations. To achieve this, uncrewed aerial vehicle (UAV) has emerged as a promising solution for emergency communication due to its low cost and deployment flexibility. However, conventional untethered UAV (U-UAV) is constrained by size, weight, and power (SWaP) limitations, making it incapable of maintaining the operation of a macro base station. To address this limitation, we propose a heterogeneous UAV-based framework that integrates tethered UAV (T-UAV) and U-UAVs, where U-UAVs are utilized to enhance the throughput of cell-edge ground user equipments (G-UEs) and guarantee seamless connectivity during G-UEs' mobility to safe zones. It is noted that the integrated access and backhaul (IAB) technique is adopted to support the wireless backhaul of U-UAVs. Accordingly, we formulate a two-timescale joint user scheduling and trajectory control optimization problem, aiming to maximize the downlink throughput under asymmetric traffic demands and G-UEs' mobility. To solve the formulated problem, we proposed a two-timescale multi-agent deep deterministic policy gradient (TTS-MADDPG) algorithm based on the centralized training and distributed execution paradigm. Numerical results show that the proposed algorithm outperforms other benchmarks, including the two-timescale multi-agent proximal policy optimization (TTS-MAPPO) algorithm and MADDPG scheduling method, with robust and higher throughput. Specifically, the proposed algorithm obtains up to 12.2\% average throughput gain compared to the MADDPG scheduling method.