Service Provisioning and Path Planning with Obstacle Avoidance for Low-Altitude Wireless Networks

TL;DR

The paper addresses the problem of deploying UAVs as aerial base stations for low-altitude wireless networks in obstacle-rich environments with heterogeneous user demands. It proposes a joint optimization of UAV trajectories $Q$, transmit beamforming $W$, and UAV-UE associations $\boldsymbol{\alpha}$, solved via a block coordinate descent framework that uses a bisection-based water-filling method for beamforming and a PPO-based DRL approach for trajectory and association. The approach demonstrates faster convergence and improved user satisfaction while achieving effective obstacle avoidance compared with baselines. This work advances robust, personalized aerial networking in dynamic, obstacle-rich settings by combining principled optimization with learning-based control.

Abstract

This paper investigates the three-dimensional (3D) deployment of uncrewed aerial vehicles (UAVs) as aerial base stations in heterogeneous communication networks under constraints imposed by diverse ground obstacles. Given the diverse data demands of user equipments (UEs), a user satisfaction model is developed to provide personalized services. In particular, when a UE is located within a ground obstacle, the UAV must approach the obstacle boundary to ensure reliable service quality. Considering constraints such as UAV failures due to battery depletion, heterogeneous UEs, and obstacles, we aim to maximize overall user satisfaction by jointly optimizing the 3D trajectories of UAVs, transmit beamforming vectors, and binary association indicators between UAVs and UEs. To address the complexity and dynamics of the problem, a block coordinate descent method is adopted to decompose it into two subproblems. The beamforming subproblem is efficiently addressed via a bisection-based water-filling algorithm. For the trajectory and association subproblem, we design a deep reinforcement learning algorithm based on proximal policy optimization to learn an adaptive control policy. Simulation results demonstrate that the proposed scheme outperforms baseline schemes in terms of convergence speed and overall system performance. Moreover, it achieves efficient association and accurate obstacle avoidance.

Figures (11)

• Figure 1: System model.
• Figure 2: The obstacle shape is projected on the x-y axis.
• Figure 3: The PPO-based framework.
• Figure 4: The performance evaluation of the proposed scheme.
• Figure 5: The user satisfaction versus the number of UAVs $N$.