Optimizing UAV Aerial Base Station Flights Using DRL-based Proximal Policy Optimization

2025-04-04

AI Summary

To address the challenges of rapid deployment and dynamic 3D coverage of unmanned aerial base stations (UABs) in emergency communications, this paper proposes a deep reinforcement learning-based collaborative trajectory optimization method. The approach integrates proximal policy optimization (PPO) with realistic radio-frequency (RF) channel state information—marking the first such integration for adaptive UAB positioning. It generalizes across diverse user equipment (UE) mobility patterns: static, linear, circular, and hybrid. The method enables real-time response and continuous coverage over large-scale, spatially distributed UEs. Evaluated across five representative mobility scenarios, it achieves >98% area coverage, improves average signal-to-interference-plus-noise ratio (SINR) by 12–27% over greedy and Q-learning baselines, and accelerates policy convergence by 3.5×. These advances significantly enhance timeliness in life-critical rescue operations and robustness of emergency wireless connectivity.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Unmanned aerial vehicle (UAV)-based base stations offer a promising solution in emergencies where the rapid deployment of cutting-edge networks is crucial for maximizing life-saving potential. Optimizing the strategic positioning of these UAVs is essential for enhancing communication efficiency. This paper introduces an automated reinforcement learning approach that enables UAVs to dynamically interact with their environment and determine optimal configurations. By leveraging the radio signal sensing capabilities of communication networks, our method provides a more realistic perspective, utilizing state-of-the-art algorithm -- proximal policy optimization -- to learn and generalize positioning strategies across diverse user equipment (UE) movement patterns. We evaluate our approach across various UE mobility scenarios, including static, random, linear, circular, and mixed hotspot movements. The numerical results demonstrate the algorithm's adaptability and effectiveness in maintaining comprehensive coverage across all movement patterns.

Problem

• Optimizing UAV base station positioning for emergency networks
• Enhancing communication efficiency via dynamic UAV-environment interaction
• Adapting to diverse user equipment movement patterns effectively

Innovation

• DRL-based Proximal Policy Optimization for UAV positioning
• Dynamic interaction with environment for optimal configurations
• Adaptive coverage across diverse UE movement patterns