Dynamic Mask Enhanced Intelligent Multi-UAV Deployment for Urban Vehicular Networks

TL;DR

This paper introduces Q-SDAM, a novel algorithm for deploying multiple UAVs to improve urban vehicular network connectivity and energy efficiency, validated with real-world data.

Contribution

It proposes a score-based dynamic action mask mechanism integrated into QMIX for effective multi-UAV deployment in VANETs, enhancing connectivity and reducing energy use.

Findings

Q-SDAM improves vehicle connectivity by 18.2%.

It reduces UAV energy consumption by 66.6%.

The method accelerates learning and optimization in UAV deployment.

Abstract

Vehicular Ad Hoc Networks (VANETs) play a crucial role in realizing vehicle-road collaboration and intelligent transportation. However, urban VANETs often face challenges such as frequent link disconnections and subnet fragmentation, which hinder reliable connectivity. To address these issues, we dynamically deploy multiple Unmanned Aerial Vehicles (UAVs) as communication relays to enhance VANET. A novel Score based Dynamic Action Mask enhanced QMIX algorithm (Q-SDAM) is proposed for multi-UAV deployment, which maximizes vehicle connectivity while minimizing multi-UAV energy consumption. Specifically, we design a score-based dynamic action mask mechanism to guide UAV agents in exploring large action spaces, accelerate the learning process and enhance optimization performance. The practicality of Q-SDAM is validated using real-world datasets. We show that Q-SDAM improves connectivity by 18.2% while reducing energy consumption by 66.6% compared with existing algorithms.