QoS-Aware 3D Coverage Deployment of UAVs for Internet of Vehicles in Intelligent Transportation

TL;DR

The paper tackles the problem of QoS-aware 3D UAV deployment to maximize vehicle coverage in IoV under UAV capacity and A2G channel constraints. It introduces QoS-IOA, a hybrid optimization framework that uses K-means clustering to initialize UAV positions and a K-means initialized grey wolf optimization (KIGWO) to refine the search, with GA-style selection, crossover, and mutation to maximize the objective $\\sum_{i=1}^{|P|}\\sum_{j=1}^{|Q|}\\gamma_{i,j}$ under $C_1$-$C_5$. A realistic urban road model and comprehensive A2G channel model, including LOS/NLOS effects and conical UAV coverage, underpin the evaluation, showing improved reliability and higher QoS satisfaction for vehicles. Simulation results demonstrate the method achieves higher or complete coverage across high- and low-density scenarios, with favorable performance under varying $R_{min}$ and UAV counts. The approach offers practical benefits for deploying UAV-assisted IoV networks in urban environments, while future work will address dynamic mobility, more complex obstacles, and real-time trajectory adaptation.

Abstract

It is a challenging problem to characterize the air-to-ground (A2G) channel and identify the best deployment location for 3D UAVs with the QoS awareness. To address this problem, we propose a QoS-aware UAV 3D coverage deployment algorithm, which simulates the three-dimensional urban road scenario, considers the UAV communication resource capacity and vehicle communication QoS requirements comprehensively, and then obtains the optimal UAV deployment position by improving the genetic algorithm. Specifically, the K-means clustering algorithm is used to cluster the vehicles, and the center locations of these clusters serve as the initial UAV positions to generate the initial population. Subsequently, we employ the K-means initialized grey wolf optimization (KIGWO) algorithm to achieve the UAV location with an optimal fitness value by performing an optimal search within the grey wolf population. To enhance the algorithm's diversity and global search capability, we randomly substitute this optimal location with one of the individual locations from the initial population. The fitness value is determined by the total number of vehicles covered by UAVs in the system, while the allocation scheme's feasibility is evaluated based on the corresponding QoS requirements. Competitive selection operations are conducted to retain individuals with higher fitness values, while crossover and mutation operations are employed to maintain the diversity of solutions. Finally, the individual with the highest fitness, which represents the UAV deployment position that covers the maximum number of vehicles in the entire system, is selected as the optimal solution. Extensive experimental results demonstrate that the proposed algorithm can effectively enhance the reliability and vehicle communication QoS.

Figures (11)

• Figure 1: System architecture of UAV-assisted IOV.
• Figure 2: Single UAV covers vehicle 3D scene .
• Figure 3: UAV overlay vehicle plane model.
• Figure 4: The road scene diagram.
• Figure 5: Results of vehicle clustering in the high-density scenario.