Enhancing Vehicular Network Performance through Integrated RSU and UAV Deployment

The on growing demand for reliable vehicle commu-nication services creates issues in providing continuous connectiv-ity and effective data delivery. Traditional roadside units (RSUs) need help adapting to changing traffic circumstances and user density. Integrating unmanned aerial Vehicles (UAVs) as aerial base stations provides a solution by increasing the coverage, relia-bility, and line-of-sight communication, and allowing for dynamic deployment. This research work uses self-learning methodology to focus on efficient and effective RSUs, UAVs, and UAV-assistant (UAVa) deployment inside vehicular networks. The primary goals are to improve network performance, Quality of Service (QoS), and interference management. In this article, we have considered two different scenarios in vehicular networks in which we have integrated a UAVa to handle emergency situations on the roads which dynamically provides network coverage to the uncovered vehicles on the roadside. We strategically deploy UAVa using a hybrid method that combines heuristic algorithms and real-world traffic insights to balance existing vehicular network resources, minimize latency, and eliminate interference. The simulation findings show that the UAVa has a much higher throughput than RSUs, emphasizing the need for dynamic adaptation and strategic positioning. This study emphasizes the significance of proper location and intelligent support in maximizing throughput and ensuring the reliability of vehicle data exchange.