Intelligent Resource Management for Vehicular Networks in Cloud-Edge Architectures

Nowadays, resource management for vehicular networks is crucial for enhancing the efficiency, scalability, and reliability of connected vehicle systems. Through leveraging AI-driven resource allocation across cloud and edge environments, this approach optimizes latency-sensitive applications, improves network performance, and supports real-time decision-making in autonomous and smart transportation systems. This article discusses employing distributed machine learning algorithms at the network edge, resource optimization, and pathfinding/optimization of vehicular communication networks. Integration with 5G will eventually allow for very low latency, energy efficiency, and privacy protection for scalability. This study adapts the algorithms to function at both local-edge devices and global-server levels, thereby enhancing traffic optimization and congestion prevention. The server manages and organizes work across regions, leveraging the strategic decisions made through local administration experiences. The algorithm is implemented on actual data collected from vehicular networks in Erbil, Iraq. This can be seen in the case of emergency medical services, where the proposed approach reduced the average response time by 23% and increased the area covered by an ambulance by up to 18% compared to traditional methods. The nearest available ambulance and a suitable hospital were chosen for emergencies to ensure the shortest and fastest route to the incident location.