AI-Driven Resource Management for Energy-Efficient Aerial Computing in Large-Scale Healthcare SDN–IoT Systems

The integration of software-defined networking (SDN) and the Internet of Things (IoT) presents significant challenges in large-scale healthcare systems, particularly in terms of optimizing resource allocation, managing energy consumption (EC), and ensuring real-time data processing. This research introduces an AI-driven resource management framework designed to address these challenges. Using autonomous aerial vehicles (AAVs) for aerial computing, the framework optimizes energy usage, reduces network latency, and enhances anomaly detection through machine learning models. Key contributions include dynamic allocation of bandwidth and processing resources, adaptive power management, and real-time traffic prediction, ensuring high Quality of Service (QoS) even in resource-constrained environments. The simulation results demonstrate a 10%–15% reduction in EC, 15% decrease in latency, and improved real-time data processing, making the system ideal for critical healthcare applications such as telemedicine and remote monitoring. The framework offers a scalable solution to efficiently manage the growing number of IoT devices and AAVs, while also maintaining a low-latency secure service delivery.