Intelligent IoT-driven optimization of large-scale healthcare networks: the INRwLF algorithm for adaptive efficiency

Significant research has focused on improving routing performance within centralized Software-Defined Networking (SDN) architectures tailored for Intelligent Internet of Things (I-IoT) environments. With the explosive growth of IoT devices, particularly in expansive and dynamic settings, scalable and energy-conscious routing strategies have become essential. Addressing the limitations of power-constrained nodes, this paper proposes a novel routing algorithm, Interior Neighbors Route with Low Fault (INRwLF), designed for integration within SDN and cloud-enabled infrastructures. Unlike traditional approaches, INRwLF employs an AI-enhanced SDN controller to dynamically construct load-balanced cluster tables and compute fault-tolerant, low-latency paths. Simulation results demonstrate that the protocol reduces energy usage and network delay, while prolonging system lifetime by 50–90%. The proposed approach enhances network efficiency and scalability, particularly in domains such as healthcare, where synchronized data collection and resilient connectivity are critical.