Enhancing Real-Time IoT Applications in Cloud Communication Networks Through Adaptive Intelligent Routing and Secure Data Transmission

The growing Internet of Things network with cloud technology enables real-time solutions in healthcare, autonomous systems, and industrial automation. These systems face challenges with response time, shifting network layouts, power conservation, and data security threats. RPL and traditional routing protocols struggle to adapt to complex networks, while machine learning-based and EERP approaches solve some issues but leave others unresolved. This study presents an AI routing method that enhances live data transfer between IoT systems and cloud platforms. The algorithm tracks network shifts to make fast routing decisions, reducing time delays and conserving power. This study implement basic encryption, device confirmation, and abnormal event recognition to protect data transfers. Simulations compared the technique's performance to RPL and EERP approaches, measuring latency, data delivery rate, energy usage, network speed, and security capabilities. Testing shows a 25-50% improvement in latency and 10-20% better PDR results. Energy utilization decreases by 30-50%, while throughput remains superior. Security features demonstrate reduced encryption overhead with improved anomaly detection and authentication. This research addresses IoT-cloud communication network challenges through an adaptable system that conserves power, protects data, and enhances reliability for time-sensitive applications.