Immersive Embedded Consumer Model Leveraging AI with Zero-Trust Architecture for Cyber-Physical System

The rapid expansion of the wireless network and its combination with the Consumer Internet of Things (CIoT) has introduced significant research challenges for Cyber-Physical Systems (CPS). The distributed nature of these embedded networks provides big data analytics with the integration of sensors, electronic devices, hardware, and network components. They provide diverse functionalities while sensing the observing environment based on the demand of network users with timely feedback, which supports efficient decision-making. However, CIoT devices in CPS increasingly interact with both physical and digital environments, such interaction raises the research challenges of performance optimization, data breaches, and long-run seamless connectivity. In addition, the constraint devices demanded lightweight communication methods to remain robust and enhance network stability. This paper presents an adaptive model that leverages AI-based optimization techniques with efficient data management and utilization of resources in consumer applications. Moreover, the integrated edges provide consistency and resilience of communication services in unpredictable systems, while adopting a Zero-Trust architecture with more trustworthy and secure transmissions. It increases the system’s scalability and improves the response time with the limited computing power of devices for real-time processing. Simulation results demonstrated the significant outcomes of the proposed model over the dynamic scenarios for packet delivery ratio by 35.5%, network throughput by 38.7%, energy consumption by 41.6%, and latency by 45% against existing solutions.