The Internet of Things (IoT) and emerging technologies have converged to drive the remarkable development of intelligent systems. The interconnection of physical objects, sensors, and tiny communication devices enables data aggregation, which is then forwarded to edge computing for local processing and analysis. Such a system improves response time and enhances network capabilities while managing the massive amount of collected data. On the other hand, existing approaches include cloud-based schemes that leverage edge-level offloading to control and manage demanding traffic. Furthermore, data security and network integrity are ensured by integrating blockchain technology with device identity authentication. However, in a dynamic environment, most approaches still incur interception and data eavesdropping, thereby affecting the reliability of connected communication channels. Therefore, developing trustworthiness and an authenticated system is a significant research challenge for the growth of smart systems. In this research, we introduce a lightweight, trusted AI-driven model to enhance security in complex systems and to ensure a more robust data-forwarding path over the long term. First, optimized methods are introduced that use an adaptive technique to explore network conditions and generate efficient data-transfer decision policies. Secondly, distributed and collaborative interactions are enabled across devices with minimal computing resources, thereby improving the system’s response time through load balancing. Ultimately, trust is continuously updated by leveraging real-time parameters and records of neighbours’ communication, thereby providing fault tolerance and trusted channels. The proposed model is verified and validated for efficacy through a wide range of simulations, and performance results demonstrate its superiority over existing approaches on realistic scenarios and metrics.
Alharbi et al. (Tue,) studied this question.