Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network

The rapid advancement of Intelligent Transportation Systems (ITS) has heightened the importance of reliable, real-time data transmission in Wireless Sensor Networks (WSNs). However, congestion in data-heavy Internet of Things (IoT)-enabled networks remains a critical challenge, impacting communication efficiency and decision-making in ITS. In high-density IoT-ITS applications, traditional congestion control methods are insufficient to address the complexity and dynamics of data flows. Existing solutions often fail to adapt in real time to varying traffic loads, leading to delays and data loss. There is a strong need for a congestion alleviation framework capable of intelligently prioritizing data while dynamically managing network resources to ensure seamless information exchange in large-scale deployments. This study presents a Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network (V-CapMiAN-Parr), which combines the Vectorized Adaptive Capsule Neural Network (V-AdCapNet) and Multi-instance Attention Network (MAN), fine-tuned by the Parrot Optimizer (ParrOpt). This integration aims to effectively detect, mitigate, and prevent congestion through an advanced capsule-based attention mechanism with adaptive optimization. The suggested V-CapMiAN-Parr framework demonstrated significant improvements in congestion control, achieving data throughput efficiencies above 99.7%, packet delivery rates above 99.5%, and network reliability reaching 99.2% under high traffic loads. The model's adaptive weighting mechanism ensures real-time responsiveness and reliability, crucial for next-gen ITS applications. The V-CapMiAN-Parr framework effectively addresses congestion issues in IoT-enabled WSNs, providing a robust, scalable solution for ITS applications. This cognitive framework's advanced data prioritization and adaptive optimization capabilities are well-suited for enhancing the performance and reliability of next-generation transportation networks, ensuring efficient data flow in high-demand environments.