Intelligent Adaptive Mechanisms for Dynamic Congestion Control and Real-Time Monitoring in IoT-Enabled Wireless Sensor Networks (WSNs)

Abstract

The fast growing domain of Internet of Things (IoT) applications leads to significant pressure on wireless sensor networks. Consequently, congestion and packet delivery delays are considered inherent characteristics of resource-constrained devices. Conducting a literature review, this paper summarizes the latest developments on fuzzy logic, reinforcement learning, and hybrid lightweight models for Adaptive Congestion Control (ACC) and analyzes their effectiveness in improving network reliability, delay, energy efficiency and overall network performance metrics. While many studies describe encouraging enhancements, the field remains challenged by issues related to computational cost, limited scalability verification, and a lack of real-world experimental validation. These observations emphasize the demand for computationally light, interpretable, and scalable adaptive frameworks with real-time responsiveness in heterogeneous IoT environments. The paper also outlines future research directions toward designing sustainable and reliable congestion-control solutions for upcoming IoT systems.