Enhancing Quality of Service in WSN Through a Routing Algorithm Based on Self-Organizing Maps

Many scholars have focused their attention on Wireless Sensor Networks (WSN) within the last ten years. QoS control, Energy intake, MAC protocols, routing protocols, statistics aggregation, self-organizing net algorithms, Internet of Things (IoT), and so forth are among the research topics that have been thoroughly studied recently. Historically, the potential of artificial intelligence (AI) has not been fully realized due to constraints in data processing capabilities and energy efficiency. Nonetheless, the unique characteristics of neural networks can be harnessed for complex tasks, such as the role of travel advisors. This research aims to combine IoT and WSN technologies to enhance Quality of Service (QoS) parameters including reliability, energy, conservation, system scalability and response time. It provides an overview of the key components and techniques utilized in WSNs to achieve QoS. The objective of the proposed article is to compare the performance of two widely used route paradigms, Energy-Aware Routing and Directed Diffusion, with the proposed routing technique called Sensor Intelligence Routing (SIR). The foundation of Sensor Intelligence Routing (SIR) is the incorporation of neural networks into discrete sensor networks. WSN simulation, OLIMPO (an ad-hoc wireless sensor network simulator for optimal scada-applications) has been used in multiple simulations to examine how well neural networks perform within the system. The results obtained from every routing method have been compared and analyzed. The paper also aims at fostering the use of IoT-based synthetic intelligence techniques.