Reinforced Learning Model with Coati optimization Algorithm for Energy Efficient Routing for WSN Connecting IoT

The emergence of notable obstacles such heterogeneity, dependability, and scalability has been brought about by the growth of varied wireless devices in real-time Internet of Things applications. A new architecture known as Energy-Efficient Routing for IoT (EER-IoT) has been designed to efficiently address these problems. IoT devices in these systems, however, have to deal with unpredictable network dynamics, energy limitations, and strict quality of service requirements. The importance of having a well-designed routing protocol is highlighted by these reasons. Inaction on this part frequently results in frequent network disconnections and poor performance. In this work, we offer the intelligent, energy-efficient routing protocol, called EER-COA-RL, that combines reinforcement learning with the Coati Optimization Algorithm. This protocol evaluates fitness functions based on residual energy (RER) and distance limitations in an effort to improve network performance and lifespan. Optimizing energy usage in Internet of Things networks is the main goal of implementing this routing method. This is especially important since wireless Internet of Things devices have limited energy resources and you need to be able to quickly adjust to changes in the network to minimize interruptions and maximize network performance.