IoT Network with Energy Efficiency for Dynamic Sink via Reinforcement Learning

In a society where better, cleaner power generation and management are needed, IoT devices and battery technologies have gained prominence. The Internet of Things (IoT) paradigm has revolutionized various industries by enabling seamless connectivity and data exchange among heterogeneous devices. However, the energy constraints of IoT devices, particularly in dynamic environments with mobile sinks, pose significant challenges to network performance and longevity. This article proposes a novel approach to enhance energy efficiency in IoT networks with dynamic sinks using reinforcement learning (RL). Better and more effective wireless communication methods could increase the lifespan of battery-powered devices and networks as these technologies advance. Compared to more conventional methods, the application of reinforcement learning can encourage even more advancements in these protocols. In order to elect cluster leaders and create clusters in a network of one hundred randomly generated nodes, a revised version of a previously suggested methodology will be presented in this study. Predictively moving the sink, or base station, from its fixed location in the middle of the plot will be the adjustment.