Smart agriculture, healthcare, industrial Internet of Things applications, and environmental monitoring all utilize in network. However, inconsistent energy use and low battery capacity drastically shorten the network's lifespan. While energy harvesting allows for sustainable operation and data aggregation lowers duplicate transmissions, their efficacy depends on intelligent control system. This research work on Reinforcement Learning based energy harvesting and data aggregation method (RL-EHDA) for duty cycle and cluster head (CH) selection. The proposed Reinforcement Learning based data aggregation and energy harvesting method dynamically modifies CH roles and node activity states according to harvested energy, residual energy, and network conditions ,When compared to conventional clustering and static duty cycling protocols, simulation findings show that the proposed Reinforcement Learning based energy harvesting and data aggregation method (RL-EHDA) system greatly increases network existence, energy utilization, and reduce packet loss.
Archana et al. (Thu,) studied this question.