A Novel Method for Optimizing Energy Consumption in Applications for Detecting Palm Rhynchophorus Ferrugineus in WSNs Using Data mining and Q-Learning

The date palm is a high-value fruit crops but unfortunately, the date production are in danger because of the Red Palm Weevil or Rhynchophorus Ferrugineus. The Rhynchophorus Ferrugineus can excavate holes in the trunks of palm tree up to 3.3ft long, thereby weakening and eventually killing the host plant. The aim of the present paper is use of wireless sensor network for automatic detection and tracking Rhynchophorus Ferrugineus. Since the energy of sensor nodes is limited, considering their energy level for enhancing network lifetime is of high significance. Data transmission can consume a great deal of energy. Hence, it is essential that a new method be designed for data transmission so as to enhance network lifetime. The method proposed in this paper is aimed at improving energy consumption of target-detecting applications in WSNs via data mining and Q-learning. The experiments and simulations are carried out on Opnet simulator. The simulation results indicate that using data mining and Q-learning can reduce energy consumption, data transmission delay and maintain load balance notably better than IEEE 802.15.4.