RNN Based Optimal Sensing Schedule Control for Wireless Sensor Networks

With the growth of the IoT technologies, the development of WSNs becomes increasingly more important. Since batteries are commonly used as energy sources for sensors in WSNs, high energy efficiency can extend the life of sensors and free them from interference such as energy harvesting. Mobile object tracking is one of the areas where WSNs are used. To save the energy, sensors usually manage multi-mode operation, in which they periodically switch active and inactive modes. There exists a tradeoff between object detection accuracy and energy efficiency. Depending on the object speed, direction and sensor deployment topology, different sensing schedules should be applied. In this paper, we propose a novel RNN-based sensor dynamic duty cycle control method that can determine the optimal sensing schedule of each sensor node. Simulation results show that the proposed model provides accurate object detection performance and achieves high energy efficiency.