Self-learning sensor scheduling for target tracking in wireless sensor networks based on adaptive dynamic programming

This paper proposes a novel self-learning sensor scheduling scheme, which makes the sensor energy consumption and tracking error optimal over the system operational horizon for target tracking in wireless sensor networks (WSNs). It employs Kalman filter estimation technique to predict the tracking accuracy. A performance index function is established based on the predicted energy consumption and tracking error. A self-learning scheduling method is proposed based on the adaptive dynamic programming algorithm. Numerical example shows the effectiveness of the proposed approach.