Research on Mobile Terminal Mobility Prediction Method Based on Unscented Kalman Filter

Abstract

For mobile terminal users in the process of moving, due to the uncertainty of movement, how to effectively predict and reasonably allocate the Edge Servers (ESs) for mobile terminal users has become the key to solving the problem. Therefore, this paper proposes and designs a mobile terminal user mobility prediction method based on an Unscented Kalman Filter (UKF). According to the application scenario of Mobile Edge Computing (MEC), the edge server with computing resources is placed at the edge node of the network. The state equation and observation equation are constructed through the trajectory points of the mobile terminal users, and the trajectory prediction is completed using the UKF. By comparing the No Filter. Method, the Linear Kalman Filter. Method and the UKF method, the research results show that the proposed method can effectively reduce the error and improve the success rate of the task compared with the other two methods so that the prediction trajectory of mobile terminal users is more accurate and more applicable.