Mobility Tracking Based on Autoregressive Models

We propose an integrated scheme for tracking the mobility of a user based on autoregressive models that accurately capture the characteristics of realistic user movements in wireless networks. The mobility parameters are obtained from training data by computing Minimum Mean Squared Error (MMSE) estimates. Estimation of the mobility state, which incorporates the position, velocity, and acceleration of the mobile station, is accomplished via an extended Kalman filter using signal measurements from the wireless network. By combining mobility parameter and state estimation in an integrated framework, we obtain an efficient and accurate real-time mobility tracking scheme that can be applied in a variety of wireless networking applications. We consider two variants of an autoregressive mobility model in our study and validate the proposed mobility tracking scheme using mobile trajectories collected from drive test data. Our simulation results validate the accuracy of the proposed tracking scheme even when only a small number of data samples is available for initial training.