Diffusion Kalman filter for distributed estimation with intermittent observations

Wenling Li, Yingmin Jia, Junping Du, Deyuan Meng

Abstract: We consider the problem of distributed estimation for stochastic linear systems with intermittent observations. An optimal diffusion Kalman filter has been derived by minimizing the mean-squared estimation error for each node. Convergence of the estimation error covariance is proved under some mild assumptions and an upper bound is obtained for the estimation error covariance. A critical value for the arrival rate of observations is provided such that the estimation error covariance is bounded. The effectiveness of the proposed filter is validated via a numerical example involving tracking a moving target in a sensor network.