Distributed variance-constrained robust filtering with randomly occurring nonlinearities and missing measurements over sensor networks

This paper is concerned with the distributed variance-constrained robust filtering problem for a class of time-varying stochastic systems subject to both randomly occurring nonlinearities and missing measurements. The target plant is disturbed by the multiplicative noises, randomly occurring nonlinearities as well as additive noises. The phenomena of the randomly occurring nonlinearities and missing measurements are modeled by the Bernoulli distributed random variables with known occurrence probabilities. The available measurements of each sensor node and its neighbor nodes can be communicated based on the network topology structure. Attention is focused on the design of a new distributed variance-constrained robust filtering algorithm such that, in the simultaneous presence of the missing measurements, multiplicative noises and randomly occurring nonlinearities, an upper bound of the filtering error covariance is obtained via the solutions to two recursive matrix equations. Subsequently, the filter parameters are designed to minimize the obtained upper bound of the filtering error covariance. Furthermore, by utilizing the mathematical induction method, a sufficient condition is provided to guarantee the boundedness of the upper bound of the filtering error covariance. At last, we provide a numerical simulation to illustrate the effectiveness of distributed variance-constrained robust filtering method. (C) 2018 Published by Elsevier B.V.