Distributed Variance-Constrained Filtering for Time-Varying Systems with Multiplicative Noises and Randomly Occurring Nonlinearities over Sensor Networks

This paper is concerned with distributed variance-constrained filtering problem for a class of time-varying systems and multiplicative noises and randomly occurring nonlinearities. The target plant is disturbed by the multi-plicative noises as well as additive noises. By fully taking the network topology structure into account, the available measurements collected by each sensor node and its adjacent sensor node are used when designing the recursive filter. Attention is focused on the design of a distributed variance-constrained filtering algorithm such that, in the simultaneous presence of multiplicative noises and randomly occurring nonlinearities, an upper bound of the filtering error covariance is obtained in terms of the solutions to two Riccati-like difference equations. Furthermore, the filter parameters are designed to minimize the obtained upper bound by utilizing a novel matrix simplification technique. Finally, a numerical simulation is utilized to demonstrate the effectiveness of the proposed distributed filtering scheme.