Distributed Multiple Model Filtering With Event-Triggered Communication

We consider distributed state estimation for Markov jump systems over wireless sensor networks. A novel composite event-triggered (ET) communication strategy is proposed to quantify the discrepancy between two Gaussian mixture distributions, providing an information-theoretic justification for the triggering mechanism. Based on the ET strategy and interacting multiple model framework, a distributed event-triggered multiple model filtering algorithm is developed. Furthermore, theoretically, sufficient conditions ensuring the mean square boundedness of the estimation error are derived via stochastic stability theory. Simulation results demonstrate that the proposed algorithm achieves a favorable trade-off between estimation accuracy and communication frequency.