Observer and neural network based compound control for networked stochastic systems subjecting to multiple disturbances and dual channel attacks

In this paper, composite anti-disturbance control strategy is proposed for networked stochastic systems (NSSs) under the influence of multiple disturbances and false data injection attacks (FDIAs). The multiple disturbances contain the exogenous perturbation and stochastic noises, the FDIAs are included in the channel of actuator and sensor. The composite observer is established to estimate states and disturbances and the neural network (NN) technique is used to approximate FDIAs. Based on event-triggered mechanisms and observers, the compound control strategy is proposed to make sure that all signals are asymptotically bounded in mean square by combining NN technology with stochastic stability theory, then two simulations are provided to prove the applicability of the presented controller.