This article addresses the problem of resilient consensus control for nonlinear multiagent systems (MASs) operating over networks subject to denial-of-service (DoS) attacks. We propose an event-triggered, recurrent-neural-network-based model predictive consensus controller (RNN-MPCC) that integrates three components: 1) a data-driven recurrent neural network (RNN) predictor of agent dynamics with a certified uniform one-step error bound; 2) a DoS-aware communication model that constrains attack frequency and duration and is embedded in the resilient consensus and update logic; and 3) an aperiodic (event-triggered) execution that reduces transmissions and solver calls while preventing Zeno behavior via a minimum interevent time. The predictive controller optimizes a receding-horizon-based cost function that penalizes the disagreement vector, control effort, and hold-induced errors, enforces input and state constraints, and constructs effective Laplacians from successfully received packets and locally held neighbor copies. Finally, simulations on a six-agent leader-follower multi-UAV network demonstrate that the proposed event-triggered RNN-MPCC achieves resilient consensus under DoS attacks.
RoshanaeeDeh et al. (Thu,) studied this question.