A Distributed Learning Model Predictive Control Scheme for Linear Systems with Coupled Constraints and Communication Noise

This paper presents a novel Distributed Learning Model Predictive Control (DLMPC) scheme for linear systems with coupled constraints under communication noise. By incorporating an iterative learning mechanism, subsystems can distributedly learn the optimal solution to an infinite horizon Optimal Control Problem (OCP), thereby outperforming methods that solve finite horizon OCP. Additionally, it addresses coupling constraint problem between subsystems and mitigates the impact of communication noise by an Alternating Direction Multiplier Method (ADMM). The feasibility and stability of the proposed scheme are proved and the effectiveness of the proposed scheme is verified through a simulation example.