Data-Based Receding Horizon Control of Linear Network Systems

We propose a distributed data-based predictive control scheme to stabilize network system described by linear dynamics. Agents cooperate predict the future evolution without knowledge of dynamics, relying instead on learning representation from single sample trajectory. employ this reformulate finite-horizon Linear Quadratic Regulator problem as optimization with separable objective functions and locally expressible constraints. show that controller resulting approximately solving using algorithm in receding horizon manner is stabilizing. validate our results through numerical simulations.