Sequence-based LQG control over stochastic networks with linear integral constraints

In this paper, we consider sequence-based LQG control of stochastic linear systems with linear integral state and input constraints over networks subject to stochastic packet delays and losses. For this scenario, we derive a novel closed-loop optimal control law that consists of a feedback term that depends linearly on the current state estimate and network acknowledgments, and a feedforward term that depends on the initial system state, the constraints, and network acknowledgments. The feedback term is given in closed-form, while the feedforward term demands the solution of a quadratic program. The number of decision variables corresponds to the number of constraints. The presented control law is evaluated by means of a Monte-Carlo simulation.