Control over unreliable networks based on control input densities

Time delays and data losses arising from an unreliable communication between the components of a control loop decrease the quality of control and thus, have to be incorporated explicitly in the control decision. In this paper, a novel concept, the so-called virtual control inputs, is presented, which extends the well-established control technique of sending sequences of future inputs by incorporating also the potential effects of previously transmitted sequences on the future system behavior. The key idea of this paper is to model the unknown future inputs as random variables characterized by probability density functions over the finite set of potential future inputs. Subject to this probabilistic description of the future inputs, the controller determines the optimal open-loop sequence over a finite horizon. The high capacity of the proposed approach is demonstrated by simulations, in which a sensor manager schedules sensors for tracking a mobile object.