A new approach for control of systems through high traffic communication networks

In this paper, a new method for real time prediction of uncertain network transmission time delays and a method for closed-loop control of plants through networks are introduced. The proposed delay prediction method is based on the Multi-Layer Perceptron neural model. For the purpose of minimizing the calculations needed in a real time implementation, a method for determination of the Markov order of the time delay sequence is presented. Furthermore, a new time varying control algorithm, with a variable feedback gain control scheme is proposed and applied to the predicted discretized model of the plant. Unlike many of the previously existing variable sampling algorithms, the proposed approach is shown, through well-known case studies, to be both accurate and fast enough for a real time implementation.