A Model Predictive Control Strategy Based on Consistency in Wavelet Projections

This paper proposes a novel method of system modelling and control based on the idea of consistency in wavelet projections. Although the idea of consistency has been a familiar knowledge in the theory of generalized sampling, extension of it in the arena of system modelling and control is relatively new. It is proposed here that nonlinear approximation could be used for predicting system output that is consistent with the signal component of the desired output measurement. This imposes a number of equality and inequality constraints on wavelet projections of the input and the output. As a natural consequence, the control design problem can be viewed in the framework of multi-scale model predictive control. Idea of consistency can be further used to design a linear control law that minimizes error in least squares sense in the chosen forecast horizon. The technique of controller realization is demonstrated based on the simulation data with the point kinetics model of a nuclear reactor.