Adaptive control of a class of nonlinear discrete-time systems using support vector machine

In this paper, we introduce the use of least square support vector machine (LS-SVM) for the adaptive control of a class of nonlinear discrete-time systems. The solution is characterized by a set of linear equations. The results are discussed with radial basis function kernel. Advantages of LS-SVM control are that no number of hidden units has to be determined for the controller and that no centers have to be specified for the Gaussian kernels. The curse of dimensionality is avoided using the finite time window. Simulation results also verify the effectiveness of the approach.