Nonparametric time-varying phasor estimation using support vector machines

A new approach to nonparametric modelling techniques for tracking time-varying voltage phasors in power systems is proposed. A first order polynomial is used to approximate these signals locally on a sliding window of fixed length. In terms of accuracy, non-quadratic methods to fit this linear function to the data, give superior performance over least squares methods. But these non-quadratic methods are iterative and much slower than the least squares method. A support vector machine (SVM) is then trained to model the non-quadratic methods and once the SVM is trained, it is much faster than the non-quadratic methods.