Support vector machine based predictive control for active power filter

A support vector machine (SVM) is presented in this paper. In the strategy, based predictive control strategy for active power filter, SVM is employed to model and predict future harmonic compensating current, it has multi advantages, such as overcoming local minima solutions, automatic choice of model complexity and good generalization performance. Based on the model output, branch-and-bound optimization method is adopted for producing proper control vector value, which is adequately modulated by means of a space vector PWM modulator that generates proper gating patterns of the inverter switches to maintain tracking of reference current. As the internal model control scheme, the SVM based predictive algorithm is used to compensate for process disturbances, measurement noise and modeling errors. The proposed control is applied to compensate the harmonic produced by the variable non-linear load, simulation results show that SVM based predictive controller is effective and feasible.