Predictive and Adaptive ANN (Adaline) Based Harmonic Compensation for Shunt Active Power Filter

Estimation of the current-reference to compensate for the harmonic and reactive component of the load current is important in a shunt type active power filter. This paper applies ANN based predictive and adaptive reference generation technique. Predictive scheme extracts the information of the fundamental component through an ANN that replaces a low pass filter. This ANN based low pass-filter is trained offline with large number of training set to predict the fundamental magnitude of load current. These predictive reference generation techniques work well for load change pattern closer to the trained data and for clean source voltage. However, the performance deteriorates in case of distortion in source voltage and also if training data drifts quite significantly from test data. To overcome this, an Adaline based ANN is applied after the operation of the predictive algorithm. It has been shown that the combined predictive adaptive approach offers better performance. Extensive results from simulation have confirmed the usefulness of the proposed technique.