Design and Analysis of Adaptive Neural Controller for Voltage Source Converter for STATCOM

Usually a STATCOM is installed to support power system networks that have a poor power factor and often poor voltage regulation. It is based on a power electronics voltagesource converter. Various PWM techniques make selective harmonic elimination possible, which effectively control the harmonic content of voltage source converters. The distribution systems have to supply unbalanced nonlinear loads transferring oscillations to the DC-side of the converter in a realistic operating condition. Thus, additional harmonics are modulated through the STATCOM at the point of common coupling (PCC). This requires more attention when switching angles are calculated offline using the optimal PWM technique. This paper, therefore, presents the artificial neural network model for defining the switching criterion of the VSC for the STATCOM in order to reduce the total harmonic distortion (THD) of the injected line current at the PCC. The model takes into the account the dc capacitor effect, effects of other possible varying parameters such as voltage unbalance as well as network harmonics. A reference is developed for offline prediction and then implemented with the help of back propagation technique.