Control of shunt custom power device based on Anti-Hebbian learning algorithm

This paper presents an implementation of shunt custom power device namely distribution static compensator (DSTATCOM) using a neural network based Anti Hebbian control algorithm for power quality improvement under linear/nonlinear type consumer loads. Learning based Anti-Hebbian control algorithm is used for extraction of fundamental active and reactive power components of load currents in terms of weighted signals which are used for deriving the reference source currents. This control algorithm is implemented on a developed DSTATCOM using a DSP for reactive power compensation, harmonic elimination and load balancing. Simulation and test results demonstrate satisfactory performance of proposed control algorithm for the control of DSTATCOM under time varying loads.