Power quality improvement using Neural Network controller based cascaded H-Bridge multilevel inverter type D-STATCOM

Abstract

The present loads are designed with modern semiconductor devices. These semiconductor devices are less sensitive to voltage fluctuations but are vulnerable to damage. Hence these sensitive loads need to be protected by suitable compensating devices; owing to this power quality (PQ) and its study have gained much attention of the researchers especially in developing countries like India. DSTATCOM is one such power conditioner used for improving PQ. This study proposes a cascaded multilevel inverter type DSTATCOM to compensate voltage sags in utilities in power distribution network. The proposed DSTATCOM is implemented using multilevel topology with isolated dc energy storage. The phase shifted PWM technique is described to generate firing pulses to cascaded inverter. The proposed Neural Network controller adopts itself to the sag and provides effective means of mitigating the voltage sags with the minimum harmonics at the utility end. The proposed concept is simulated using MATLAB / SIMULINK.