Voltage and Frequency Recovery in Power System and MicroGrids Using Artificial Intelligent Algorithms

This thesis developed an advanced assessment tools to recover the power system voltage margin to the acceptable values during the disturbance. First, the effect of disturbance in islanded microgrids are analyzed using power factor-based power-voltage curves and a comprehensive under voltage-frequency load shedding(UVFLS) method is proposed as a last resort in order to restore the system voltage and frequency. The effect of disturbance in conventional power system is investigated by introducing a phenomenon called fault induced delayed voltage recovery(FIDVR) and comprehensive real-time FIDVR assessments are proposed to employ appropriate emergency control approaches as fast as possible to maintain the system voltage margins within the desired range. Then, polynomial regression techniques have been used for predicting the FIDVR duration. Next, advanced FIDVR assessment is implemented which simultaneously predicts whether the event can be classified as FIDVR or not and also predicts the duration of FIDVR with high accuracy.