A Novel Approach for Voltage Sag Cause Identification Using V-V Plane with Soft Computing

This paper presents a novel approach for detecting and classifying the underlying causes of voltage sags using the voltage-Voltage (V-V) plane method combined with soft computing techniques. Voltage sags, which can result from various disturbances such as LLLG faults, transformer energization (TE), and induction motor starting (IMS), pose significant challenges to power quality. The proposed method utilizes voltage phasor measurements to create a distinctive signature on the V-V planes, enabling the differentiation of various sag causes. By incorporating soft computing techniques, such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), the system can automatically classify the type of disturbance with high accuracy. This approach enhances the reliability of power quality monitoring and provides a robust tool for identifying and mitigating voltage sag events, ultimately improving the overall stability and performance of electrical power systems.