Sequential feature selection for power system event classification utilizing wide-area PMU data

The increasing penetration of intermittent, non-synchronous generation has led to a reduction in total power system inertia. Low inertia systems are more sensitive sudden changes and susceptible secondary issues that can result large-scale events. Due the short time frames involved, automatic methods for event detection diagnosis required. Wide-area monitoring (WAMS) provide data required detect diagnose However, due quantity data, it is almost impossible operators manually process raw data. important information be extracted presented real/near-time decision-making control. This study demonstrates an approach wide-area classification many A mixture sequential feature selection linear discriminant analysis (LAD) adopted reduce dimensionality PMU Successful obtained by employing quadratic (QDA) on synchronized frequency, phase angle, voltage measurements. reliability proposed method evaluated using simulated case studies benchmarked against other methods.