Online Detection of Events With Low-Quality Synchrophasor Measurements Based on $i$Forest

摘要: In this article, we propose an online data-driven approach that leverages the isolation mechanism for fast event detection with low-quality data measurement. The proposed adaptive and forest ( $i$ Forest)-based (AOIFD) method adopts a hierarchical subspace feature selection scheme to design two levels of detectors. As such, it is capable differentiating events from measurements, preventing false alarms in presence measurements. We further augmentation address training imbalance, which caused by rare occurrence events. Moreover, process update AOIFD so can adapt time-varying operating conditions power systems. algorithm practical sense fast-response requires no system modeling information global communications. Case studies both synthetic realistic PMU are conducted validate effectiveness method.