Speaker: Shiyang Li, ECpE Graduate Student
Advisor: Venkataramana Ajjarapu
Title: Adaptive Online Monitoring of Power System Voltage Stability Margin via Local Regression
Abstract: Voltage instability/collapse is usually a major reason for power system blackouts. To prevent the catastrophic loss of the blackout events, at the bottom of the countermeasures in power system operation is the real-time monitoring of voltage stability margin (VSM). In this talk, an online voltage stability margin monitoring approach based on machine learning techniques is proposed. Considering the increasing variability and uncertainty of power system operation, this approach utilizes the locality of underlying pattern between VSM and reactive power reserve (RPR), and can adapt to the changing condition of system. Local regression and adaptive database are applied to fulfill this goal. LASSO is tailored to solve the local regression problem so as to mitigate the curse of dimensionality for large scale system. Along with the VSM prediction, its confidence interval is also estimated in a simple but effective way, then utilized as an evidence to trigger the database updating. IEEE 30-bus system and a 60,000-bus large system are used to test and demonstrate the proposed approach. The results show that the proposed approach can be successfully employed in online voltage stability monitoring for real size system.