Online Critical Unit Detection and Power System Security Control: An Instance-Level Feature Importance Analysis Approach

Abstract

Rapid and accurate detection of critical units is crucial for the security control of power systems, ensuring reliable and continuous operation. Inspired by the advantages of data-driven techniques, this paper proposes an integrated deep learning framework of dynamic security assessment, critical unit detection, and security control. In the proposed framework, a black-box deep learning model is utilized to evaluate the dynamic security of power systems. Then, the predictions of the model for specific operating conditions are interpreted by instance-level feature importance analysis. Furthermore, the critical units are detected by reasonable local interpretation, and the security control scheme is extracted with a sequential adjustment strategy according to the results of interpretation. The numerical simulations on the CEPRI36 benchmark system and the IEEE 118-bus system verified that our proposed framework is fast and accurate for specific operating conditions and, thereby, is a viable approach for online security control of power systems.

Using SHAP Values and Machine Learning to Understand Trends in the Transient Stability Limit

“…SHAP is demonstrated to effectively determine the relationships between small signal stability and metrics of interest using a Random Forrest (RF) regressor. Authors in [30] integrate SHAP with dynamic security assessment for critical unit detection using classification. However, the authors seek to gain insights into a classifier and do not consider the impact of RES; which is a key driver of nonlinear changes in the dynamic response in power systems [31] that must be better understood.…”