Real-time long-term voltage stability assessment based on eGBDT for large-scale power system with high renewables penetration

Abstract

• A data-driven voltage stability assessment framework is established, which can be performed utilizing observed PMU measurements and is completely independent from system modeling. • Based on the complete datasets, considering the random and uncertainty of renewable energy in multiple scenarios, we developed a refined voltage state classification ( secure, warning and emergency ) for high renewables penetration power systems. • Dramatic speedup by virtue of GOSS and HEEFB techniques enables the traditional GBDT-based learning algorithms to be effective for handling massive high-dimensional data, realizing the real-time assessment of voltage stability. Real-time voltage stability assessment is a critical issue for ensuring the safety of large-scale renewable energy connected power system. In this paper, a data-driven approach based on the enhanced Gradient Boost Decision Tree (eGBDT) for long-term voltage stability assessment from massive high-dimensional PMU measurements was proposed. This approach effectively improves the ability of the traditional GBDT algorithm to handle high-dimensional observed data by utilizing gradient-based one-side sampling (GOSS) and histogram-enhanced exclusive feature bundling (HEEFB) techniques, realizing spatial dimension reduction and feature compression. The proposed method exploits both the accuracy of the GBDT algorithm and the fast computational capacity of GOSS and HEEFB techniques, which effectively reduces the calculation time. Case studies on the Nordic32 system and IEEE 118-bus test system demonstrated the accuracy and the speed of the proposed approach. Extensive studies on the robustness of dealing with missing data illustrate that the proposed method is practically suitable for real-time application.