Identification of Vulnerable Lines in Smart Grid Systems Based on Improved Agglomerative Hierarchical Clustering

Abstract

The identification of vulnerable lines in smart grid systems is of great significance to increase the stability of the smart grid systems and reduce the occurrence of cascading fault blackouts. Inspired by the machine learning method, this study proposes a vulnerable line identification approach based on the improved agglomerative hierarchical clustering algorithm. By jointly considering the topological parameters and the electrical properties, we discuss the vulnerability of the transmission lines and establish the influencing factors. Then, we adopt principal component analysis (PCA) to select the influencing factors and reduce their dimensionality. Finally, an improved agglomerative hierarchical clustering algorithm is proposed and employed to divide the lines to identify the vulnerable lines in the smart grid systems. Experiments over the IEEE 39-bus system demonstrate that our proposed method can efficiently and accurately identify different types of potential vulnerable lines in smart grid systems.