Phasor Measurements-Aided Decision Trees for Power System Security Assessment

This paper describes a data mining algorithm in power system security assessment. Decision tree (DT) is utilized for on-line status appraisal of a realistic Chinese power grid model for the first time. Using knowledge database that covers all possible pre-fault operating conditions, decision rules in the form of hierarchical trees are developed for on-line assessment. Furthermore, phasor measurement units (PMU) are taken into consideration to better decision treepsilas performance. The results demonstrate that the proposed data mining scheme is able to identify crucial security indicators and gives reliable security predictions. In addition, voltage phase angle difference that obtained by PMU is proved helpful in improving DTpsilas identification accuracy.