A fast stability assessment scheme based on classification and regression tree

Traditional power system stability analysis based on full model computation shows its drawbacks in real-time applications where fast variations are present at both demand side and supply side. This paper presents the use of Decision Trees (DT) for fast evaluation of power system oscillatory stability and voltage stability based on voltage and current phasor measurements. An operating point is grouped into one of several stability categories based on the value of corresponding stability indicator. A new methodology for knowledge base creation has been elaborated to assure practical and sufficient training datasets. Encouraging results are obtained through the performance examination using the generated knowledge base. The impact of DT growing method and node setting on the classification accuracy has been explored. Finally, the differences in performance between regression tree and several other data mining tools have been compared.