Risk assessment of voltage sag based on multi-source data mining

Abstract

Abstract This paper proposes the data mining method of voltage sag severity based on DHP algorithm and replaceable coefficient to assess the risk of voltage sag. The DHP (Direct Hashing and Pruning) is served to mine the relationship between voltage sag characteristic attribute (VSCA) in the fault scenario and the voltage sag severity (VSS) of node. Using direct hash pruning technology, frequent item sets can be found quickly and mining efficiency can be improved. The association rules are matched with the actual fault scenarios through replaceable coefficients to get the VSS of actual fault scenarios. Finally, the effectiveness and accuracy of this method are verified by simulation and examples.