Importance Sampling Based Decision Trees for Security Assessment and the Corresponding Preventive Control Schemes: the Danish Case Study

Decision Trees (DT) based security assessment helps Power System Operators (PSO) by providing them with the most significant system attributes and guiding them in implementing the corresponding emergency control actions to prevent system insecurity and blackouts. DT is obtained offline from time-domain simulation and the process of data mining, which is then implemented online as guidelines for preventive control schemes. An algorithm named Classification and Regression Trees (CART) is used to train the DT and key to this approach lies on the accuracy of DT. This paper proposes contingency oriented DT and adopts a methodology of importance sampling to maximize the information contained in the database so as to increase the accuracy of DT. Further, this paper also studies the effectiveness of DT by implementing its corresponding preventive control schemes. These approaches are tested on the detailed model of western Danish power system which is characterized by its large scale wind energy penetration and high proportion of distributed generation (DG). DIgSILENT PowerFactory is adopted for the power system simulation and Salford Predictive Modeler (SPM) is used for data mining.