Knowledge Acquisition of Online Static Voltage Stability Margin Assessment Based on Random Forest Algorithm

Modern power system has produced a large amount of offline data during the operational planning studies. In order to extract the evaluation rules of voltage stability margin from massive data, a knowledge acquisition model based on random forest (RF) algorithm is proposed in this paper. Firstly, the training set of the random forest is obtained by PV curve analysis and calculation of voltage stability margin, based on the simulation data under n-k fault. Then, the online evaluation model of the voltage stability margin is trained using the RF algorithm. Finally, by using the proposed RF rule extraction method, some voltage stability margin evaluation rules are extracted with high accuracy and coverage. The proposed method is verified on IEEE 3-machine 9-bus system. Simulation result shows that the obtained knowledge of voltage stability margin has high accuracy, and can effectively evaluate the real-time operation status of the power grid.