Study On Power System Transient Stability Assessment Based On SVM And Evidence Theory

It is of great significance to judge the system transient stability quickly and accurately. Support vector machine can make assessment fast owing to its good statistical properties compared with traditional methods. In view of evidence theory's advantages of solving problem of uncertainty, so integrate it in order to improve the reliability of transient stability assessment. An information fusion assessment model based on support vector machines and D-S evidence theory is presented in this paper, the selection of characteristic is studied also. Disturbed trajectory is a direct expression of the dynamic behavior of the system. A method is proposed based on the DTW distance to determine similarity of the disturbed trajectory. The methods are verified in improving the accuracy of the assessment and reducing the training time effectively through the simulation.