Research on Power System Transient Stability Assessment Based on Statistical Learning Theory

Abstract

Abstract. This paper presents a method of model construction for the power system transient stability assessment based on statistical learning theory integrated with the bagging and the approximate reasoning. Support vector machines operate on the principle of structure risk minimization. This paper takes full advantage of its ability to solve the problem with small sample, nonlinear and high dimension. Hence better generalization ability is guaranteed. The multi-class identification for power system transient stability assessment is solved by the data set reconstruction. The assessment model uses the data set regulation, bagging and approximate reasoning to improve the training speed, the accuracy and stability of the estimation result. The IEEE 39-Bus test system is employed to demonstrate the validity of the proposed approach.

v-SVM for transient stability assessment in power systems

“…x 8 The average value of kinetic energy of all generator rotors at the time of fault removal x 9 The minimum value of initial acceleration rates of all generators…”

“…The advantages of SVMs are good generalization ability and global minimize-tion. SVMs have been used for TSA in [8][9] and some satisfactory results have been obtained. Compared with Back-propagation (BP) network, SVMs are better in insensitivity of input dimensions and generalization.…”

“…The performance of SVMs depends on the type of kernel functions, and the parameters of kernel functions, which are determined by experience or experiments. But there is no description about the effects of kernel functions and the parameters of kernel functions in [8][9].…”