A method for evaluating transient stability of power systems based on pin-svm

Abstract

The invention relates to a Pin-SVM (Support Vector Machine)-based transient stability evaluation method for a power system. The method comprises the following steps: establishing an original feature set comprising training sample data and test sample data; training a transient stability evaluation model of the power system by the training sample data; carrying out stability evaluation on a power system state simulated by the test sample data by using the transient stability evaluation model of the power system; for the fault type of the actual power system, classifying the faults according to the membership degree of a power system feature subset relative to the stable class and unstable class of the power system, if the power system belongs to the unstable class, then the fault being a serious fault; otherwise, the fault being a nonserious failure; obtaining an evaluation index when the fault screening and stability evaluation are completed. According to the method provided by the invention, the feature set dimension and the redundant information can be reduced, and the feature dimension can be reduced, and the evaluation accuracy is higher. The method can be applied to the online safety and stability evaluation of the regional power system in China, and the safe and stable operation of the complex power system is powerfully ensured.

Description

technical field [0001] The invention relates to a method for evaluating transient stability of a power system. In particular, it involves a Pin-SVM-based transient stability assessment method for power systems. Background technique [0002] Transient Stability Assessment (TSA) is an important part of power system security and stability analysis. With the continuous development of the power system and the continuous expansion of the interconnection scale of the regional power grid, the power system is facing more risks of safe and stable operation. In order to avoid the recurrence of blackouts similar to those in the United States, Canada and Western Europe, an accurate and stable evaluation method for the transient stability of the power system is sought is of great significance. [0003] In artificial intelligence methods, the Support Vector Machine (SVM) algorithm based on statistical principles has been widely used in power system transient stability assessment, but the...

AI Technical Summary

Problems solved by technology

[0003] In artificial intelligence methods, the Support Vector Machine (SVM) algorithm based on statistical principles has been widely used in power system transient stability assessment, but the method has problems in the construction, selection and classification of input features in practical applications. The problem of device construction still needs to be improved

More input features may contain features that have nothing to do with the stability index. The redundancy between features makes the model training time longer, the weight convergence is difficult, and the classification performance is not ideal; while the energy function index is strongly related to the system stability, a small number of indexes The steady state of the system can be represented by

Images