Transient stability assessment of power system using support vector machine with generator combinatorial trajectories inputs

Transient stability assessment (TSA) is part of dynamic stability assessment of power systems, which involves the assessment of the system’s ability to remain synchronism under credible disturbances. By qualitative analysis, this paper shows that the transient stability status of a power system following a large disturbance such as a fault can be early predicted based on dynamic response trajectories of rotor angle, speed, voltage, electromagnetic power and imbalance power. Based on this, a binary support vector machine (SVM) classifier with combinatorial trajectories inputs was trained to predict the transient stability status. Besides, a credible area and an incredible area of the classifier were given to improve the practicality of the classifier and a revised strategy was proposed to improve the performance of the SVM classifier in incredible area. The proposed approach was implemented and tested on New England 39-bus test system. Results show that the proposed approach can achieve 99.759% accuracy in credible area and 93.611% accuracy in incredible area.

This photo is flow chart of transient stability assessment based SVM classifiers with inputs of combinatorial trajectories.Figure optionsDownload as PowerPoint slideHighlights
► SVM classifiers were trained with combinatorial trajectories inputs.
► A credible area and an incredible area of the classifier were given.
► A revised strategy was proposed to improve the performance in incredible area.
► The approach achieved 99.76% and 93.61% accuracy in credible and incredible area.