Abstract
Machine learning techniques have been widely used in transient stability prediction of power systems. When using the post-fault dynamic responses, it is difficult to draw a definite conclusion about how long the duration of response data used should be in order to balance the accuracy and speed. Besides, previous studies have the problem of lacking consideration for the confidence level. To solve these problems, a hierarchical method for transient stability prediction based on the confidence of ensemble classifier using multiple support vector machines (SVMs) is proposed. Firstly, multiple datasets are generated by bootstrap sampling, then features are randomly picked up to compress the datasets. Secondly, the confidence indices are defined and multiple SVMs are built based on these generated datasets. By synthesizing the probabilistic outputs of multiple SVMs, the prediction results and confidence of the ensemble classifier will be obtained. Finally, different ensemble classifiers with different response times are built to construct different layers of the proposed hierarchical scheme. The simulation results show that the proposed hierarchical method can balance the accuracy and rapidity of the transient stability prediction. Moreover, the hierarchical method can reduce the misjudgments of unstable instances and cooperate with the time domain simulation to insure the security and stability of power systems.
Highlights
With the continuous growth of electricity demand and the enlargement of the power system interconnection scale, power systems are becoming increasingly complex and have been forced to operate closer to their stability limits
Based on the aforementioned analysis, we propose in this paper a support vector machines (SVMs)-based ensemble classifier and its confidence evaluation index
Prediction results of SVM-based ensembleclassifiers classifiers using of SVMs
Summary
With the continuous growth of electricity demand and the enlargement of the power system interconnection scale, power systems are becoming increasingly complex and have been forced to operate closer to their stability limits. Transient instability has historically been the dominant stability problem in power systems [1]. The study on the transient stability has great significance for the secure and stable operation of power systems. Time domain simulation is the most traditional transient stability analysis method. This method depends on exact models and parameters, and it is time-consuming which makes it hard to apply online. Other traditional methods, such as the transient energy function method and extended equal-area criterion, have model limitations which makes it hard for them to give efficient and precise results for large-scale power systems. The machine learning techniques, with high computing speed and precision, as well as the capacity of mining the potential useful information
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call