The transmission and distribution sectors of the power system are operated near the stability margin for the best usage of the existing infrastructure. The operation near the stability margin makes the power system susceptible to cascading failures, triggered by power system faults. As a result, the power quality and the reliability of the service provided by the utilities are identified to be at risk. Providing an adequate system that identifies the power system faults is highly essential for the faster restoration of the power supply. In this paper, a comparative analysis of the performance of three machine learning algorithms that classify the power system faults is studied. The voltage and current signals were extracted from a standard IEEE 14 bus system and different faulty and non-faulty cases were simulated in MATLAB Simulink. The multi-class dataset is used to train and test the models and the performance metrics such as accuracy, precision, and recall are used for the analysis. The main objective of this work is to report the performance of the classifiers and identify the best performing classifier.
Comparative Analysis of Machine Learning Algorithms for the Classification of Power System Faults
2019-06-01
3393711 byte
Conference paper
Electronic Resource
English
Driver Classification of Shifting Strategies Using Machine Learning Algorithms
British Library Conference Proceedings | 2020
|Driver Classification of Shifting Strategies Using Machine Learning Algorithms
SAE Technical Papers | 2020
|Driver Classification of Shifting Strategies Using Machine Learning Algorithms
British Library Conference Proceedings | 2020
|