TY - JOUR ID - 21596 TI - Distribution power system outage diagnosis based on root cause analysis JO - Scientia Iranica JA - SCI LA - en SN - 1026-3098 AU - Bashkari, M.S. AU - Sami, A. AU - Rastegar, M. AU - Bordbari, M.J. AD - School of Electrical and Computer Engineering, Department of Engineering, Shiraz University, Zand Avenue, Shiraz, P.O. Box 71348-51154, Iran. Y1 - 2019 PY - 2019 VL - 26 IS - Special Issue on machine learning, data analytics, and advanced optimization techniques... SP - 3672 EP - 3680 KW - power system reliability KW - Distribution system outages KW - Data mining KW - Random Forest KW - Cost matrix KW - Ensemble DO - 10.24200/sci.2019.54190.3638 N2 - This paper proposes data mining-based models to diagnose outage data in distribution power systems. In this work, outage data from a local distribution company is gathered and aligned with weather data. Then, a subset of features is selected to reduce the processing time and simplifying purposes. To increase the fairness of final models and to account for differences in misclassification cost, using a customized cost matrix is proposed. Two decision tree-based modeling algorithms are trained and tested. Results show the ability of the established models to diagnose the root cause of an outage fairly well. In addition, an ensemble of the decision tree-based models is built, which outperforms the other two models in almost all cases. Finally, applications of such models in decreasing outage duration and improving the reliability of the power distribution network are discussed. UR - https://scientiairanica.sharif.edu/article_21596.html L1 - https://scientiairanica.sharif.edu/article_21596_585eb73379d9bb1afd59a2f9a5bb4bcb.pdf ER -