Title: Enhanced R package-based cluster analysis fault identification models for three phase power system network
Authors: K. Nithiyananthan; Pratap Nair; Raman Raguraman; Tan Yong Sing; Syahrel Emran Bin Siraj
Addresses: Department of Electrical and Electronics Engineering, Karpagam College of Engineering, Coimbatore, Tamilnadu, India ' Faculty of Engineering and Computer Technology, AIMST University, Bedong, Kedah, Malaysia ' Faculty of Engineering and Computer Technology, AIMST University, Bedong, Kedah, Malaysia ' Faculty of Engineering and Computer Technology, AIMST University, Bedong, Kedah, Malaysia ' Faculty of Engineering and Computer Technology, AIMST University, Bedong, Kedah, Malaysia
Abstract: The main objective of this research work is to develop an R-based fault identification model for power system in a cluster analysis environment. Cluster analysis-based data mining techniques model has been implemented to locate the three-phase transmission lines fault in IEEE 30 bus power system. Power World version 18 software was used to simulate the IEEE 30 bus power system and the three-phase transmission lines fault. The bus voltages at fault were collected and import to R statistical software to identify the faults at buses. Through cluster analysis using squared euclidean distance method, fault has been identified at each bus. Then the data also imported to R statistical package to compute the cophenetic distance of dendrogram and check the accuracy of clustering. This meant that the application of data mining techniques yields a huge potential in solving complex problems related to power system, it not only yield an accurate result but also fast computation. The proposed innovative successful model was able to locate the fault at each bus by bus nominal voltage comparison method.
Keywords: power system transmission lines faults; data mining; cluster analysis; R; SPSS.
International Journal of Business Intelligence and Data Mining, 2019 Vol.14 No.1/2, pp.106 - 120
Received: 26 Apr 2017
Accepted: 06 Apr 2018
Published online: 16 Nov 2018 *