Enhanced R package-based cluster analysis fault identification models for three phase power system network
by K. Nithiyananthan; Pratap Nair; Raman Raguraman; Tan Yong Sing; Syahrel Emran Bin Siraj
International Journal of Business Intelligence and Data Mining (IJBIDM), Vol. 14, No. 1/2, 2019

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.

Online publication date: Tue, 11-Dec-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Intelligence and Data Mining (IJBIDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com