Data Mining-Based Method to Reduce Multiple Estimation for Fault Location in Radial Distribution Systems

Author(s)

Reche, Evandro Agostinho ^[1] ; de Sousa, Jeovane Vicente ^[1] ; Coury, Denis Vinicius ^[1] ; Souza Fernandes, Ricardo Augusto ^[2]

Affiliation

^[1] Univ Sao Paulo, Sao Carlos Sch Engn, Dept Elect & Comp Engn, BR-13566590 Sao Carlos, SP - Brazil

^[2] Univ Fed Sao Carlos, Dept Elect Engn, BR-13565905 Sao Carlos, SP - Brazil

• Document type: Journal article
• Source: IEEE TRANSACTIONS ON SMART GRID; v. 10, n. 4, p. 3612-3619, JUL 2019.
• Web of Science Citations: 2

Abstract

This paper presents an approach to reduce the multiple estimation effect of fault location algorithms. This effect occurs in fault location techniques based on fault distance estimation concerning radial distribution feeders. This approach is based on a data mining technique called data mining of code repositories (DAMICORE). This tool is executed from the perspective of cloud computing in the context of smart grids. It is noteworthy that the voltage and current signals are received by a cloud using smart meters and disturbance recorders. Thus, this cloud receives a feature vector that is extracted by them from the signals acquired. Considering this, the cloud becomes responsible for executing the DAMICORE which, in turn, defines relations among the faulty events. The IEEE 34-Bus Test Feeder was simulated as the test case system. Moreover, the data mining process was able to reduce errors due to the multiple estimation of faulty branches. (AU)

• FAPESP's process: 17/16742-7 - Microgrids:Identification and solution of problems in hybrid distributed generation systems
• Grantee: Denis Vinicius Coury
• Support Opportunities: Regular Research Grants