Articles «Previous Next»

Performance Comparison of MLP and RBF Neural Networks for Fault Location in Distribution Networks with DGs

Hadi Zayandehroodi, Universiti Kebangsaan Malaysia(UKM)
Azah Mohamed, Universiti Kebangsaan Malaysia(UKM)
Hussain Shareef, Universiti Kebangsaan Malaysia(UKM)
Marjan Mohammadjafari, Islamic Azad University, Kerman, Iran

Abstract

With high penetration of distributed generations (DGs), power distribution system is regarded as a multisource system in which fault location scheme must be direction sensitive. This paper presents an automated fault location method using radial basis function neural network (RBFNN) for a distribution system with DG units. In the proposed method, the fault type is first determined by normalizing the fault currents of the main source and then fault location is predicted by using RBFNN. Several case studies have been considered to verify the accuracy of the RBFNN. A comparison is also made between the RBFNN and the conventional multilayer perceptron neural network for locating faults in a power distribution system with DGs. The test results showed that the RBFNN can accurately determine the location of faults in a distribution system with several DG units.

Suggested Citation

Hadi Zayandehroodi, Azah Mohamed, Hussain Shareef, and Marjan Mohammadjafari. "Performance Comparison of MLP and RBF Neural Networks for Fault Location in Distribution Networks with DGs" IEEE International Conference on Power and Energy (PECon2010) (2010): 341-345.