A new approach to power system protection in distribution network with DG units by using radial basis function neural network

The presence of distributed generation (DG) units in a distribution system will greatly affect the configuration and operation mode of the power system, especially with respect to the protection scheme. This paper presents a new approach to power system protection using radial basis function neural network (RBFNN) for a distribution system with DG units. In the proposed method, the fault type is determined first by normalizing the fault currents of the main source. For implementing fault location considering various types of faults, two staged RBFNNs have been developed. The first RBFNN is used for determining the fault distance from each power source and the second RBFNN is used for identifying the faulty line. To isolate the fault another RBFNN has been developed for determining which circuit breakers (CBs) that must be open or close. Several case studies have been made to verify the accuracy of the proposed method for fault diagnosis in a distribution system with DGs using a MATLAB based developed software and DlgSILENT Power Factory 14.0.524. The predicted results showed that the proposed RBFNN based protection method can accurately determine the location of faults and isolate the faulted line in the test power system.