Islanding detection for grid integrated distributed generation using adaptive neuro-fuzzy inference system

To ensure the safety of line workers and the general public, safety of customer and utility equipment, prevent mis-operation of power system protective equipment, prevent power quality issues and ensure the general security of the power system, connection standards for DG require that islanding be quickly detected and consequently distributed generation(DG) sources be quickly disconnected. In this paper an Adaptive Neuro-fuzzy Inference System (ANFIS) is proposed for detecting islanding in integrated distribution power networks. The proposed ANFIS method is based on the parameters of the passive islanding detection mechanism. Voltage, rate of change of frequency (ROCOF) and rate of change of power (ROCOP) are the inputs used for the training and validation of the proposed islanding detection method. The test power system for generating the data used for the training of the ANFIS network and evaluating the performance of the proposed islanding detection technique is a segment of the South-East Nigeria 33/11KV power distribution network. Time performance region and Non-detection Zone (NDZ) was employed in the evaluation of the scheme. Results from simulations carried out showed that the ANFIS islanding detection method detected islanding faster than the frequency relay method and that, in all cases simulated, the proposed method showed a smaller NDZ than the frequency relay islanding detection method.