Artificial neural network based islanding detection technique for mini hydro type distributed generation

The integration of distributed generation in conventional radial distribution system provides improvement in power quality and enhancement in the power supply capacity. However, this integration changes the nature of distribution system from passive to active and has given rise to certain technical issues. The occurrence of islanding is one of the important issues in this context. This paper presents a new islanding detection technique based on artificial neural network. The proposed technique uses rate of change of frequency, rate of change of voltage, rate of change of active power, and rate of change of reactive power as the ANN inputs. The appropriate data base of various islanding and non islanding cases is created for training the ANN. The ANN test results ensure that proposed method is able to classify accurately islanding and non islanding events and has zero non detection zone.