A robust wavelet-ANN based technique for islanding detection

A simple and robust approach for islanding detection is introduced in this paper. The proposed approach detects islanding using the transient signals. The three phases' currents seen at the DG terminals are combined into one modal signal that fully represents the system. The feature vector is extracted from the selected modal current signal utilizing discrete wavelet transform. The extracted feature vector is then used to train an artificial neural network to detect islanding. Based on the training results the proposed approach was modified to obtain the characteristic signature that characterizes islanding events thus the computational burden is reduced to minimum. Tests were conducted on the proposed algorithm to validate its robustness. Test results showed that the algorithm is reliable and fast.