Traveling-Wave Fault Location Techniques in Power System Based on Wavelet Analysis and Neural Network Using GPS Timing

In this paper four fault location algorithms based on discrete wavelet transform using global positioning system are described and compared. In two approaches, the location of fault is determined according to arrival instances of traveling waves and in two other approaches, the non-linear relations are simulated by artificial neural network to improve the responses. All the possible fault types are generated using the ATP-EMTP and results using the four methods are discussed. Extensive simulation studies indicate that proposed networks decrease errors percentages of two wavelet-based approaches from 0.35 to 0.22 and 0.21 to less than 0.15 %, respectively, though exploiting small size data base for training.