ANN Based Distance Protection of High Voltage Transmission Line

Abstract

This abstract illustrates distance protection scheme for high voltage power transmission line by using Principal Component Analysis (PCA) and Artificial Neural Network (ANN) methods. Discrimination between internal, external fault and power swing condition is a very challenging task in transmission line distance protection scheme due to large power system parameter variations and their complex structure. Therefore, instead of impedance or amplitude of current or voltage-based approach this thesis used waveform-based approach that uses waveform of local end three phase voltages and currents, and then PCA is used to reduce the dimensions of these voltages and currents samples that is utilized to train and test different ANNs for detection of faults in internal zone, classification of fault types and also for the identifying fault location (km). The power transmission line is modelled in PSCAD/EMTDC software to obtain the relaying under different operating conditions. The proposed algorithm is evaluated in MATLAB under different operating conditions during Power Transfer and the tested data is simulated in PSCAD/EMTDC by varying inception angle, fault location, fault resistances, power angle and fault types. Results show that the proposed algorithm is simple, reliable, selective and fast under different operating conditions of high voltage power transmission line.