Neural network application in directional comparison carrier protection of EHV transmission lines

The increasing scale and complexity of power systems require high performance and high reliability of power system protection. Protective relaying based on directional comparison with power line carrier or microwave channels is the most suitable protection scheme for long distance EHV transmission lines and widely used in power systems. The key element of such protection is the directional relay used to discriminate fault direction. In order to overcome the disadvantages of conventional directional relays, the authors of this paper put forward a directional comparison carrier protection scheme based on artificial neural networks (ANNs). The protection is extensively tested using the electromagnetic transient program (EMTP) under various electric power system operating and fault conditions. It is proved that the directional comparison carrier protection based on ANNs, which can recognize various fault patterns of the protected transmission line (such as fault direction, fault phases, etc.) correctly under any kind of operating and fault conditions and the whole process, is satisfactory for EHV transmission line protection