ADAPTIVE DISTANCE PROTECTION OF DOUBLE-CIRCUIT LINES USING ARTIFICIALNEURAL NETWORKS

Because of the zero sequence mutual coupling of parallel circuits, the distance calculation performed by a ground distance relay is incorrec t. This error is influenced by the actual power system condition. Alth ough accounted for by using a large safety margin in the zone boundari es, unexpected overreach can still occur and the operation speed is de creased. Adaptive protection offers an approach to compensate for the influence of the variable power system conditions. By adapting the rel ay settings to the actual power system condition, the relay will respo nd more accurately to power system faults. The selectivity of the prot ection system is increased, as is the power system reliability. In thi s paper, an adaptive distance relaying concept is presented. In order to minimize the required communication, local measurements are used to estimate the entire power system condition. An artificial neural netw ork is used to estimate the actual power system condition and to calcu late the appropriate tripping impedance. Application of this concept t o the model of the Dutch 380 kV power system has resulted in an enormo us increase in relaying accuracy. The relaying error is reduced substa ntially. Most importantly, the standard deviation, indicating the rela y's sensitivity to power system condition variations, is reduced to ne arly zero. The zone boundary is kept nearly constant. which facilitate s the relay coordination. The selectivity of the entire power system p rotection system is improved. It is shown that adaptive protection imp roves the protection system selectivity, and that artificial neural ne tworks can very well be used to estimate the actual power system condi tion.