Ag. Jongepier et L. Vandersluis, ADAPTIVE DISTANCE PROTECTION OF DOUBLE-CIRCUIT LINES USING ARTIFICIALNEURAL NETWORKS, IEEE transactions on power delivery, 12(1), 1997, pp. 97-105
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.