The modeling of directional overcurrent relay in loop system using cascade forward neural network

The problems arising in loop electrical network system is a relay setting that follows changes in the system such as power source operation, regular maintenance and damage to powers source. To obtain an adaptive relay which is capable of following the changes in the network system, this paper is proposes the modeling of the coordination of the power system network with the cascade forward neural network (CFNN) by simulating three power sources, fifteen protection relays, six buses, and three loads. CFNN applied in the directional overcurrent relay (DOCR) curve model using sample data from protection coordination in loop electrical network system. On the modeling process by comparing some number of neurons and learning rate to get the best accuracy and time speed with four combination input and two outputs. The results of modeling relay using CFNN method showed mean square error of 3,24e-06 with a current contribution of 95% and mean square error of 2,10e-03 with a current contribution of 105% and from modeling is very accurate and can be applied to digital overcurrent relay.