TY - GEN
T1 - The modeling of directional overcurrent relay in loop system using cascade forward neural network
AU - Sahrin, Alfin
AU - Tjahjono, Anang
AU - Pujiantara, Margo
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/28
Y1 - 2017/11/28
N2 - 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.
AB - 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.
KW - Cascade forward neural network
KW - Digital overcurrent
KW - Directional overcurrent relay
KW - Protection relay
UR - http://www.scopus.com/inward/record.url?scp=85043515293&partnerID=8YFLogxK
U2 - 10.1109/ISITIA.2017.8124057
DO - 10.1109/ISITIA.2017.8124057
M3 - Conference contribution
AN - SCOPUS:85043515293
T3 - 2017 International Seminar on Intelligent Technology and Its Application: Strengthening the Link Between University Research and Industry to Support ASEAN Energy Sector, ISITIA 2017 - Proceeding
SP - 69
EP - 74
BT - 2017 International Seminar on Intelligent Technology and Its Application
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th International Seminar on Intelligent Technology and Its Application, ISITIA 2017
Y2 - 28 August 2017 through 29 August 2017
ER -