Authors :
Ezechukwu .O. A; Chukwuagu. M.I; Ezendiokwelu C. E
Volume/Issue :
Volume 7 - 2022, Issue 3 - March
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3LbcO29
DOI :
https://doi.org/10.5281/zenodo.6471762
Abstract :
In this work neural network controlled UPFC
and TCSC device was used for the reduction of losses in
power transmission network. The main problem
addressed in this work is the optimal placements and
control of UPFC and TCSC for the minimization of
power transmission networks. To address these
problems, Artificial Neural networks and genetic
algorithm be used for the control and placements of the
FACTS devices respectively for optimal active power
loss reduction. The novel contribution of this work is to
produce a model and train ANN for UPFC control using
critical disruptive voltage and thyrist or firing and
variation. Genetic algorithm was used for the optimal
placement of the FACTS devise in the
MATLAB/SIMULINK model of the Nigeria 330KV
transmission system. Findings showed that the proposed
neural network controlled UPFC achieved better active
and reactive power loss reduction that the TCSC. It
outperformed the TCSC by 6.08% in the reduction of
active loss and by 15.34% in the reduction of reactive
power loss in the power system.
Keywords :
TRAINING, NEURAL NETWORK, UPFC, TCSC.
In this work neural network controlled UPFC
and TCSC device was used for the reduction of losses in
power transmission network. The main problem
addressed in this work is the optimal placements and
control of UPFC and TCSC for the minimization of
power transmission networks. To address these
problems, Artificial Neural networks and genetic
algorithm be used for the control and placements of the
FACTS devices respectively for optimal active power
loss reduction. The novel contribution of this work is to
produce a model and train ANN for UPFC control using
critical disruptive voltage and thyrist or firing and
variation. Genetic algorithm was used for the optimal
placement of the FACTS devise in the
MATLAB/SIMULINK model of the Nigeria 330KV
transmission system. Findings showed that the proposed
neural network controlled UPFC achieved better active
and reactive power loss reduction that the TCSC. It
outperformed the TCSC by 6.08% in the reduction of
active loss and by 15.34% in the reduction of reactive
power loss in the power system.
Keywords :
TRAINING, NEURAL NETWORK, UPFC, TCSC.
