TY - EJOU
AU - Sujith, M.
AU - Padma, S.
TI - Implementation of PSOANN Optimized PI Control Algorithm for Shunt Active Filter
T2 - Computer Modeling in Engineering \& Sciences
PY - 2020
VL - 122
IS - 3
SN - 1526-1506
AB - This paper proposes the optimum controller for shunt active filter (SAF) to
mitigate the harmonics and maintain the power quality in the distribution system. It consists
of shunt active filter, Voltage Source Inverter (VSI), series inductor and DC bus and nonlinear load. The proposed hybrid approach is a combination of Particle Swarm
Optimization (PSO) and Artificial Neural Network (ANN) termed as PSOANN. The PI
controller gain parameters of kp and ki are optimized with the help of PSOANN. The
PSOANN improves the accuracy of tuning the gain parameters under steady and dynamic
load conditions; thereby it reduces the values of THD within the prescribed limits of IEEE
519. The PSO optimizes the dataset of terminal voltage and DC voltage present in shunt
active filter for different load condition. The optimized dataset acts as the input for the
controller to predict the optimal gain with minimal error and to generate the optimized
control signal for the SAF. The proposed methodology is modelled and simulated with the
help of MATLAB/Simulink platform and illustrated the few test cases considered for
exhibiting the performance of proposed hybrid controller. The experimental results are
measured with developed laboratory prototype and compared with the simulation results to
validate the effectiveness of the proposed control methodology.
KW - Artificial neural network
KW - particle swarm optimization
KW - shunt active filter
KW - voltage source inverter
KW - total harmonic distortions
DO - 10.32604/cmes.2020.08908