Application of Artificial Intelligence
Techniques for Improvement of Power
Quality Using Hybrid Filters
Soumya Ranjan Das, Prakash K. Ray, Asit Mohanty and Tapas K. Panigrahi
Abstract The present paper implements a Shunt Hybrid Active Filter (SHAF) essen-
tial for reactive power suppression across the load and eradicates harmonics in devel-
oping the power quality (PQ) under variable source and load conditions in the dis-
tribution network. For better compensation features, SHAF employing the harmonic
reduction performance of both passive filter and active filter is presented in this paper.
In this work, an adaptive linear neuron (ADALINE) based Variable step size leaky
least mean square (VSSLLMS) control approach is applied to examine the operation
of SHAF in a three-phase system. This competent approach is needed for gener-
ating the gating pulses essential for IGBT inverter and increasing the performance
compared to the conventional ADALINE-LMS controller. The proposed controller
provides faster convergence and also provides better performance compared to con-
ventional one. Simulation results show the significant improvement in ADALINE-
VSSLLMS approach compared to ADALINE-LMS approach. The simulations of
the proposed system under different load and source conditions are performed using
MATLAB/SIMULINK.
Keywords ADALINE · LMS algorithm · Shunt Hybrid Active Filter (SHAF) ·
Variable Step Size Leaky Least Mean Square (VSSLLMS) · Total Harmonic
Distortion (THD)
S. R. Das
Department of Electrical and Electronics Engineering, IIIT Bhubaneswar, Khurda 751003, India
e-mail: srdas1984@gmail.com
P. K. Ray (B ) · A. Mohanty
Department of Electrical Engineering, CET Bhubaneswar, Bhubaneswar 751003, India
e-mail: pkrayiiit@gmail.com
A. Mohanty
e-mail: asithimansu@gmail.com
T. K. Panigrahi
Department of Electrical Engineering, PMEC Berhampur, Brahmapur 761003, India
e-mail: tkpanigrahi.ee@pmec.ac.in
© Springer Nature Singapore Pte Ltd. 2020
H. S. Behera et al. (eds.), Computational Intelligence
in Data Mining, Advances in Intelligent Systems and Computing 990,
https://doi.org/10.1007/978-981-13-8676-3_61
719