In this paper, a novel adaptive current control technique is proposed, to transfer the improved quality of green energy from a PV plant to the customers as well as to the power grid. Parallely, a high-gain-high-efficient DC-DC converter driven by Kalman-MPPT logic is also proposed to boost the PV array voltages. The proposed adaptive controller follows RNN-Hebbian-LMS based adaptive control algorithm to achieve better performance in terms of system power quality. The Hebbian-LMS (least mean square) algorithm is used to update the weights of the recurrent neural network (RNN) based current controller. The aim of the RNN-Hebbian-LMS control technique is to maintain constant voltage regardless of any system hindrances. Besides, it also provides system stability over wide range of parameter drifting and damp out the system oscillations quickly. The proposed control algorithm along with the high-gain-high-efficient converter performs outstanding in overcoming the stability and sensitivity issues incurred in conventional PI controller. Comparative results for conventional PI and proposed RNN-Hebbian-LMS current controllers are presented to shows the improvement in power quality, settling time and stable operation obtained with the proposed control scheme.
Moushumi Patowary, with a cross-discipline experiences for more than 9years, is currently pursuing the Ph.D. degree in electrical engineering from the National Institute of Technology Meghalaya, India. Her research interests include Distributed Power Generation using Renewable Energy Sources, Modeling and Control of Microgrid, AI techniques, Power Quality Assessment, Power System Reliability Evaluation, Reliability Assessment on Distributed Generation.