Neural-network-based maximum-power-point tracking of coupled-inductor interleaved-boost-converter-supplied PV system using fuzzy controller

The photovoltaic (PV) generator exhibits a nonlinear V-I characteristic and its maximum power (MP) point varies with solar insolation. In this paper, a feedforward MP-point tracking scheme is developed for the coupled-inductor interleaved-boost-converter-fed PV system using a fuzzy controller. The p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial electronics (1982) 2003-08, Vol.50 (4), p.749-758
Main Authors: Veerachary, M., Senjyu, T., Uezato, K.
Format: Article
Language:English
Subjects:
Control systems
Error correction
Fuzzy control
Fuzzy systems
Neural networks
Pulse generation
Signal generators
Solar power generation
Studies
Switches
Switching converters
Voltage
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The photovoltaic (PV) generator exhibits a nonlinear V-I characteristic and its maximum power (MP) point varies with solar insolation. In this paper, a feedforward MP-point tracking scheme is developed for the coupled-inductor interleaved-boost-converter-fed PV system using a fuzzy controller. The proposed converter has lower switch current stress and improved efficiency over the noncoupled converter system. For a given solar insolation, the tracking algorithm changes the duty ratio of the converter such that the solar cell array voltage equals the voltage corresponding to the MP point. This is done by the feedforward loop, which generates an error signal by comparing the instantaneous array voltage and reference voltage corresponding to the MP point. Depending on the error and change of error signals, the fuzzy controller generates a control signal for the pulsewidth-modulation generator which in turn adjusts the duty ratio of the converter. The reference voltage corresponding to the MP point for the feedforward loop is obtained by an offline trained neural network. Experimental data are used for offline training of the neural network, which employs a backpropagation algorithm. The proposed peak power tracking effectiveness is demonstrated through simulation and experimental results. Tracking performance of the proposed controller is also compared with the conventional proportional-plus-integral-controller-based system. These studies reveal that the fuzzy controller results in better tracking performance.
ISSN:0278-0046
1557-9948
DOI:10.1109/TIE.2003.814762