PV boost converter conditioning using neural network
This master report presents a voltage control system for DC-DC boost converter integrated with Photovoltaic (PV) array using optimized feed-forward neural network controller. A specific output voltage of a boost converter is regulated at a constant value under input voltage variations caused by a...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/6627/1/24p%20AIZAT%20ABD%20AZIZ.pdf http://eprints.uthm.edu.my/6627/2/AIZAT%20ABD%20AZIZ%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/6627/3/AIZAT%20ABD%20AZIZ%20WATERMARK.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This master report presents a voltage control system for DC-DC boost converter
integrated with Photovoltaic (PV) array using optimized feed-forward neural network
controller. A specific output voltage of a boost converter is regulated at a constant
value under input voltage variations caused by a sudden changes in irradiation for a
purpose of supplying a stabilize dc voltage to Base Transceiver Station (BTS)
telecommunication equipment that required a 48V dc input supply to be operated.
For a given solar irradiance, the tracking algorithm changes the duty ratio of the
converter such that the output voltage produced equals to 48V. This is done by the
feed-forward loop, which generates an error signal by comparing converter output
voltage and reference voltage. Depending on the error and change of error signals,
the neural network controller generates a control signal for the pulse widthmodulation
generator which in turn adjusts
the duty ratio of the converter. The
effectiveness
of the proposed method
is verified
by developing a simulation
model
in
MATLAB-Simulink
program.
Tracking performance
of the proposed controller is
also
compared
with the conventional
proportional-integral-differential
(PID)
controller.
The simulation
results
show that the proposed neural
network controller
(NNC)
produce an improvement
of control
performance
compared
to the PID
controller. |
|---|