Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation

International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 3 Issue 5, August 2019
@ IJTSRD | Unique Paper ID – IJTSRD27867
Artificial Neural Network
System Modeling
Myint Thuzar
1,2Department of Electrical Power Engineering,
How to cite this paper: Myint Thuzar |
Cho Hnin Moh Moh Aung"ArtificialNeural
Network for Solar Photovoltaic System
Modeling and Simulation" Published in
International
Journal of Trend in
Scientific Research
and Development
(ijtsrd), ISSN: 2456-
6470, Volume-3 |
Issue-5, August
2019,pp.2110-2114,
https://doi.org/10.31142/ijtsrd27867
Copyright © 2019 by author(s) and
International Journal ofTrend inScientific
Research and Development Journal. This
is an Open Access article distributed
under the terms of
the Creative
Commons Attribution
License (CC BY 4.0)
(http://creativecommons.org/licenses/by
/4.0)
In this paper, we presented neural network based MPPT
method. Artificial Neural Network (ANN) is an artificial
network that can able to mimic the human biological neural
networks behavior. ANN widely used in modeling complex
relationships between inputs and outputs
systems. ANN can also be defined as parallel distributed
information processing structure. The ANN consists of
inputs, and at least one hidden layer and one output layer.
These layers have processing elements which are called
neurons interconnected together. To calculate error
contribution of each neuron after a batch of data processing
a method called ‘back propagation’is used.Back propagation
is commonly used by the gradient descent optimization
algorithm to adjust the weight of neurons by
gradient of the loss function. This technique is also called
back propagation error. This is because the error is
calculated at the output and circulated back through the
network layers.[5] At the end, the result based on the
simulation of the data collected from the photovoltaic array
system is used to train the neutral network and output
efficiency of the designed DC-DC boot converter with MPPT
control strategy is accepted the maximum power amount
and showed the result voltage, current and
each different have been recorded.
2. MATHEMATICAL MODELING of PV ARRAY
The reference modules of PV array is 200.143 W. The basic
building block of PV arrays is the solar cell,whichis basically
a p-n semiconductor junction, shown in Figure 1.[6]
IJTSRD27867
Volume 3 Issue 5, August 2019 Available Online: www.ijtsrd.com e-
27867 | Volume – 3 | Issue – 5 | July - August 2019
Artificial Neural Network for Solar Photovoltaic
System Modeling and Simulation
Myint Thuzar1, Cho Hnin Moh Moh Aung2
1Professor, 2Student
Department of Electrical Power Engineering, Mandalay Technological University, Mandalay, Myanmar
http://creativecommons.org/licenses/by
ABSTRACT
This paper presented neural network based maximum power point tracking
on the design of photovoltaic power input to a DC
load. Simulink model of photovoltaic array tested the neural network with
different temperature and irradiance for maximum power point of a
photovoltaic system. DC-DC boot converter is used in load when an average
output voltage is stable required which can be lower thantheinputvoltage.At
the end, the different temperature and irradiance of the data collected
the photovoltaic array system is used to train the neutral network and output
efficiency of the designed DC-DC boot converter with MPPTcontrolstrategyis
accepted the maximum power amount to show the result voltage,currentand
power output for each different have been presented. And also
that the neural network based MPPT tracking require less time and more
accurate results than the other algorithm based MPPT
KEYWORDS: NeuralNetwork;MaximumPower Point;Irradiance& Temperature;
DC-DC Boot Converter
1. INTRODUCTION
The main principle of MPPT is responsible for extractingthemaximumpossible
power from the photovoltaic and feed it to the load via DC to DC converter
which steps up/steps down the voltage to required magnitude.
techniques have been used in past but Perturb & Observe (P&O) algorithm is
most widely accepted. [1,2] P&O algorithm has also been shown to provide
wrong tracking with rapidly varying irradiance.[3
per, we presented neural network based MPPT
method. Artificial Neural Network (ANN) is an artificial
network that can able to mimic the human biological neural
networks behavior. ANN widely used in modeling complex
relationships between inputs and outputs in nonlinear
systems. ANN can also be defined as parallel distributed
information processing structure. The ANN consists of
inputs, and at least one hidden layer and one output layer.
These layers have processing elements which are called
ected together. To calculate error
contribution of each neuron after a batch of data processing
a method called ‘back propagation’is used.Back propagation
is commonly used by the gradient descent optimization
algorithm to adjust the weight of neurons by calculating the
gradient of the loss function. This technique is also called
back propagation error. This is because the error is
calculated at the output and circulated back through the
network layers.[5] At the end, the result based on the
the data collected from the photovoltaic array
system is used to train the neutral network and output
DC boot converter with MPPT
control strategy is accepted the maximum power amount
poweroutputfor
MATHEMATICAL MODELING of PV ARRAY
The reference modules of PV array is 200.143 W. The basic
building block of PV arrays is the solar cell,whichis basically
Figure 1.[6]
The following equations define the model of a PV panel:
shdoutph IIII 
 








 

KTN
IRVq
expII
s
s
satd
shdphout IIII 
 








 

s
satphout
nKT
IRVq
expIII
In this equations, Isat is the reverse saturated current of
diode, q is the electron charge, V is the voltage across the
-ISSN: 2456 – 6470
August 2019 Page 2110
Solar Photovoltaic
nd Simulation
Mandalay Technological University, Mandalay, Myanmar
This paper presented neural network based maximum power point tracking
on the design of photovoltaic power input to a DC-DC boot converter to the
load. Simulink model of photovoltaic array tested the neural network with
for maximum power point of a
DC boot converter is used in load when an average
output voltage is stable required which can be lower thantheinputvoltage.At
the end, the different temperature and irradiance of the data collected from
the photovoltaic array system is used to train the neutral network and output
DC boot converter with MPPTcontrolstrategyis
accepted the maximum power amount to show the result voltage,currentand
different have been presented. And also demonstrated
that the neural network based MPPT tracking require less time and more
accurate results than the other algorithm based MPPT.
NeuralNetwork;MaximumPower Point;Irradiance& Temperature;
The main principle of MPPT is responsible for extractingthemaximumpossible
power from the photovoltaic and feed it to the load via DC to DC converter
which steps up/steps down the voltage to required magnitude. Various MPPT
techniques have been used in past but Perturb & Observe (P&O) algorithm is
P&O algorithm has also been shown to provide
wrong tracking with rapidly varying irradiance.[3-4]
The following equations define the model of a PV panel:
(1)



1
(2)
(3)





 






sh
s
R
IRV
1
(4)
In this equations, Isat is the reverse saturated current of
diode, q is the electron charge, V is the voltage across the

diode, I is output current, Rse is series resistance, Rsh is
shunt resistance, n is ideality factor of the diode, k is the
Boltzman’s constant and T is the junction temperature in
Kelvin.
Figure2 Typical I-V and PV characteristics of a PV
module [7]
In the figure can be observe that at voltage Vm the power is
at the maximum. This is the maximum power point of PV
characteristics that we need to track using MPPT algorithm.
A. Modeling and Simulation of PV Array
For the modeling of PV array, we used MATLAB Simulink.
The simulation model is based on equations 1 to 4. Simulink
model of PV array subsystem is constructed and P
characteristics of the PV array with different irradiance and
temperature are shown in Figure 3 & Figure 4.
TABLE I. Parameters of the KC200GT PV Module at
25°C
Parameters Symbols
Current at Maximum Power Imax
Voltage at Maximum Power Vmax
Maximum Power Pmax
Short Circuit Current Isc
Open Circuit Voltage Voc
Ideality Factor Ns
Figure 3 P-V Characteristics of PV Array Various
irradiance
International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com
diode, I is output current, Rse is series resistance, Rsh is
shunt resistance, n is ideality factor of the diode, k is the
onstant and T is the junction temperature in
V and PV characteristics of a PV
In the figure can be observe that at voltage Vm the power is
at the maximum. This is the maximum power point of PV
need to track using MPPT algorithm.
Modeling and Simulation of PV Array
For the modeling of PV array, we used MATLAB Simulink.
The simulation model is based on equations 1 to 4. Simulink
model of PV array subsystem is constructed and P-V
of the PV array with different irradiance and
temperature are shown in Figure 3 & Figure 4.
TABLE I. Parameters of the KC200GT PV Module at
Symbols Ratings
7.62 A
26.3 A
200.143 W
8.21 A
32.9 V
54
V Characteristics of PV Array Various
Figure4 P-V Characteristics of PV Array Various
temperature
From Figures, we saw with irradiance increased, power
increased and temperature increased, power decrease.
Hence, this Simulink model is determine the characteristics
of PV array. Hence the Simulink model is correct.
3. MATHEMATICAL EQUATION of DC
CONVERTER
D =
I =
d = I × I ×
𝐿 =
×( )
C =
×
Where, D = duty cycle of the boot converter; Vin = input
voltage of the PV module; Vout = output voltage of
converter; Iout= output current of the boot converter;Pout=
output power of the boot converter; Iripple= ripple current
of the inductor; L= inductor of the boost converter; C=
capacitor of the boot converter.
Figure 5 DC-DC Boot Converters and Con
Algorithm [8]
www.ijtsrd.com eISSN: 2456-6470
V Characteristics of PV Array Various
temperature
Figures, we saw with irradiance increased, power
increased and temperature increased, power decrease.
Hence, this Simulink model is determine the characteristics
of PV array. Hence the Simulink model is correct.
MATHEMATICAL EQUATION of DC-DC BOOT
(5)
(6)
(7)
(8)
(9)
Where, D = duty cycle of the boot converter; Vin = input
voltage of the PV module; Vout = output voltage of the
converter; Iout= output current of the boot converter;Pout=
output power of the boot converter; Iripple= ripple current
of the inductor; L= inductor of the boost converter; C=
capacitor of the boot converter.
DC Boot Converters and Control
Algorithm [8]

The principle drives the boost converter is the tendency of
an inductor to resist changes in the current. When being
charged it acts as a load and absorbs energy; when being
discharged it acts as an energy source. The voltage it
produces during the discharge phase is related to the rate of
change of current, and not to the original charging voltage,
thus allowing different input from the PV array and output
voltages to the DC load. In MPPT systems, this signal is
controlled by MPPT controller is shown in proposed model
in Figure 6. By changing the duty cycletheloadimpedance as
seen by the source is varied and matched at the point of the
peak power with the source so as to transfer the maximum
power. The simulation results of the solar P
controller algorithm is shown in Figure 7.
TABLE II. Parameter of DC Load for Simulation
Parameters Specification
Constant Torque 0.9 Nm
Initial Speed 10 rad/s
Armature Resistance 1.2 Ω
Inductance, La 2.4 mH
TABLE III. Parameter of DC-DC Boot Converter
Simulation Result
Parameters Ratings
Output Current 4.5 A
Input Voltage 26.3 A
Power Converter 200.143 W
Switching Frequency 20 kHz
Output Voltage 45 V
Inductance 0.1774 mH
Capacitance 220.7 µF
Figure6 Simulink Model of DC-DC Boot Converter
Figure7 Outputs and Input Voltage of Boot Converter
The principle drives the boost converter is the tendency of
an inductor to resist changes in the current. When being
charged it acts as a load and absorbs energy; when being
discharged it acts as an energy source. The voltage it
during the discharge phase is related to the rate of
change of current, and not to the original charging voltage,
thus allowing different input from the PV array and output
voltages to the DC load. In MPPT systems, this signal is
ller is shown in proposed model
in Figure 6. By changing the duty cycletheloadimpedance as
seen by the source is varied and matched at the point of the
peak power with the source so as to transfer the maximum
power. The simulation results of the solar PV with MPPT
TABLE II. Parameter of DC Load for Simulation
Specification
0.9 Nm
10 rad/s
1.2 Ω
2.4 mH
Boot Converter
Ratings
4.5 A
26.3 A
200.143 W
20 kHz
45 V
0.1774 mH
220.7 µF
Boot Converter
7 Outputs and Input Voltage of Boot Converter.
A. Artificial Neural Network Base MPPT Technique
In this work, the Levenberg
implemented using MATLAB to train the neural network.
The Levenberg-Marquardt method is
accurate technique for solving nonlinear least squares
problems. Since thevariations oftemperatureandirradiance
effect are highly nonlinear in producing the output power
and voltage, we decided to use the LevenbergMarquardt
algorithm to train the neural network. The following steps
describe how we implement theneural network basedMPPT
for a PV array.[9,10].
B. Selecting Network Structure
The input information is connected to the hidden layers
through weighted interconnections wherethe
calculated. The number of hidden layers and the number of
neurons in each layer controls the performance of the
network. Neural network is a trial and error design method.
The ANN developed in this paper with two inputs solar
irradiance and temperature, oneoutputlayerconsistsoftwo
neurons (Vmax, Pmax) and one hidden layer, shown in
Figure 8.
Figure8 Block Diagram of ANN with Two Layers
C. Collecting Data and Training the Network
The Simulink model of PV array is simulated for a range
solar irradiances and temperatures to find corresponding
Pmax and Vmax shown in Figure 9. The training points are
passed into the designed network to teach it how toperform
when different points than thetrainingpointsareinserted to
it. After training of the neural network is completed, then 5
of the collected data points are used as test points. The
function of test points is to evaluate the performance of the
designed ANN after its training is finished. The error is then
feedback to the neural network for further training. The
network is trained using the MATLAB NNET tool box.
Artificial Neural Network Base MPPT Technique
In this work, the Levenberg-Marquardt algorithm is
implemented using MATLAB to train the neural network.
Marquardt method is a very fast and
accurate technique for solving nonlinear least squares
problems. Since thevariations oftemperatureandirradiance
effect are highly nonlinear in producing the output power
and voltage, we decided to use the LevenbergMarquardt
o train the neural network. The following steps
describe how we implement theneural network basedMPPT
Selecting Network Structure
The input information is connected to the hidden layers
through weighted interconnections wheretheoutput data is
calculated. The number of hidden layers and the number of
neurons in each layer controls the performance of the
network. Neural network is a trial and error design method.
The ANN developed in this paper with two inputs solar
temperature, oneoutputlayerconsistsoftwo
neurons (Vmax, Pmax) and one hidden layer, shown in
Figure8 Block Diagram of ANN with Two Layers
Collecting Data and Training the Network
The Simulink model of PV array is simulated for a range of
solar irradiances and temperatures to find corresponding
Pmax and Vmax shown in Figure 9. The training points are
passed into the designed network to teach it how toperform
when different points than thetrainingpointsareinserted to
ing of the neural network is completed, then 5
of the collected data points are used as test points. The
function of test points is to evaluate the performance of the
designed ANN after its training is finished. The error is then
work for further training. The
network is trained using the MATLAB NNET tool box.

Figure 9 Training the Neural Network with MATLAB
NNET toolbox
D. Result and Discussion for Neural Network MPPT
The network which was fully trained withthelowest error
capable to be used in the testing process.Performanceresult
of ANN to minimize the RMS error in the training
performance curve. Network was trained until it achieved a
very small MSE typically 6.19e-06 which reached after 6
epochs. We can observe that the outputs from the neural
model closely match the target values. For 5 new testing
input irradiance and temperature data points the neural
network has been tested. In shown in Figure 11 to Figure 16
we can see that, at each time, the neural network prov
Pmax and Vmax data points clearly matched with measured
data points from the actual Simulink model.
Figure10 Simulink Model Data Collection for ANN
Figure11 Vmax from Neural Network and actual
Simulink model with different temperature testing
point
Figure 9 Training the Neural Network with MATLAB
Result and Discussion for Neural Network MPPT
The network which was fully trained withthelowest error is
capable to be used in the testing process.Performanceresult
of ANN to minimize the RMS error in the training
performance curve. Network was trained until it achieved a
06 which reached after 6
the outputs from the neural
model closely match the target values. For 5 new testing
input irradiance and temperature data points the neural
network has been tested. In shown in Figure 11 to Figure 16
we can see that, at each time, the neural network provided
Pmax and Vmax data points clearly matched with measured
data points from the actual Simulink model.
10 Simulink Model Data Collection for ANN
Figure11 Vmax from Neural Network and actual
Figure12 Imax from Neural Network and actual
point
Figure13 Pmax from Neural Network and actual
point
.
Figure 14 Vmax from Neural Network and
Simulink model with different irradiance testing point
Figure 15 Imax from Neural Network and actual
12 Imax from Neural Network and actual
point
point
Figure 14 Vmax from Neural Network and actual
Figure 15 Imax from Neural Network and actual

Simulink model with different irradiance te
4. CONCLUSION
The main goal of the MPPT technique is to extract the
maximum power available in the PV array. 200.143W PV
array is developed by using MATLAB/Simulink. The
irradiance and temperature are two factors forwhichthe PV
array output power varies. But we are not showed the
comparison withotherMPPTtechniquemethods.Theneural
network is trained by using IrandT(°K)inputdataandPmax
and Vmax output data. From the figure, weobservedthatthe
tested data exactly matched with targe
training of neural network has been proved accurate. We
tested the neural network for 5 new input data (Ir, T (°K)),
we observed from the graph that theoutput(Pmax,Vmax)of
neural network exactly matched with actual 200.143 W PV
array output. By using the neural networkatanirradianceof
1000 W/m2 and temperature of 25°C (298°K), wewereable
to obtain the output power of 198.1813W at 25.8174V. The
actual 200.143 W Simulink model of PV array shows the
maximum power of 200W at 26.3V. Hen
network algorithm can received more accurate results. The
maximum power output we are getting from solar array
alone is around 200W. To get this constant output voltage,
we implemented the MPPT Algorithms with DC
Converter. In future work, we would like to develop two
different working model of Solar Photovoltaic system
employing these algorithms practically using Buck and Cuk
Converter.
5. ACKNOWLEDGEMENT
The author is especially indebted and grateful to my parents
for their encouragement. The author would like to express
16 Pmax from Neural Network and actual
The main goal of the MPPT technique is to extract the
maximum power available in the PV array. 200.143W PV
array is developed by using MATLAB/Simulink. The
irradiance and temperature are two factors forwhichthe PV
power varies. But we are not showed the
comparison withotherMPPTtechniquemethods.Theneural
network is trained by using IrandT(°K)inputdataandPmax
and Vmax output data. From the figure, weobservedthatthe
tested data exactly matched with target values; hence
training of neural network has been proved accurate. We
tested the neural network for 5 new input data (Ir, T (°K)),
we observed from the graph that theoutput(Pmax,Vmax)of
neural network exactly matched with actual 200.143 W PV
tput. By using the neural networkatanirradianceof
1000 W/m2 and temperature of 25°C (298°K), wewereable
to obtain the output power of 198.1813W at 25.8174V. The
actual 200.143 W Simulink model of PV array shows the
maximum power of 200W at 26.3V. Hence the neural
network algorithm can received more accurate results. The
maximum power output we are getting from solar array
alone is around 200W. To get this constant output voltage,
we implemented the MPPT Algorithms with DC-DC Boost
work, we would like to develop two
different working model of Solar Photovoltaic system
employing these algorithms practically using Buck and Cuk
The author is especially indebted and grateful to my parents
ment. The author would like to express
her thanks to partner field’s student and all
Mandalay Technological University.
REFERENCES
[1] A. Mellit, S.A. Kalogirou, L. Hontoria, et al. Artificial
intelligence techniques forsizingphotovoltaic syst
a review. Renewable Sustainable Energy Rev.
2009;13(2):406–419
[2] V. Salas, E. Olias, A. Barrado, et al. Review of the
maximum power point tracking algorithms for stand
alone photovoltaic systems. Sol Energy Mater Sol Cells.
2006;90(11):1555–1578.
[3] R. Sridhar, N. Thamizh Selvan, S. Jeevananthan and P.
Sujith Chowdary, "Performance improvement of a
photo voltaic array usingMPPT(P&O)technique,"
2010 International Conference on Communation
Control and Computing Technologies,
Ramanathapuram, 2010, pp. 1
10.1109/ICCCCT.2010.5670550
[4] S. Haykin, (1998). Neural Networks: A Comprehensive
Foundation (2nd ed.): Prentice Hall.[8]
[5] K. Karabacak, N. Cetin. Artificial neural networks for
controlling wind-PV power systems: A review. Renew
Sustain Energy Rev. 2014;29:804
[6] HR. Kamath, RS. Aithal, PKSA. Kumar, et al. Modelingof
Photovoltaic Array and MaximumPowerPointTracker
Using ANN. 2012;1–13
[7] H. Ibrahim, N. Anani. Variations of PV module
parameters with irradiance and temperature. Energy
Procedia. 2017;134:276
[8] B.C. Babu, T. Cermak, S. Gurjar, et al. Analysis of
mathematical modeling of PV module with MPPT
algorithm. 2015 IEEE 15th International Conference
Environment and Electrical Engineering;2015 June10
13; Rome, Italy. IEEE; 2015.
[9] Jay Patel, Vishal Sheth, Gaurang Sharma, “Design &
Simulation of Photovoltaic System Using Incremental
MPPT Algorithm”, International Journal of Advanced
Research in Electrical,ElectronicsandInstrumentation
Engineering Vol. 2, Issue 5, May 2013.
[10] S. Pukhrem. A Photovoltaic Panel Model in
Matlab/Simulink. MathWorks. 2013;20
her thanks to partner field’s student and all teachers from
Mandalay Technological University.
A. Mellit, S.A. Kalogirou, L. Hontoria, et al. Artificial
intelligence techniques forsizingphotovoltaic systems:
a review. Renewable Sustainable Energy Rev.
V. Salas, E. Olias, A. Barrado, et al. Review of the
maximum power point tracking algorithms for stand-
alone photovoltaic systems. Sol Energy Mater Sol Cells.
1578.
dhar, N. Thamizh Selvan, S. Jeevananthan and P.
Sujith Chowdary, "Performance improvement of a
photo voltaic array usingMPPT(P&O)technique,"
2010 International Conference on Communation
Control and Computing Technologies,
Ramanathapuram, 2010, pp. 191-195. doi:
10.1109/ICCCCT.2010.5670550
S. Haykin, (1998). Neural Networks: A Comprehensive
Foundation (2nd ed.): Prentice Hall.[8]
K. Karabacak, N. Cetin. Artificial neural networks for
PV power systems: A review. Renew
v. 2014;29:804–827.
HR. Kamath, RS. Aithal, PKSA. Kumar, et al. Modelingof
Photovoltaic Array and MaximumPowerPointTracker
H. Ibrahim, N. Anani. Variations of PV module
parameters with irradiance and temperature. Energy
017;134:276–285.
B.C. Babu, T. Cermak, S. Gurjar, et al. Analysis of
mathematical modeling of PV module with MPPT
algorithm. 2015 IEEE 15th International Conference
Environment and Electrical Engineering;2015 June10-
13; Rome, Italy. IEEE; 2015.
Patel, Vishal Sheth, Gaurang Sharma, “Design &
Simulation of Photovoltaic System Using Incremental
MPPT Algorithm”, International Journal of Advanced
Research in Electrical,ElectronicsandInstrumentation
Engineering Vol. 2, Issue 5, May 2013.
A Photovoltaic Panel Model in
Matlab/Simulink. MathWorks. 2013;20–23

Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation

More Related Content

What's hot (20)

Similar to Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation (20)

More from ijtsrd (20)

Recently uploaded (20)

Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation