ISSN (Print) : 0974-6846

Indian Journal of Science and Technology, Vol 9(45), DOI: 10.17485/ijst/2016/v9i45/105313, December 2016 ISSN (Online) : 0974-5645

A New Modified Artificial Neural Network Based

MPPT Controller for the Improved Performance
of an Asynchronous Motor Drive

B. Pakkiraiah and G.D. Sukumar

Department of Electrical and Electronics Engineering, Vignan’s Foundation for Science Technology and
Research University, Guntur, A.P, India-522213;
[email protected],:[email protected]

Abstract
Objectives: To improve the performance of asynchronous motor drive, the proposed Artificial Neural Network (ANN) based
Maximum Power Point Tracking (MPPT) controller has been used to fed the asynchronous motor drive with the obtained
output voltage and currents of PV MPPT. Methods and Analysis: DC-DC boost converter and space vector modulation
technique inverter are used to provide the required supply to the load. The proposed ANN based MPPT improves the
system efficiency even at abnormal weather conditions. Findings: Solar energy is an important alternative out of the
various renewable energy sources. On an average the sunshine hour in India is about 6hrs per day also the sun shines in
India is about 9 months in a year. To generate electricity from the sun, the Solar Photo Voltaic (SPV) modules are used. The
SPV comes in various power outputs to meet the load requirements. Maximization of power from a solar photo voltaic
module is a special case to increase the efficiency of the system. The proposed artificial neural network (ANN) based MPPT
controller is used to track the maximum power. DC-DC boost converter and space vector modulation technique inverter
are used to provide the required supply to the load. The proposed ANN based MPPT improves the system efficiency even
at abnormal weather conditions. Torque and current ripple contents have been reduced to a large extent with the help of
proposed ANN based MPPT for an asynchronous motor drive. Also the better performance of an asynchronous motor drive
is analyzed by the comparison of existed conventional and proposed MPPT controller using Matlab-simulation results.
Improvement: Improvements in torque and current ripple and better speed performances are clearly analyzed with the
help of practical validations. And also few of the observations are carried out and tabulated.

Keywords: Artificial Neural Network (ANN), Asynchronous Motor (ASM) drive, DC-DC Boost Converter, Maximum Power
Point Tracking (MPPT) Controller, Ripple, Solar Photovoltaic (SPV) System, Space Vector Modulation (SVM), Torque

1.  Introduction problem can be overcome. Out of various renewable

sources solar PV System is leading now a day due to its
As the earth’s natural resources are decreasing day by simple structure. The various structure of PV panel sys-
day, to meet the increase in the power demand the power tem and their suitability for locations have discussed1-4.
sector is looking at alternate energy resources. Due to The performance of the PV system can be improved by
usage of renewable energy sources the carbon content in using power electronic devices along with maximum
the atmosphere can be reduced by which global warming power point controller.

*Author for correspondence

 A New Modified Artificial Neural Network Based MPPT Controller for the Improved Performance of an Asynchronous Motor
Drive

Several MPPT techniques were developed to track better performance with the PV system. Various strate-
the maximum power point (MPP) efficiently. Most of gies are used for selecting the vectors orders with zero
the existing MPPT techniques suffer from the drawbacks vectors in reducing the harmonic content and switching
of slow tracking, wrong tracking and oscillations during losses19,20.
rapidly changing weather conditions, which reduces the The space vector modulation technique of an
utilization efficiency. To overcome this, an ANN based inverter is composed with number of sub hexa-
MPPT is implemented. Here two stage MPPT is imple- gons. The sector identification can be done by using
mented to improve non uniform irradiance on the PV the triangle, which encloses the tip of the reference
system. Blocking diode is connected in series to prevent space vector model with forming of six regions21-23.
the reverse current flow from the load, a bypass diode is To overcome the distortions in the output voltage and
also used to enhance the power capture and also to prevent currents of an inverter, the single phase SVM based
hotspots5-7. ANN based MPPT with 2 stage method for cascaded H-Bridge multilevel inverter is used for
MPP presents the independent of time dependency and PV system to improve the power quality even under
trade property, due to which MPP can be tracked with- abnormal weather conditions. The better torque ripple
out time increment through PV characteristic changes8,9. is obtained with the help of genetic algorithm based
The nonlinear characteristics of array with rapidly chang- particle swarm optimization based indirect vector con-
ing irradiation and temperature can be overcome using trol for torque control of an induction motor drive24. A
differential Evolution (DE) and ANN along with conven- comparison of neuro fuzzy with space vector modula-
tional MPPT10. tion technique neural network and conventional based
A modified ANN based MPPT is introduced by system has been presented25.
using the Incremental Conductance method using sen- The advantage of this proposed ANN based MPPT
sors to get better performance. Compared to Incremental algorithm is to control the MPP even under abnormal
Conductance and the PandO technique it is much faster weather conditions, compared to other conventional
for the sudden change of the climatical combinations. To algorithms. In section 2 mathematical modeling of PV
evaluate the effectiveness of the network the least mean array is discussed. Section 3 explains about the proposed
square error is introduced to give accuracy of the network11. MPPT algorithm. Mathematical modeling of asyn-
The 2-level genetic algorithm based neural network (NN) chronous motor drive is discussed in section 4. Section
is used to estimate the battery power for influencing the 5 states a brief note on proposed space vector modula-
factors as light intensity, temperature and battery junc- tion technique. Using the proposed MPPT along with
tion temperature12. A recurrent NN model is trained by boost converter to boost up the PV output and to feed
a Particle Swarm Optimization (PSO) method for solar asynchronous motor drive is detected in section 6.
radiation observation and controlling to predict the accu- Matlab-simulation results with the comparison of con-
rate solar radiation of standalone systems of hybrid power ventional and proposed MPPT techniques are available
systems13. in section 7 and the concluding marks are illustrated in
3 layered ANN with back propagation based MPPT is section 8.
implemented for boost converter of standalone PV system
to minimize the long term system losses and to increase
the conversion efficiency even under variable tempera- 2.  Mathematical Modeling of PV
ture14. PV module energy conversion efficiency lies in Array
between 12%-20%. The energy conversion loss depends
on PV system and also the loads that are connected. This Solar photovoltaic system is made of photovoltaic cells.
can be overcome using MPPT with DC-DC converter to Cells are connected to form panels and panels are grouped
get the required load voltage at the maximum power point to form array. The basic mathematical equations describe
voltage15-18. Solar energy is a major untapped resource in the ideal PV cell and those are clearly mentioned in equa-
a tropical regional country like India. India plans to pro- tions (1) and (2)
duce 20 Giga watts of solar by 2020. A MPPT controller
with the inverter is connected to the asynchronous motor (1)
drive with space vector modulation technique to get the

2 Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology
 B. Pakkiraiah and G.D. Sukumar

Where: PREF = Reference irradiance in W/m2 (1000 W/m2 is taken

IPVCELL is the incident light current, is the reverse under STC)
saturation current of a diode, Q is the charge of an electron ISCR = Short circuit current of a module
at 1.602 10-19 C, K is the Boltzmann’s constant at 1.38 TSCI = Temperature coefficient of short circuit current in
10-23 J/K, is the applied temperature Kelvin, N is A/oK
the diode identity factor constant and VPVCELL is the voltage TAPP and TREF are applied and reference temperatures in
across the cell. Practical PV cell is represented in Figure 1. Kelvin
The calculated Ipv cell values are noted in Table 1.
Ideal PV cell
RSE
+
IM Table 1.  The calculated Ipv cell values for different
irradiance and different temperature
IPVCELL VM IM
Id RSH
Load
Irradiance Temperature (in oC)
in (W/m2) 20 oC 30 oC 40 oC 50 oC 60 oC
- 1000 8.6615 8.6785 8.6955 8.7125 8.7295
800 6.9292 6.9428 6.9564 6.97 6.9836
Figure 1.  Practical PV cell equivalent circuit.
500 4.3307 4.3392 4.3477 4.3562 4.3647
PV system basic equation will not represent I-V 250 2.1653 2.1696 2.1738 2.1781 2.1823
characteristics, as a practical module consists of various 100 0.8661 0.8678 0.8695 0.8712 0.8729
PV cells which require additional parametric values as 50 0.4330 0.4339 0.4347 0.4356 0.4364
series and parallel resistances (RSE & RSH) which are rep- 10 0.0866 0.0867 0.0869 0.0871 0.0872
resented in Figure 1. PV module modeling is based on
mathematical equation of the solar cell which is given Modules reverse saturation current ( at nomi-
by Eq. 2 nal condition and reference temperature is given by
Eq. (4)
 (2)
Where:  (4)
IMD = PV module current in Amps Where:
IPVCELL = Photocurrent or light generated current in IRS = Reverse saturation current in Amps
Amps NT = total no. of cells in a module
IOCELL = Diode reverse saturation current of in Amps
Q = Electron charge in Coulombs Here module voltage decreases as the applied temper-
N = Ideality factor (taken from data sheet) ature goes on increases which can be calculated by Eq. (5)
K = Boltzmann constant in J/oK
TAPP = Applied temperature for the PV module in
Kelvin  (5)
VMD = Module voltage in Volts On the other hand saturation current (
RSE = Series resistance in ohms is given as
RSH = Parallel resistance in ohms
Current generated by light (IPVCELL) depends linearly  (6)
on solar radiation and also on temperature is defined by
Where:
Eq. (3)
EGO = semiconductor band gap energy of the module
in J/C, the shunt resistance RSH is inversely proportional to
(3) leakage current and a small variation of series resistance
Where: will affect the PV output power. A PV cell will produce
PAPP = Applied solar irradiance in W/m2 (applied to the less than 2 watts at approximately 0.5 V and 0.7 V at open
module during the experiment) circuit condition. The cells must be connected in series

Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology 3
 A New Modified Artificial Neural Network Based MPPT Controller for the Improved Performance of an Asynchronous Motor
Drive

and parallel combination to get required power. Array Vdc

basic output current of single diode module is calculated -

by Eq. (7)
+
Vmppt

PV system
(7)
Yk
Supervised Output
Where and are the number of solar cells
connected in series and parallel. Modeling of PV array is learning law Σ layer (k)

done based on data sheet parameters of SSI-3M6-250W

Wl
poly-crystalline solar module at 25o C and 1000 W/m2. Yj
hidden
Based on above parameters PV model in Simulink is layer (j)
developed under standard test conditions.
Yi
input
3.  Proposed Maximum Power layer (i)

Point Tracking Algorithm

Figure 2.  ANN based MPPT. Xi
Maximum power point tracking control technique is
mainly used to extract maximum capable power of the a. Practical Outputs of Conventional MPPT
PV modules with respective solar irradiance and tem- Controller with Variable Irradiance at Constant
perature at particular instant of time by MPP tracking Temperature
controller. A number of algorithms were implemented
When the irradiance is varied from 100, 250, 500, 800 and
to track the MPP efficiently. Most of the existing MPPT
1000 W/m2 it is observed that the PV current and voltage
algorithms suffer from the drawbacks of slow tracking,
will increases with irradiance levels. Due to this net PV
wrong tracking and oscillations during rapidly changing
array power also gets increases. These characteristics are
environmental conditions, which reduces the utilization
observed in Figure 3.
efficiency.
To overcome these drawbacks an ANN based MPPT
Control technique is introduced in this paper. Here it
improves the performance of the system and efficiency
with much better than any other conventional meth-
ods. In this technique a multi layered neural network is
used. A two stage off line trained artificial neural net-
work based MPPT is added to estimate the temperature
and irradiance from the PV array voltage and current
signals.
Supervised learning is implemented to nullify the
error with providing the required multiplication fac- Figure 3.  Practical I-V & P-V characteristics with variable
tors to the weights at the hidden layer. This technique irradiance and constant temperature.
gives the better performance even under rapidly chang-
ing weather conditions for both steady and transient b. Practical Outputs of Conventional MPPT Controller
instants with reducing the training set. The boost con- with Variable Temperature and Constant Irradiance
verter, inverter are used to provide maximum output
voltage to the load. Here a supervised learning feed When the temperature varies from 20o C, 30o C, 40o C, 50o
forward trained network is introduced to overcome the C and 60o C it increases the PV current marginally with
non-linearities of PV array. Proposed artificial neural drastically decrease in PV array voltage. Due to this net
network based MPPT algorithm flow chart is shown in PV array output power reduces. These characteristics are
the Figure 2. presented in Figure 4.

4 Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology
 B. Pakkiraiah and G.D. Sukumar

and RR are stator and rotor per phase resistances. LS, LR are
stator and rotor self inductances and LM is mutual induc-
tance. Flux linkages of stator and rotor can be expressed as

(12)
(13)
(14)
Figure 4.  Practical I-V & P-V characteristics with variable
temperature and constant irradiance. (15)
From the above Equations (8)-(11), squirrel cage
c. Practical Outputs of Proposed MPPT Controller with asynchronous motor can be analyzed by the following
Variable Temperature and Variable Irradiance equations in stator reference frame as
When both the temperature and irradiance are variable
then it increases the PV module current and decreases
the voltage till the temperature rise and vice-versa. Also it
increases the array current and slightly increases the volt-
age till the irradiance rise and vice-versa. These results are
illustrated in Figure 5.
(16)
The electromagnetic torque Te of the induction motor
is given by

(17)

From the dynamic representation of an asynchro-

nous motor, the flux of the rotor is aligned along with the
Figure 5.  Practical I-V & P-V characteristics of PV array d-axis, then the q-axis rotor flux λqR= 0. So from the equa-
with variable temperature and variable irradiance. tions (14) and (17), it is described in the previous section
and putting λqR=0, then the the vector control electro-
magnetic torque of the motor can be expressed as
4.  Mathematical Modeling
Asynchronous Motor Drive
(18)
The mathematical modeling of a three phase, squirrel If flux linkage of the rotor λdR is not disturbed, then the
cage asynchronous motor drive can be analyzed with sta- torque can be controlled independently by adjusting the
tionary reference frame as stator q- component current iqS. As the rotor flux aligned
on d-axis, then it leads λqR= 0 and λdR = λR, then
 (8)
(9)
 (19)
(10)

(11) 5.  Proposed SVM Technique for

Two Level Inverter
Where ,
Suffixes S and R represents stator and rotor respectively. In this the space vector modulation technique is
VdS and VqS are d-q axis voltages of respectively, idS, iqS and implemented with the two level inverter for the solar
idR, iqR are d-q axis stator and rotor currents respectively. RS array, which produces the DC supply. SVM basic

Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology 5
 A New Modified Artificial Neural Network Based MPPT Controller for the Improved Performance of an Asynchronous Motor
Drive

working principle and switching sequence is given in

order to get symmetrical pulses for balancing of the
voltages. This technique is used to control the out-
put voltage of the inverter with the ANN based MPPT
controller. In the proposed SVM technique, the d-axis
and q-axis voltages are converted into instantaneous
three-phase reference voltages. Then the imaginary
switching time periods are proportional to the instan-
taneous values of reference phase voltages. Which are
defined as
Figure 6.  Space vector diagram.

, (20)

Where TS and VDS are the interval sampling time and 6.  Proposed MPPT System with
dc link voltages respectively. Here the sampling frequency Dc-Dc Converter, Inverter
is the twice that of the carrier frequency. and ASM Drive
Then the imaginary switching times of maximum
(MAXI), middle (MID) and minimum (MINI) can be in The below system represents the proposed system struc-
each sampling interval using Equations (21)-(23). ture with DC-DC converter. In this, PV array contains 6
PV modules with 250 Watts each; these modules are con-
(21) nected in the combination of series and parallel to yield
better output voltage and current. The proposed artificial
(22)
neural network (ANN) based MPPT controller extracts
(23) the maximum power from solar array at three various
conditions.
The voltage active vector switching times T1 and T2 are
Case I: at variable irradiance and constant tempera-
calculated as
ture.
and Case II: at variable temperature and constant irradi-
ance and,
(24) Case III: at variable temperature and variable irradi-
The switching time of the zero voltage vector is cal- ance which is a new technique when compared to the
culated as other conventional methods.
These individual case outputs are presented in section
(25) 3 and 7. The proposed system structure with the asyn-
The state time zero will be shared between two chronous motor drive is presented in Figure 7.
zero states as T0 for V0 and T7 for V7 respectively,
and that can be given as
DC-DC
PV Boost Inverter
(26) Array Converter

(27) ASM Drive

Duty ratio
VPV CELL IPV CELL
The various SVM techniques can be generated by
changing K0 between 0 and 1. However, in this SVM Proposed
technique, the zero voltage vector time is distributed MPPT PWM
equally among V0 and V7. Hence, here K0 is chosen as
0.5 to obtain the SVM control technique as shown in Figure 7.  Proposed MPPT system with DC-DC converter
Figure 6. and asynchronous motor drive.

6 Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology
 B. Pakkiraiah and G.D. Sukumar

The point of operation of the solar array is adjusted by Table 2.  Practical PV array output power at different
changing the duty cycle. DC-DC boost converter boosts instants during partially cloudy day
the PV array output voltage and also increases the maxi- Time in Temperature in (0C) Array Power in (Watts)
mum utilization of PV array by operating at MPP. Boost (am/pm)
converter increases the array output voltage up to 400 08.00 30.75 188.70
Volts with the help of SVM based inverter.
09.06 33.35 642.94
The minimum inductor value (LMIN) is calculated from
10.00 38.25 725.62
Equation (28) to ensure the continuous inductor current.
11.00 39.55 839.61

 (28) 12.00 40.50 853.60

12.10 40.68 866.36
13.00 41.35 801.78
Where is DC voltage, D is duty ratio, fS is switch-
ing frequency of the converter, is average output 14.00 40.08 662.70
current. The minimum capacitance value (CMIN) can be 15.00 38.42 611.00
calculated using Equation (29). 16.00 37.32 453.12
16.30 37.06 381.51

(29) a. Simulation Results of Asynchronous Motor Drive with

Inverter
The switching frequency selection is trade-off between
switching losses, cost of switch and the converter effi- Simulation results are obtained with the reference speed
ciency. of 1400 RPM and switching frequency of 5 KHz. The
behavior of the motor parameters such as stator phase
current, torque and speed are illustrated in the below
7.  Results and Discussion results. Here the motor drive is being fed with 400 Volts
supply with the help of boost converter and inverter. The
The proposed model has been implemented with Matlab- inverter output voltages are presented in Figure 9.
simulink. The input to the module is temperature and
solar irradiance. At Standard Test Conditions (STC) con-
taining 60 cells to produce 250 Watt power and such 6
modules are arranged to form solar array. From simula-
tion results we got the array generated open circuit voltage
is 75.96 Volts with short circuit current about 26.01 Amps
and the maximum power obtained at MPP is 1500 Watts.
These results are observed in Figure 8.

Figure 9.  Inverter output voltages.

b. Simulation Results of Asynchronous Motor Drive at

Figure 8.  I-V & P-V characteristics obtained from PV starting
array.
For the asynchronous motor drive the maximum cur-
Practical array output power values are tabulated in rent and the content of the ripple in the torque is reduced
Table 2. during starting to reach the steady state earlier. With

Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology 7
 A New Modified Artificial Neural Network Based MPPT Controller for the Improved Performance of an Asynchronous Motor
Drive

the proposed MPPT the maximum torque, stator phase c. Simulation Results of Asynchronous Motor Drive at
current and the speed are obtained as 12.28 N-m, 7.596 steady state condition
Amps and 1400 RPM respectively. It is noted that the con-
tent of the ripple in the torque is 0.29 with lot of reduction Here torque ripple with the proposed MPPT is reduced
compared to the other existed methods. Due to this better a lot i.e. the torque ripple content with the conventional
speed response is obtained. These results are presented in and proposed MPPT are 0.35 and 0.05 respectively. The
Figure 10-12. better speed response is obtained with the proposed ANN
based MPPT controller. The responses of the stator phase
current, torque and speed at steady state with conven-
tional and proposed MPPT are observed in Figure 13-14.

Figure 10.  Stator phase current responses with

conventional and proposed MPPT controller at starting.

Figure 13.   Stator phase current, torque and speed responses

with the conventional MPPT controller at steady state.

Figure 11.  Speed responses with conventional and

proposed MPPT controller at starting.

Figure 14.  Stator phase current, torque and speed

Figure 12.  Torque responses with conventional and responses with the proposed MPPT controller at steady
proposed MPPT controller at starting. state.

8 Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology
 B. Pakkiraiah and G.D. Sukumar

d. Simulation Results of Asynchronous Motor Drive at 8.  Conclusion

transients with step change in load
The PV array model with the proposed artificial neural
Here the content of ripple in the current and torque are
network (ANN) based MPPT control technique is tested.
reduced by the proposed MPPT. Also the speed decre-
From this the behavior of the asynchronous motor drive
ment is little less with the proposed MPPT during the load
is analyzed with comparing both conventional and pro-
change. The transient responses during the step change in
posed ANN MPPT controller results. Also the behavior
load torque 8 N-m is applied at 0.7 sec and removed at 0.9
of the proposed ANN MPPT is observed with practical
sec are available in Figure 15-17.
validations during a partially cloudy day. PV system with
DC-DC boost converter and space vector modulation
based technique inverter enhances the system perfor-
mance with improving the power quality even under
abnormal weather conditions. The ripple contents in the
torque and stator phase currents are reduced a lot with
the proposed ANN based MPPT. Here the early steady
state response of the motor drive is reached along with
attaining of better speed response. Thus with the pro-
posed ANN based MPPT controller, the utilization and
efficiency of the system is improved much.
Figure 15.  Stator phase current responses with
conventional and proposed MPPT controllers at transients 9.  Acknowledgment
with step change in load.
Funding support given by SERB, Department of Science
and Technology (DST), Government of India with vides
SERB order No: SERB/ET-069/2013 for the solar based
project is acknowledged.

10.  References
1. Faranda R, Leva S. Energy Comparison of MPPT tech-
niques for PV systems. WSEAS Transactions on Power
Systems. 2008; 3(6):446–55.
Figure 16.  Torque responses with conventional and 2. Mellit A, Kalogirou SA. Artificial Intelligence Techniques
proposed MPPT controllers at transients with step change for Photovoltaic Applications. A Review Progress in Energy
in load. and Combustion Science. 2008; 34(5):574–632.
3. Saadi A, Moussi A. Neural Network use in the MPPT of
photovoltaic pumping system. Renewable and Sustainable
Energy Reviews. 2003;39–45.
4. Kanth KM, Kishore RD. Implementation of MPPT tech-
niques for a high step-up converter with voltage multiplier
module based photovoltaic system. Indian Journal of
Science and Technology. 2015; 8(23):1–6.
5. Kumar MY, Varma PS. A Comparative Study for Alleviation
of Current Harmonics using PI/Fuzzy Controller based
PV-APF System. Indian Journal of Science and Technology.
2016; 9(23):1–7.
Figure 17.  Speed responses with conventional and 6. Pakkiraiah B, Sukumar GD. Research Survey on Various
proposed MPPT controllers at transients with step change MPPT Performance Issues to Improve the Solar PV System
in load. Efficiency. Journal of Solar Energy. 2016; 1–20.

Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology 9
 A New Modified Artificial Neural Network Based MPPT Controller for the Improved Performance of an Asynchronous Motor
Drive

7. Jiang L, Nayanasri DR, Maskell DL, Vilathgamuwa 16. Mei Q, Shan M, Liu L, Guerrero MJ. A novel improved vari-
DMA Simple and Efficient Hybrid Maximum Power able step-size incremental-resistance MPPT method for PV
Point tracking Method for PV Systems Under Partially systems. IEEE Transactions on Industrial Electronics. 2011;
Shaded Conditions. IEEE Industrial Electronics Society. 58(6):2427–34.
2013;1513–8. 17. Pakkiraiah B, Sukumar GD. A New Modified MPPT
8. Alireza R, Maziar I, Majid G, Saeed V. Investigation of Controller for Solar Photovoltaic System. IEEE International
ANN-GA and Modified Perturb and Observe MPPT Conference on Research in Computational Intelligence and
Techniques for Photovoltaic System in the Grid Connected Communication Networks. India, 2015.
Mode. Indian Journal of Science and Technology. 2015; 18. Mohammed SS, Devaraj D, Ahamed TPI. Modeling,
8(1):pp.87–95. Simulation and Analysis of Photovoltaic Modules under
9. Lee HH, Phuong LM, Dzung PQ, Vu NTD, Khoa LD. The Partially Shaded Conditions. Indian Journal of Science and
New Maximum Power point Tracking Algorithm using Technology.2016; 9(16):1–8.
ANN-based Solar PV Systems. IEEE TENCON Conference 19. Joshi J J, Karthick P, Kumar R S. A solar panel connected
on Korea. 2010. multilevel inverter with SVM using fuzzy logic control-
10. Sheraz M, Abido MA. An Efficient MPPT Controller using ler. IEEE International Conference on Energy Efficient
Differential Evolution and Neural Network. IEEE Power Technologies for Sustainability, India. 2013. p.1201–6.
and Energy (PECon) International Conference on Saudi 20. Aleenejad M, Eini HI, Farhangi S. A minimum loss switch-
Arabia. 2012. ing method using space vector modulation for cascaded
11. Xu J, Shen A, Yang C, Rao W, Yang X. ANN based on H-bridge multilevel inverter. IEEE 20th Iranian Conference
Incremental Conductance Algorithm for MPP Tracker. on Electrical Engineering, Iran.2012.p.546–51.
IEEE 6th International Conference on Bio-Inspired 21. Sreeja C, Arun S. A novel control algorithm for three phase
Computing: Theories and Applications, China. 2011. multilevel inverter using SVM. IEEE PES Innovative Smart
p.129–34. Grid Technologies-India (ISGT India). 2011;262–67.
12. Jie L, Ziran C. Research on the MPPT Algorithms for 22. Pakkiraiah B, Sukumar GD.A New Modified MPPT
Photovoltaic System Based on PV Neural Network. Controller for Improved Performance of an Asynchronous
IEEE Control and Decision Conference, China. Motor Drive under Variable Irradiance and Variable
2011.p.1851–4. Temperature. International Journal of Computers and
13. Zhang N, Behera PK, Williams C. Solar Radiation Prediction Applications-Taylor and Francis. 2016;1–14.
Based on Particle Swarm Optimization and Evolutionary 23. Mbarushimana A, Ai X. Real time digital simulation of
Algorithm using Recurrent Neural Networks. IEEE PWM converter control for grid integration of renewable
International Systems Conference, USA. 2013 p.280–6. energy with enhanced power quality. IEEE International
14. Ramaprabha R, Mathur BL, Sharanya M. Solar Array Conference on Electric Utility Dereglation and Restructing
Modeling and Simulation of MPPT using Neural and Power Technologies. 2011.p.712–8.
Network. IEEE Transactions on Control, Automation, 24. Kim DH. GA-PSO based vector control of indirect three
Communication and Energy and Conservation. 2009. phase induction motor. Elsevier Science Direct Applied
p.1–5. Soft Computing.2007;7(2):601–11.
15. Adly M, Ibrahim M, Sherif H E. Comparative study of 25. Sukumar D, Jitendranath J, Saranu S. Three-level Inverter-
improved energy generation maximization techniques for fed Induction Motor Drive Performance Improvement with
photovoltaic systems. IEEE Asia-Pacific Power and Energy Neuro-fuzzy Space Vector Modulation. Electrical Power
Engineering Conference,Egypt. 2012. p.1–5. Components and Systems. 2014;42(15):1633–46.

10 Vol 9 (45) | December 2016 | www.indjst.org Indian Journal of Science and Technology