Performance Comparison of Conventional and AI

based MPPT in Solar PV System

Yashwant Rana Pankaj Pratush Seraj Ansari
Department of Electrical & Electronics Department of Electrical & Electronics Department of Electrical & Electronics
Engineering, ABES Engineering Engineering, ABES Engineering Engineering, ABES Engineering
College, Ghaziabad, UP, INDIA. College, Ghaziabad, UP, INDIA. College, Ghaziabad, UP, INDIA.
[email protected] [email protected] [email protected]
2022 IEEE 10th Power India International Conference (PIICON) | 978-1-6654-5930-3/22/$31.00 ©2022 IEEE | DOI: 10.1109/PIICON56320.2022.10045285

Sagar Jaiswal Gurpreet Singh Rahul Virmani

Department of Electrical & Electronics Department of Electrical & Electronics Department of Electrical & Electronics
Engineering, ABES Engineering Engineering, ABES Engineering Engineering, ABES Engineering
College, Ghaziabad, UP, INDIA. College, Ghaziabad, UP, INDIA. College, Ghaziabad, UP, INDIA.
[email protected] [email protected] [email protected]

Abstract— Obtaining Maximum power possible is a crucial oscillations at MPP and have a low efficiency. Several studies
task in PV systems. Various MPPT strategies based on classical are already being conducted to enhance the performance of
and artificial intelligence methodologies have been proposed in these approaches using AI [7], [8], [11]–[15]. [16]. ANN has
the literature so far. Those approaches, on the other hand, have already been employed to increase the performance of the
been tried on a variety of PV systems and in a variety of P&O approach [17]. AI based MPPT, in contrast to traditional
environments. This paper aims to provide a meticulous relative MPPT procedures, are efficient and can provide higher
analysis of widely used AI based MPPT methods. The MPPT results[18]–[21]. In [22], fuzzy logic has also been utilized to
approaches that will be deliberated are: Artificial Neural Network
enhance the performance of INC method. The proportional
(ANN), Perturb and Observe (P&O), Adaptive Neuro Fuzzy
integral derivate (PID) controller is widely used in control
Inference System (ANFIS), Incremental Conductance (INC). In
the same photovoltaic system, the developed MPPT controllers are
systems because of its performance, simplicity, and stability
assessed in the same weather conditions. The system is first in the steady state domain. [23] proposes an MPPT control
modelled and then simulated in the MATLAB Simulink. Under the utilizing a fuzzy PID controller. The advantages of fuzzy logic
identical variable temperature and sun irradiance settings, and traditional PID control are combined in the hybrid
simulations are run to confirm the accuracy of the suggested controller to achieve better performance in terms of accuracy
controllers. Finally, a comparative analysis is shown to evaluate and precision.
the created methodologies based on performance. The concluding
ANN and FL seem to be fairly the ideal solution to the
part contains recommendations on the validity of each MPPT
MPPT problem because of the non-linear relationship
approach that are believed to be valuable to researchers in the
MPPT field.
between the extracted power and the output voltage (P-V).
The fuzzy controller's digital implementation was completed
Keywords— Maximum power point tracking (MPPT), in [24]–[27], more efficient fuzzy controller was suggested
artificial intelligence (AI), artificial neural network (ANN), employing evolutionary algorithms in [28] and particle swarm
adaptive neuro fuzzy inference system (ANFIS), Perturb and optimization in [29] to pick the optimum membership
Observe (P&O), incremental conductance (INC). functions.
The use of ANN have also been proposed in [30], [31].
I. INTRODUCTION
The demand for a big database in employing ANN using
The power industry has been driven to speed up research into measurements of irradiance, temperature, and the related ideal
alternative energy resources due to increased energy demand duty cycle for training the ANN is addressed in [32]. The
and the strain on conventional energy supply, which has a bad fuzzy controller is utilized in [33] to create the database for
impact on the environment. One of the most promising is neural network training. The authors of [34] proposed
photovoltaic (PV) power. Its design as a stand-alone system employing genetic algorithms (GA) to optimize the ANN
might provide a significant amount of electricity to isolated structure. In [35], a complicated technique is presented, in
locations. PV systems are already widely used globally, and which a fuzzy controller is utilized to choose amongst
demand is increasing year after year. numerous ANN models, with the local model being chosen
based on the best performance in the operational temperature
PV modules are made up of a large number of PV cells and irradiance range.
coupled in series and parallel. The maximum power point of a
PV module is affected by variations in solar irradiance and The PV curve has a distinct MPP during uniform solar
temperature. Maximum power point tracking (MPPT) is the insolation. The situation gets more difficult when the PV array
process of extracting the maximum amount of power from a is partially shaded or receives non-uniform insolation. In this
PV array. A dependable MPPT controller must be instance, the PV curve will have numerous peaks, one of
incorporated due to the costing issues of PV modules and their which will be the global MPP. The global MPP tracking
poor productivity (between 10% and 23%) [1], [2]. Perturb appears to be an optimization difficulty. Several studies have
and Observe[3], [4], Incremental Conductance[5]–[9], and attempted to create global MPPTs by developing various
Hill Climbing[10] are all well-established and well-known approaches based mostly on meta-heuristic optimization
strategies in the literature. These approaches are simple and algorithms. MPPT algorithms were suggested in the
upfront to embed in controllers, however they exhibit. evolutionary computing family as per Genetic Algorithms in
[36] and Differential Evolution in [37]–[39].

978-1-6654-5930-3/22/$31.00 ©2022 IEEE

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.
 The bio inspired algorithms such as PSO has also been
employed for MPPT because of its simplicity and quick
calculation competence [40]–[42]. Furthermore, MPPT
approaches based on Cuckoo Search (CS) method [43], Ant
colony optimization (ACO) [44], Colony of Flashing Firefly
algorithm (FA) [45] and Artificial bee colony algorithm
(ABC) [46] have recently been implemented. Researchers
have suggested various AI based MPPT algorithms. It's
difficult to provide a broad assessment of the numerous MPPT
strategies mentioned above. This is because those MPPT
Fig. 2. Simulated PV Module IV characteristics at fixed temperature
approaches have been deployed on a variety of PV systems 25ºC and irradiances 1,0.8,0.6,0.4,0.2 (kW/m2)
and evaluated in a variety of weather situations.
This paper aims to bridge this gap by evaluating and
comparing the most popular AI-based MPPT approaches on
same PV model and under similar test conditions. At the last,
the primary conclusion and suggestions for each MPPT
technique are presented.
II. MODELLING OF PV SYSTEM
The PV system consists of a PV module, MPP tracker, and
load. A power converter and an MPPT control unit, both of
which are controlled by a CPU, make up the MPP tracker. The
converter keeps the PV operating point at MPP regardless of
the climatic conditions to harvest the most electricity possible. Fig. 3. Simulated PV Module IV characteristics at fixed temperature
This part covers PV module modelling and electrical 25ºC and irradiances 1,0.8,0.6,0.4,0.2 (kW/m2)
characteristics simulation under various environmental
circumstances. Here, we have considered the single diode III. TECHNIQUES FOR TRACKING MAXIMUM POWER POINT
IN PV SYSTEMS
model is considered for making the simulated model.
A. Perturb and Observe (P&O)
The perturbation and observation approach is common
and works by perturbing the array's terminal voltage
periodically and comparing the PV output power to the
preceding perturbation cycle. The perturbation will continue
in the same direction in the following cycle if the power is
raised; otherwise, the direction of the disturbance will be
Fig. 1. Single diode model of PV cell
reversed. The flowchart for this technique is shown in Figure
The photovoltaic array's output current is: 4. The P&O approach has two drawbacks in some situations:
When the operational point is compelled to function near the
I = Isc − Id (1) MPP, oscillations around the MPP emerge in a steady state.
Because of this issue, some of the available energy is lost
Id = Io(e qVd / KT − 1) (2) [47]. Further, This approach somewhat fails in the rapidly
changing atmospheric circumstances since it shifts the
Where, Io is the diode's reverse saturation current, Vd is the
voltage across the diode, q is the electron charge, K is the operating point further from the MPP [48].
Boltzmann constant (1.38 * 10-23 J/K), and T is the junction
temperature in Kelvin.
The specifications of the simulated system at STC (Standard
Test conditions) of 250 C and at isolation of 1 kW/m2 is shown
in Table 1.

TABLE I. SPECIFICATIONS OF THE SIMULATED PV MODULE AT 25ºC AND

1000 WATTS PER SQUARE METER

Fig. 4. Flowchart of P&O MPPT

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.
 The figure below shows the simulated model of P&O The figure below shows the simulated model of INC
MPPT on a PV system with specifications as shown in table I. MPPT on a PV system with specifications as shown in table I.

Fig. 7. Simulated model of PV system with inhibited INC MPPT Controller.

C. Artificial Neural Network (ANN)

Artificial neural network (ANN) is an AI based
technique. AI provides a number of benefits over traditional
Fig.5. Simulated model of PV system with inhibited P&O MPPT approaches. Conventional methods have the disadvantage of
Controller. being slow to respond to variations in solar irradiance and
temperature, plus failing to track the highest power point. The
B. Incremental Conductance (INC) inputs are solar temperature and irradiance. The neural
The incremental conductance method (INC) monitors network's target is the duty ratio of a DC-DC boost converter.
and compares the PV module's incremental and instantaneous The neural network suggests a duty ratio value for each
conductance’s to calculate the PV module's terminal voltage. change in solar temperature and irradiance so as to achieve the
When the incremental conductance reaches the instantaneous maximum power point for each alteration in solar temperature
conductance, it shows that the maximum power point has been and irradiance.
discovered[49]. Within working limitations, output power
increases as the terminal voltage of the PV module increases
(power curve slope is positive, dP/dV > 0). At operating points
beyond MPP, the output power of the PV modules reduces as
the terminal voltage of the modules increases (the slope of the
power curve is negative, dP/dV < 0). The slope of the curve is
zero when the operating point is exactly at the MPP, as
predicted.
Fig. 8. Neural Network for MPPT

Fig. 9. Neural Network training by MATLAB ANN tool

Fig. 6. Flowchart of INC MPPT
Solar irradiance and temperature are provided to the neural
The incremental conductance approach has the benefit of
network. Trial and error is used to establish the number of
being able to determine the precise direction of perturbation at
buried layers. The neural network's output is the duty ratio to
any instant. The incremental conductance approach also
the boost converter. To monitor maximum power from solar
avoids various perturbation phenomena such as operating
panels under varied temperature and irradiance circumstances,
point oscillation around the MPP.
the training points are acquired by adjusting the temperature
and irradiance inputs to the PV array and gathering duty ratio

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.
data to the boost converter. The neural network is trained interpretation of Fuzzy Logic has resulted in the creation of a
using the MATLAB m-"nntool" FILE. The MATLAB novel hybrid approach known as 'neuro fuzzy networks'.
toolbox is used to train neural networks as shown in Figure 9.
The network is created by utilizing the Levenberg-Marquardt The purpose of this research is to present an ANFIS-based
method to train it. The mean squared error (MSE) is the ANN's MPPT technique for tracking PV module maximum power
execution function. A total of 1000 data points are used to train under changing weather circumstances. The suggested input
the neural network. Temperatures vary from 15 to 35 degrees variables are solar irradiance and temperature. The duty
Celsius, with irradiance levels ranging from 100 to 1000 watts cycle is an output variable used to regulate the DC-DC
per square metre. isolated boost converter so that maximum power tracking is
The figure below shows the simulated model of ANN MPPT maintained. Because typical FLC modelling relies on trial
on a PV system with specifications as shown in table I. and error, there's a low probability of getting perfect results.
As a result, membership functions and fuzzy rules can
be derived using ANFIS learning. First and foremost, the
training data should be gathered. To get the training data in
this work, the following procedures were taken:
• The system was simulated using typical MPPT
methods under varying solar radiation and temperature
conditions.
• A MATLAB algorithm designed specifically for this
purpose was used to collect and process the data.
• Following that, the revised data was jumbled. The data
is then filtered once more to obtain only the data
collection's unique rows.
Fig. 10. Simulated model of PV system with inhibited ANN MPPT Controller.
The figure below shows the simulated model of ANFIS MPPT
D. Adaptive Neuro Fuzzy Inference System (ANFIS) on a PV system with specifications as shown in table I.
Fuzzy logic, when integrated with neural networks, it
produces really impressive results. Data may be used to train
neural networks. Understanding the knowledge obtained by
neural networks, on the other hand, has proven difficult. To be
more explicit, developing an understanding of the meaning
connected with each neuron and weight is typically
challenging. Fuzzy rule-based models, on the other hand, are
simple to comprehend since they employ language words and
the framework of IF-THEN rules.

Fig. 12. Simulated model of PV system with inhibited ANFIS MPPT

Controller.

IV. SIMULATION RESULTS AND DISCUSSIONS

All the MPPT algorithms are tested by giving 25ºC
temperature and step changing irradiance shown in Fig 18 as
input to the PV module.

Fig. 11. ANFIS training data block diagram

However, unlike neural network, fuzzy logic cannot learn on

its own. Fuzzy logic system learning and identification need
approaches from other fields, such as statistics and system
identification. Because neural network can learn, it makes
sense to combine these two approaches. The combination of Fig. 13. Step changing Solar Irradiance
the learning ability of Neural Network with the knowledge The figures below show the PV array’s output power graph of
P&O, INC, ANN and ANFIS based MPPT controller

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.
respectively, on a PV system with specifications as shown in REFERENCES
table I.
[1] A. K. Pandey, V. V. Tyagi, J. A. Selvaraj, N. A. Rahim, and S. K.
Tyagi, “Recent advances in solar photovoltaic systems for
emerging trends and advanced applications,” Renew. Sustain.
Energy Rev., vol. 53, pp. 859–884, 2016, doi:
10.1016/j.rser.2015.09.043.
[2] M. A. Eltawil and Z. Zhao, “MPPT techniques for photovoltaic
applications,” Renew. Sustain. Energy Rev., vol. 25, pp. 793–813,
2013, doi: 10.1016/j.rser.2013.05.022.
[3] A. K. Abdelsalam, A. M. Massoud, S. Ahmed, and P. N. Enjeti,
Fig. 14. PV array output power response with P&O MPPT controller “High-performance adaptive Perturb and observe MPPT technique
for photovoltaic-based microgrids,” IEEE Trans. Power Electron.,
vol. 26, no. 4, pp. 1010–1021, 2011, doi:
10.1109/TPEL.2011.2106221.
[4] P. Mohanty, G. Bhuvaneswari, R. Balasubramanian, and N. K.
Dhaliwal, “MATLAB based modeling to study the performance of
different MPPT techniques used for solar PV system under various
operating conditions,” Renew. Sustain. Energy Rev., vol. 38, pp.
581–593, 2014, doi: 10.1016/j.rser.2014.06.001.
[5] A. Safari and S. Mekhilef, “Simulation and hardware
implementation of incremental conductance MPPT with direct
Fig. 15. PV array output power response with INC MPPT controller control method using cuk converter,” IEEE Trans. Ind. Electron.,
vol. 58, no. 4, pp. 1154–1161, 2011, doi:
10.1109/TIE.2010.2048834.
[6] K. S. Tey and S. Mekhilef, “Modified incremental conductance
MPPT algorithm to mitigate inaccurate responses under fast-
changing solar irradiation level,” Sol. Energy, vol. 101, pp. 333–
342, 2014, doi: 10.1016/j.solener.2014.01.003.
[7] K. S. Tey, S. Mekhilef, and S. Member,
“Pauta_Ejercicio_1_2009_02.pdf,” vol. 61, no. 10, pp. 5384–
5392, 2014.
Fig. 16. PV array output power response with ANN MPPT controller [8] T. K. Soon and S. Mekhilef, “A fast-converging MPPT technique
for photovoltaic system under fast-varying solar irradiation and
load resistance,” IEEE Trans. Ind. Informatics, vol. 11, no. 1, pp.
176–186, 2015, doi: 10.1109/TII.2014.2378231.
[9] D. Lalili, A. Mellit, N. Lourci, B. Medjahed, and E. M. Berkouk,
“Input output feedback linearization control and variable step size
MPPT algorithm of a grid-connected photovoltaic inverter,”
Renew. Energy, vol. 36, no. 12, pp. 3282–3291, 2011, doi:
10.1016/j.renene.2011.04.027.
[10] E. Koutroulis, K. Kalaitzakis, and N. C. Voulgaris, “Development
of a microcontroller-based, photovoltaic maximum power point
Fig. 17. PV array output power response with ANFIS MPPT controller
tracking control system,” IEEE Trans. Power Electron., vol. 16,
no. 1, pp. 46–54, 2001, doi: 10.1109/63.903988.
V. CONCLUSION [11] P. E. Kakosimos and A. G. Kladas, “Implementation of
Assuming that the source is limitless, solar photovoltaic-based photovoltaic array MPPT through fixed step predictive control
technique,” Renew. Energy, vol. 36, no. 9, pp. 2508–2514, 2011,
electricity production keep on rising. The low conversion
doi: 10.1016/j.renene.2011.02.021.
efficiency of solar PV-based systems is a challenge. MPPT is [12] M. A. G. De Brito, L. Galotto, L. P. Sampaio, G. De Azevedo
a technique for maximising output power of solar cells Melo, and C. A. Canesin, “Evaluation of the main MPPT
providing maximum energy at all levels of irradiance. This is techniques for photovoltaic applications,” IEEE Trans. Ind.
completed by matching the load and source sides' impedances. Electron., vol. 60, no. 3, pp. 1156–1167, 2013, doi:
In this work, four MPPT approaches are described in depth: 10.1109/TIE.2012.2198036.
[13] J. Ahmed and Z. Salam, “An improved perturb and observe (P&O)
P&O, INC, ANN, and ANFIS[50]. As shown in fig. (19-22), maximum power point tracking (MPPT) algorithm for higher
an increase in the output of the solar panel employing an efficiency,” Appl. Energy, vol. 150, pp. 97–108, 2015, doi:
ANFIS-based MPPT is superior in performance. 10.1016/j.apenergy.2015.04.006.
[14] A. Harrag and S. Messalti, “Variable step size modified P&O
TABLE II. PERFORMANCE COMPARISON OF SIMULATED MPPT MPPT algorithm using GA-based hybrid offline/online PID
ALGORITHMS controller,” Renew. Sustain. Energy Rev., vol. 49, pp. 1247–1260,
2015, doi: 10.1016/j.rser.2015.05.003.
[15] A. Loukriz, M. Haddadi, and S. Messalti, “Simulation and
Parameters P&O INC ANN ANFIS experimental design of a new advanced variable step size
Incremental Conductance MPPT algorithm for PV systems,” ISA
Tracking Slow Slow Moderate Fast Trans., vol. 62, pp. 30–38, 2016, doi:
Speed 10.1016/j.isatra.2015.08.006.
Overall Medium Medium High High [16] G. Dileep and S. N. Singh, “Maximum power point tracking of
Efficiency solar photovoltaic system using modified perturbation and
observation method,” Renew. Sustain. Energy Rev., vol. 50, pp.
Steady Large Moderate Small Small 109–129, 2015, doi: 10.1016/j.rser.2015.04.072.
Oscillations
[17] S. Messalti, A. G. Harrag, and A. E. Loukriz, “A new neural
System Simple Simple Medium Medium networks MPPT controller for PV systems,” 2015 6th Int. Renew.
Complexity Energy Congr. IREC 2015, 2015, doi:
10.1109/IREC.2015.7110907.
Dynamic Poor Medium High High [18] F. Chekired, A. Mellit, S. A. Kalogirou, and C. Larbes, “Intelligent
Response maximum power point trackers for photovoltaic applications using
FPGA chip: A comparative study,” Sol. Energy, vol. 101, pp. 83–
99, 2014, doi: 10.1016/j.solener.2013.12.026.

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.
[19] S. Lyden and M. E. Haque, “Maximum Power Point Tracking using differential evolution algorithm,” Energy Build., vol. 67, pp.
techniques for photovoltaic systems: A comprehensive review and 245–252, 2013, doi: 10.1016/j.enbuild.2013.07.085.
comparative analysis,” Renew. Sustain. Energy Rev., vol. 52, pp. [38] K. S. Tey, S. Mekhilef, H. T. Yang, and M. K. Chuang, “A
1504–1518, 2015, doi: 10.1016/j.rser.2015.07.172. differential evolution based MPPT method for photovoltaic
[20] B. Bendib, H. Belmili, and F. Krim, “A survey of the most used modules under partial shading conditions,” Int. J. Photoenergy,
MPPT methods: Conventional and advanced algorithms applied vol. 2014, 2014, doi: 10.1155/2014/945906.
for photovoltaic systems,” Renew. Sustain. Energy Rev., vol. 45, [39] M. A. M. Ramli, K. Ishaque, F. Jawaid, Y. A. Al-Turki, and Z.
pp. 637–648, 2015, doi: 10.1016/j.rser.2015.02.009. Salam, “A modified differential evolution based maximum power
[21] S. Saravanan and N. Ramesh Babu, “Maximum power point point tracker for photovoltaic system under partial shading
tracking algorithms for photovoltaic system - A review,” Renew. condition,” Energy Build., vol. 103, pp. 175–184, 2015, doi:
Sustain. Energy Rev., vol. 57, pp. 192–204, 2016, doi: 10.1016/j.enbuild.2015.06.058.
10.1016/j.rser.2015.12.105. [40] M. Miyatake, M. Veerachary, F. Toriumi, N. Fujii, and H. Ko,
[22] T. Radjai, L. Rahmani, S. Mekhilef, and J. P. Gaubert, “Maximum power point tracking of multiple photovoltaic arrays:
“Implementation of a modified incremental conductance MPPT A PSO approach,” IEEE Trans. Aerosp. Electron. Syst., vol. 47,
algorithm with direct control based on a fuzzy duty cycle change no. 1, pp. 367–380, 2011, doi: 10.1109/TAES.2011.5705681.
estimator using dSPACE,” Sol. Energy, vol. 110, pp. 325–337, [41] K. Ishaque, Z. Salam, M. Amjad, and S. Mekhilef, “An improved
2014, doi: 10.1016/j.solener.2014.09.014. particle swarm optimization (PSO)-based MPPT for PV with
[23] Y. Wang, L. Ding, and N. Li, “The application of fuzzy parameters reduced steady-state oscillation,” IEEE Trans. Power Electron.,
self-tuning PID controller in MPPT of photovoltaic power vol. 27, no. 8, pp. 3627–3638, 2012, doi:
system,” Proc. 2011 Int. Conf. Transp. Mech. Electr. Eng. TMEE 10.1109/TPEL.2012.2185713.
2011, no. Figure 2, pp. 1129–1132, 2011, doi: [42] K. Ishaque and Z. Salam, “A deterministic particle swarm
10.1109/TMEE.2011.6199403. optimization maximum power point tracker for photovoltaic
[24] F. Bouchafaa, D. Beriber, and M. S. Boucherit, “Modeling and system under partial shading condition,” IEEE Trans. Ind.
simulation of a gird connected PV generation system with MPPT Electron., vol. 60, no. 8, pp. 3195–3206, 2013, doi:
fuzzy logic control,” 2010 7th Int. Multi-Conference Syst. Signals 10.1109/TIE.2012.2200223.
Devices, SSD-10, 2010, doi: 10.1109/SSD.2010.5585530. [43] J. Ahmed and Z. Salam, “A Maximum Power Point Tracking
[25] F. Chekired, C. Larbes, D. Rekioua, and F. Haddad, (MPPT) for PV system using Cuckoo Search with partial shading
“Implementation of a MPPT fuzzy controller for photovoltaic capability,” Appl. Energy, vol. 119, pp. 118–130, 2014, doi:
systems on FPGA circuit,” Energy Procedia, vol. 6, pp. 541–549, 10.1016/j.apenergy.2013.12.062.
2011, doi: 10.1016/j.egypro.2011.05.062. [44] L. L. Jiang, D. L. Maskell, and J. C. Patra, “A novel ant colony
[26] A. Messai, A. Mellit, P. A. Massi, A. Guessoum, and H. Mekki, optimization-based maximum power point tracking for
“FPGA-based implementation of a fuzzy controller (MPPT) for photovoltaic systems under partially shaded conditions,” Energy
photovoltaic module,” Energy Convers. Manag., vol. 52, no. 7, pp. Build., vol. 58, pp. 227–236, 2013, doi:
2695–2704, 2011, doi: 10.1016/j.enconman.2011.01.021. 10.1016/j.enbuild.2012.12.001.
[27] N. Khaehintung, K. Pramotung, and P. Sirisuk, “RISC [45] K. Sundareswaran, S. Peddapati, and S. Palani, “MPPT of PV
microcontroller built-in fuzzy logic controller for maximum power systems under partial shaded conditions through a colony of
point tracking in solar-powered for battery charger,” IEEE Reg. 10 flashing fireflies,” IEEE Trans. Energy Convers., vol. 29, no. 2,
Annu. Int. Conf. Proceedings/TENCON, vol. D, no. 1, pp. 637– pp. 463–472, 2014, doi: 10.1109/TEC.2014.2298237.
640, 2004, doi: 10.1109/tencon.2004.1415013. [46] A. soufyane Benyoucef, A. Chouder, K. Kara, S. Silvestre, and O.
[28] C. Larbes, S. M. Aït Cheikh, T. Obeidi, and A. Zerguerras, A. Sahed, “Artificial bee colony based algorithm for maximum
“Genetic algorithms optimized fuzzy logic control for the power point tracking (MPPT) for PV systems operating under
maximum power point tracking in photovoltaic system,” Renew. partial shaded conditions,” Appl. Soft Comput. J., vol. 32, pp. 38–
Energy, vol. 34, no. 10, pp. 2093–2100, 2009, doi: 48, 2015, doi: 10.1016/j.asoc.2015.03.047.
10.1016/j.renene.2009.01.006. [47] S. Singh, S. Manna, M. I. H. Mansoori, and A. K. Akella,
[29] P. C. Cheng, B. R. Peng, Y. H. Liu, Y. S. Cheng, and J. W. Huang, “Implementation of Perturb Observe MPPT Technique using
“Optimization of a fuzzy-logic-control-based MPPT algorithm Boost converter in PV System,” Int. Conf. Comput. Intell. Smart
using the particle Swarm optimization technique,” Energies, vol. Power Syst. Sustain. Energy, CISPSSE 2020, pp. 29–32, 2020, doi:
8, no. 6, pp. 5338–5360, 2015, doi: 10.3390/en8065338. 10.1109/CISPSSE49931.2020.9212203.
[30] W. M. Lin, C. M. Hong, and C. H. Chen, “Neural-network-based [48] P. Tamas, “Analyzing and modeling PV with " P & O " MPPT
MPPT control of a stand-alone hybrid power generation system,” Algorithm by MATLAB / SIMULINK,” no. V.
IEEE Trans. Power Electron., vol. 26, no. 12, pp. 3571–3581, [49] L. Xu, R. Cheng, and J. Yang, “A New MPPT Technique for Fast
2011, doi: 10.1109/TPEL.2011.2161775. and Efficient Tracking under Fast Varying Solar Irradiation and
[31] Y. H. Liu, C. L. Liu, J. W. Huang, and J. H. Chen, “Neural- Load Resistance,” Int. J. Photoenergy, vol. 2020, 2020, doi:
network-based maximum power point tracking methods for 10.1155/2020/6535372.
photovoltaic systems operating under fast changing [50] A. Sharma, S. Gupta, and N. Kumar, “Modelling and Comparison
environments,” Sol. Energy, vol. 89, pp. 42–53, 2013, doi: of Different MPPT Algorithms for a Standalone PV System,”
10.1016/j.solener.2012.11.017. Proc. Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2020, no.
[32] M. Hatti, A. Meharrar, and M. Tioursi, “Power management Icesc, pp. 989–995, 2020, doi:
strategy in the alternative energy photovoltaic/PEM Fuel Cell 10.1109/ICESC48915.2020.9155717.
hybrid system,” Renew. Sustain. Energy Rev., vol. 15, no. 9, pp.
5104–5110, 2011, doi: 10.1016/j.rser.2011.07.046.
[33] H. Boumaaraf, A. Talha, and O. Bouhali, “A three-phase NPC
grid-connected inverter for photovoltaic applications using neural
network MPPT,” Renew. Sustain. Energy Rev., vol. 49, pp. 1171–
1179, 2015, doi: 10.1016/j.rser.2015.04.066.
[34] A. A. Kulaksiz and R. Akkaya, “A genetic algorithm optimized
ANN-based MPPT algorithm for a stand-alone PV system with
induction motor drive,” Sol. Energy, vol. 86, no. 9, pp. 2366–2375,
2012, doi: 10.1016/j.solener.2012.05.006.
[35] A. Chaouachi, R. M. Kamel, and K. Nagasaka, “A novel multi-
model neuro-fuzzy-based MPPT for three-phase grid-connected
photovoltaic system,” Sol. Energy, vol. 84, no. 12, pp. 2219–2229,
2010, doi: 10.1016/j.solener.2010.08.004.
[36] Y. Shaiek, M. Ben Smida, A. Sakly, and M. F. Mimouni,
“Comparison between conventional methods and GA approach for
maximum power point tracking of shaded solar PV generators,”
Sol. Energy, vol. 90, pp. 107–122, 2013, doi:
10.1016/j.solener.2013.01.005.
[37] M. F. N. Tajuddin, S. M. Ayob, Z. Salam, and M. S. Saad,
“Evolutionary based maximum power point tracking technique

Authorized licensed use limited to: Graphic Era (Deemed to be University). Downloaded on March 13,2023 at 05:13:29 UTC from IEEE Xplore. Restrictions apply.