Analysis and Implement of Hybrid ANN PandO Based MPPT Controller to Enhance Efficiency of Photovoltaic System

International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 6 Issue 5, July-August 2022 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470
@ IJTSRD | Unique Paper ID – IJTSRD50589 | Volume – 6 | Issue – 5 | July-August 2022 Page 907
Analysis and Implement of Hybrid ANN - P&O Based MPPT
Controller to Enhance Efficiency of Photovoltaic System
Shubham Dwivedi1
, Poonam Jounjare2
1
Student, 2
Assistant Professor,
1,2
School of Research and Technology, People’s University, Bhopal, Madhya Pradesh, India
ABSTRACT
Solar energy is a potential energy source in Myanmar and its
application is ever increasing. In solar PV application, the
photovoltaic module is needed to harvest this kind of energy. The PV
module exhibit nonlinear I–V and P– V characteristics. The
maximum power produced varies with both irradiance and
temperature. The maximum efficiency is achieved when PV works at
its maximum power point which can be obtained by using suitable
MPPT algorithm. Most of PV systems use conventional MPPT
methods such as incremental conductance (IC) and perturb and
observe (P and O). With the advanced in control technology, the
intelligent control techniques are commonly used in all areas. A
conventional MPPT controller is used to maximise the conversion
efficiency under normal conditions but fails in abnormal conditions.
This paper proposes an intelligent ANN-P&O MPPT controller for
the Boost converter that utilises the effective regions of both ANN
and P&O methods to identify the global maximum point in order to
improve the conversion efficiency of a PV system and a comparative
simulation study of three MPPT algorithms specifically (i) perturb
and observe, (ii) artificial neural network (ANN), and (iii) NN –
P&O. MATLAB/SIMULINK software is used to test how well the
controller works in unusual situations and compare it to its individual
counterparts.
KEYWORDS: Maximum Power Point Tracking, Perturb and Observe
Method, ANN Method, Boost Converter, Hybrid NN – P&O
How to cite this paper: Shubham
Dwivedi | Poonam Jounjare "Analysis
and Implement of Hybrid ANN - P&O
Based MPPT Controller to Enhance
Efficiency of Photovoltaic System"
Published in
International Journal
of Trend in
Scientific Research
and Development
(ijtsrd), ISSN: 2456-
6470, Volume-6 |
Issue-5, August
2022, pp.907-918, URL:
www.ijtsrd.com/papers/ijtsrd50589.pdf
Copyright © 2022 by author (s) and
International Journal of Trend in
Scientific 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)
I. INTRODUCTION
Spotless and sustainable power sources like
photovoltaic (PV) control is played a significant job
in electric power age, and become basic nowadays
because of deficiency and natural effects of
customary powers. The sunlight-based vitality is
straightforwardly changed over into electrical vitality
by sun based photovoltaic modules. As a result of
nonlinear I-V and PV qualities of PV sources, their
yield power is principally relied on the ecological
conditions and nature of burden associated. Thus,
these conditions will be influenced the general
productivity of the PV frameworks [1]. But the
productivity of the sun-based PV module is low.
Because of the mind-boggling expense of sun-based
cells, a most extreme power point tracker is expected
to work the PV cluster at its greatest power point.
Subsequently the greatest power is extricated from
the PV generator depends on three variables:
insolation, load profile (load impedance) and cell
temperature (surrounding temperature). To get the
most extreme power from PV, a greatest power point
tracker (MPPT) is utilized [2]. There are so many
methods and algorithms for tracking of the MPP of
the PV systems. In this paper, comparative
investigations of Perturb and observe (P&O)
algorithm and artificial neural network (ANN)
technique algorithm using dc-dc converter is done in
terms of the maximum power transfer capability of
these algorithms.
II. STAND -ALONE SOLAR POWER
SYSTEM
The solar PV system consists of a PV module, the
dc/dc boost converter, the maximum power point
tracking algorithm and the load. Radiation (R) is
incident on the PV module. It generates a voltage (V)
IJTSRD50589

International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
and current (I) which will be fed into the load [3]. The
voltage power characteristic of a photovoltaic (PV)
array is nonlinear and time varying because of the
changes caused by the atmospheric conditions. When
the solar radiation and temperature varies the output
power of the PV module also changes. In order to
obtain the maximum efficiency of the PV module, it
must operate at the maximum point of the PV
characteristic. The most extreme power point relies
upon the temperature and irradiance which are non-
direct in nature. The greatest power point following
control framework is utilized and work viability on
the non-straight varieties in the parameters, such as
temperature and radiations [4]. A MPPT is used for
extracting the maximum power from the solar PV
module and transferring that power to the load. A
dc/dc converter (boost converter) serves the purpose
of transferring maximum power from the solar PV
module to the load. A dc/dc converter acts as an
interface between the load and the module. The dc/dc
converter with maximum power point tracking
algorithm and the load is shown in Fig. 1. By
changing the duty cycle, the load impedance 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. Therefore, MPPT techniques are
needed to maintain the PV array’s operating at its
MPP [3]. In this paper, two most popular of MPPT
technique (Perturb and Observe (P&O) methods and
artificial neural network (ANN) methods and dc-dc
converter will be involved in comparative study.
MPPT
DC
DC
PV module Load
Fig. 1 Block Diagram of PV System with MPPT
III. MAXIMUM POWER POINT TRACKING
Most extreme Power Point Tracking (MPPT) is helpful apparatus in PV application. Sun oriented radiation and
temperature are the primary factor for which the electric power provided by a photovoltaic framework. The
voltage at which PV module can create greatest power is called 'most extreme power point ( pinnacle control
voltage). The primary rule of MPPT is in charge of separating the greatest conceivable power from the
photovoltaic and feed it to the heap by means of dc to dc converter which steps up/ down the voltage to required
size [5]. There are many maximum power point techniques. Among them, two MPPT techniques of ANN,
perturb and observe (P&O) have been selected for the purpose of comparison in this paper.
A. DC/DC Boost Converter
The dc-dc converter is used to supply a regulated dc output with the given dc input. These are widely used as an
interface between the photovoltaic panel and the load in photovoltaic generating systems. The load must be
adjusted to match the current and voltage of the solar panel so as to deliver maximum power. The dc/dc
converters are described as power electronic switching circuits. It converts one form of voltage to other. These
may be applicable for conversion of different voltage levels. Fig.2 shows the circuit diagram of dc-dc boost
convertor [7].
Fig. 2 Circuit Diagram of Boost Converter
The dc-dc boost converter circuit consists of Inductor (L), Diode (D), Capacitor (C), load resistor (RL), the
control switch(S). These components are connected in such a way with the input voltage source (Vin) so as to
step up the voltage. The output voltage of the boost converter is controlled by the duty cycle of the switch.
Hence by varying the ON time of the switch, the output voltage can be varied. The relationships of input voltage,
output voltage and duty cycle are as follow:

(1)
Where, Vin, Vo are the input and output voltage of the converter and D is the duty cycle of the control switch.
B. DC/DC Buck-Boost Converter
A buck-boost converter is a type of dc-dc converter that has an output voltage magnitude either greater than or
less than the magnitude of the input voltage magnitude. It’s described by a voltage source connected in parallel to
an inductor, a reverse-biased free- wheeling diode, a capacitor, and a load of resistance R at the output terminal.
In MPPT with ANN technique, Vmppt will be lower than the input voltages in some conditions. Thus buck/boost
converter is more favorable than boost converter for ANN technique [7].
Fig. 3 Circuit Diagram of Boost Converter
(2)
Where, Vin, Vo are the input and output voltage of the converter and D is the duty cycle of the control switch.
C. ANN Technique
The ANN control system has to be trained before being used in the photovoltaic system. The neural network is a
powerful technique for mapping the input-output nonlinear function. The network tries to simulate its learning
process through the various input fed to it during each cycle of data interpretation. It changes its structure based
on the internal and external information that flows in and out of the network system.
The ANN control framework must be prepared before being utilized in the photovoltaic framework. The neural
system is an incredible method for mapping the info yield nonlinear capacity. In the proposed structure, a two
layer falling neural system method is fused that predicts the PV exhibit voltage at which the most extreme power
is achievable. These build up a non-direct connection between the information and yield with a concealed layer
that capacities with inclinations like neurons of the our mind. The hidden layer in the model is a two layer neural
network. This is then sent to layer 1 with 50 neurons where a process input synthesizes the signal with weights
and generates a tangent sigmoid transfer function. The output of layer 1 is the input for layer 2 with another set
of 50 neurons that assigns weightage to the values and generates a pure linear transfer function [8].
Fig.4. MPPT System with ANN Controller

D. Perturb and Observe (P&O) Technique
Fig. 5 State-flow Chart of P&O MPPT Technique
P&O is the most often utilized method to follow the greatest power because of its straightforward structure. This
method works by intermittently irritating the PV module terminal voltage and contrasting the PV yield control
and that of the past annoyance cycle [1]. As shown in Fig. 5 if the PV module operating voltage changes and
power increases the control system moves the operating point in that direction; otherwise, the operating point is
moved in the opposite direction.
IV. SIMULATION AND RESULTS
After modeling the Stand-Alone PV System, the comparative analysis of Maximum Power Point Tracking
Algorithms is analysed. The simulation models for Maximum Power Point Tracking Algorithms are executed
with MATLAB/Simulink version R2019a. The simulation results of Maximum Power Point Tracking
Algorithms for all the schemes are shown in the following sections.
Fig 6. MATLAB/ Simulink Hybrid NN – P&O MPPT Algorithm for Solar PV System

To analyse the performance of the output voltages, the output currents and the output power are measured as
shown. The PV parameters of the system are shown in Table I.
TABLE I PV PARAMETERS
Parameters Specifications
Maximum power, Pm 250 W
Series-connected modules per string 1 nos
Parallel strings 1 nos
Cells per module (Ncell) 60
Maximum power voltage, Vpm 30.7 V
Maximum power current, Ipm 8.15 A
Open circuit voltage, Voc 37.3V
Short circuit current, Ise 8.66 A
A. Simulation Results with Different Algorithms
For comparative study with different algorithms, three algorithms are applied for MPP tracking in this research
as (i) Perturb and Observe (P and O) method, (ii) ANN method And NN – P&O. The simulation results for
different algorithms under standard condition, 1000 W/m2 irradiation and C temperature are shown in the
following figures.
(a). Voltage
(b). Current

(c). Power
(d). Duty Cycle
Fig 7. PV Output (a) Voltage, (b) Current, (c) Power & (d) Duty Cycle with P&O Method.
(a). Voltage

(b). Current
(c). Power
(d). Duty Cycle
Fig 8. PV Output (a) Voltage, (b) Current, (c) Power & (d) Duty Cycle with ANN Method.

(a). Voltage
(b). Current
(c). Power

(d). Duty Cycle
Fig 9. PV Output (a) Voltage, (b) Current, (c) Power & (d) Duty Cycle with NN – P&O Method.
Fig 10 Comparison Between all three techniques
Fig. 10 shows comparison for power output variation under the temperature at constant irradiation 1000
W/m2. According to this fig. 10, the power provided and the transient performance by Hybrid NN – P&O is
better compared to P and O method and ANN Method.

B. Simulation Result Comparisons of MPPT Techniques
The simulation results of output voltage, output current, and output power for temperature of 25ºC and the
irradiation 1000 Wm-2 are shown in Table II. According to the simulation results, in comparison of the three
output powers, the power provided by NN – P&O technique is larger in 1000 W irradiation case.
TABLE II: COMPARISON OF SIMULATION RESULTS FOR 25ºC TEMPERATURE AND 1000
W IRRADIATION
Irradiation (W/m2
) Parameter
Algorithm
ANN P and O Hybrid NN – P&O
1000
Vo (V) 29.8 28.9 30.5
Io (A) 8.0438 8.0096 8.0596
Po (W) 249.1 248.9 249.8
The simulation results of output voltage, output current and output power for temperature of 25ºC and the
irradiation of 1000 Wm-2 are shown in Table III.
TABLE III: COMPARISON OF SIMULATION RESULTS FOR 1000 WM-2 IRRADIATIONS AND
TEMPERATURE
Temperature (ºC) Parameter
Algorithm
ANN P and O Hybrid NN – P&O
25
Vo (V) 29.8 28.9 30.5
Io (A) 8.0438 8.0096 8.0596
Po (W) 249.1 248.9 249.8
According to the simulation results. In comparison of the other two output powers, the power provided by NN –
P&O technique is larger in the temperature case.
V. Conclusion
Simulation results for ANN, P&O, and Hybrid NN–
P&O methods presented in this thesis show that the
Hybrid ANN-P&O controller tracks the Maximum
Power Point (MPP) quickly compared to the
individual P&O controller and ANN controller. The
NN–P&O method is very fast and precise in finding
and tracking the MPP in the case of rapidly changing
solar irradiation. Furthermore, this method can stably
extract the maximum power point under slowly
changing solar irradiation, and efficiency is better
with the combination of the improved P&O-ANN
method. On the other hand, the ANN method can
maintain its output voltage close to its maximum
power voltage (Vmp) and thus can provide more
power than the P and O methods. Again, the ANN
technique exhibits better transient response and
reaches steady state conditions more quickly. On the
contrary, when irradiation changes fast in a short
time, the P & O method fails to track the MPP. Also,
this method has high oscillation around MPP under
slow changing solar irradiation, which leads to high
power loss in the long term.
VI. Future Scope
The possibility to combine two or more
renewable energy sources, based on the natural
local potential of the users.
Combinations of algorithms and controllers, like
PSO, GA, Fuzzy Logic, and ANFIS, can be used
to make PV systems work more efficiently.
Environmental protection especially in terms of
carbon dioxide emissions reduction.
Low-cost wind energy and solar energy can be
competitive with nuclear, coal, and gas energy,
especially considering possible future cost trends
for fossil and nuclear energy. Diversity and
security of supply Quick deployment: modular
and easy to install.
REFERENCES
[1] PH Heera; V. Mini “Solar Photovoltaic System
with Power Quality Improvement” 2020
International Conference on Power Electronics
and Renewable Energy Applications (PEREA).
[2] Julio Fredy Chura Acero; Henry Pizarro
Viveros; Norman Jesús Beltrán Castañón;
Reynaldo Condori Yucra “mprovement of
Power Quality for Operation of the Grid-
Connected Photovoltaic Energy System
Considering the Irradiance Uncertainty” 2020
IEEE XXVII International Conference on
Electronics, Electrical Engineering and
Computing (INTERCON).
[3] Bhagyashree Parija; Santi Behera; Ruturaj
Pattanayak; Sasmita Behera “Power Quality
Improvement in Hybrid Power System using D-
STATCOM” 2019 3rd International
Conference on Computing Methodologies and
Communication (ICCMC).

[4] Nirav Patel; Nitin Gupta; B. Chitti Babu”
Multifunctional VSC Controlled Solar
Photovoltaic System with Active Power
Sharing and Power Quality (PQ) Improvement
Features” 2019 IEEE 1st International
Conference on Energy, Systems and
Information Processing (ICESIP).
[5] Tripurari Nath Gupta; Shadab Murshid; Bhim
Singh” Single-Phase Grid Interfaced Hybrid
Solar PV and Wind System using STF-FLL for
Power Quality Improvement” 2018 8th IEEE
India International Conference on Power
Electronics (IICPE).
[6] Varsha Rani; Om Prakash Mahela; Himanshu
Doraya “Power Quality Improvement in the
Distribution Network with Solar Energy
Penetration Using Distribution Static
Compensator” 2018 International Conference
on Computing, Power and Communication
Technologies (GUCON).
[7] Ravi Dharavath; I. Jacob Raglend; Atul
Manmohan “Implementation of solar PV —
Battery storage with DVR for power quality
improvement” 2017 Innovations in Power and
Advanced Computing Technologies (i-PACT).
[8] Priyank Shah; Ikhlaq Hussain; Bhim Singh
“Power quality improvement of grid interfaced
solar PV using adaptive line enhancer based
control scheme” 2017 6th International
Conference on Computer Applications In
Electrical Engineering-Recent Advances
(CERA).
[9] Jayasankar V N; Vinatha U “Implementation of
adaptive fuzzy controller in a grid connected
wind-solar hybrid energy system with power
quality improvement features” 2016 Biennial
International Conference on Power and Energy
Systems: Towards Sustainable Energy
(PESTSE).
[10] Rajan Kumar; Bhim Singh “Grid interfaced
solar PV powered brushless DC motor driven
water pumping system” 2016 7th India
International Conference on Power Electronics
(IICPE).
[11] G. Cipriani, V. D. Dio, F. Genduso, R. Miceli
and D. L. Cascia, "A new modified Inc-Cond
MPPT technique and its testing in a whole PV
simulator under PSC,” in Proc. of the 2015
IEEE Applied Power Electronics Conference
and Exposition (APEC), Charlotte, NC, pp.
3060- 3066.
[12] S. K. Ji, H. Y. Kim, S. S. Hong, Y. W. Kim and
S. K. Han, "Nonoscillation Maximum Power
Point Tracking algorithm for Photovoltaic
applications,” in Proc. of the 2014 Power
Electronics and ECCE Asia (ICPE & ECCE),
Jeju, pp. 380-385.
[13] Yi-Hsun Chiu, Yu-Shan Cheng, Yi-Hua Liu,
Shun-Chung Wang and ZongZhen Yang, "A
novel asymmetrical FLC-based MPPT
technique for photovoltaic generation system,”
in Proc. of the 2014 International Power
Electronics Conference (IPEC-Hiroshima 2014
- ECCE ASIA), Hiroshima, pp. 3778-3783.
[14] S. Dwari, L. Arnedo, S. Oggianu and V.
Blasko, "An advanced high performance
maximum power point tracking technique for
photovoltaic systems,” in Proc. of the 2013
IEEE Applied Power Electronics Conference
and Exposition (APEC), Long Beach, CA,
2013, pp. 3011- 3015.
[15] N. Mendis, K. M. Muttaqi, S. Sayeef and S.
Perera, "Standalone Operation of Wind
Turbine-Based Variable Speed Generators With
Maximum Power Extraction Capability,” IEEE
Transactions on Energy Conversion, vol. 27,
no. 4, pp. 822-834, Dec. 2012.
[16] S. Poshtkouhi and O. Trescases, "Multi-input
single-inductor dc-dc converter for MPPT in
parallel-connected photovoltaic applications,”
in Proc. of the 2011 IEEE Applied Power
Electronics Conference and Exposition
(APEC), Fort Worth, TX, pp. 41-47.
[17] I. Colak, E. Kabalci and G. Bal, "Parallel DC-
AC conversion system based on separate solar
farms with MPPT control,” in Proc. of the 2011
Power Electronics and ECCE Asia (ICPE &
ECCE), Jeju, pp. 1469-1475.
[18] G. Gamboa, J. Elmes, C. Hamilton, J. Baker,
M. Pepper and I. Batarseh, "A unity power
factor, maximum power point tracking battery
charger for low power wind turbines,” in Proc.
of the 2010 IEEE Applied Power Electronics
Conference and Exposition (APEC), Palm
Springs, CA, pp. 143-148.
[19] M. E. Haque, M. Negnevitsky and K. M.
Muttaqi,” A novel control strategy for a
variable-speed wind turbine with a permanent
magnet synchronous generator”. IEEE
Transactions on industry application, vol. 46,
no. 1, pp. 331-339, jan/feb 2010.

[20] M. Kiani, D. Torregrossa, M. Simoes, F.
Peyraut and A. Miraoui, "A novel maximum
peak power tracking controller for wind energy
systems powered by induction generators,” in
Proc. of the 2009 IEEE Electrical Power &
Energy Conference (EPEC), Montreal, QC, pp.
1-3.
[21] M. Shirazi, A. H. Viki and O. Babayi, "A
comparative study of maximum power
extraction strategies in PMSG wind turbine
system,” in Proc. of the 2009 IEEE Electrical
Power & Energy Conference (EPEC),
Montreal, QC, pp. 1-6.
[22] H. Patel and V. Agarwal, "Maximum Power
Point Tracking Scheme for PV Systems
Operating Under Partially Shaded Conditions,”
IEEE Transactions on Industrial Electronics,
vol. 55, no. 4, pp. 1689-1698, April 2008.
[23] M. E. Haque, K. M. Muttaqi and M.
Negnevitsky, “Control of a Stand alone variable
speed wind turbine with a permanent magnet
synchronous generator”, Proceeding of IEEE
power and energy society general meeting, pp.
20-24 july 2008.
[24] T. Esram and P. L. Chapman, "Comparison of
Photovoltaic Array Maximum Power Point
Tracking Techniques,” IEEE Transactions on
Energy Conversion, vol. 22, no. 2, June 2007,
pp. 439-449.
[25] T. F. Chan, L. L. Lai, “permanent magnet
machines for distributed generation: a review”,
Proc. 2007 IEEE power engineering annul
meeting, pp. 1-6.
[26] M. Fatu, L. Tutelea, I. Boldea, R. Teodorescu,”
Novel motion sensorless control of stand alone
permanent magnet synchronous generator
(PMSG) : harmonics and negative sequence
voltage compensation under nonlinear load ”,
2007 European conference on Power Electronic
and Application, 2-5 Sept. 2007.
[27] D. Sera, R. Teodorescu, and P. Rodriguez, “PV
panel model based on datasheet values”, IEEE
International Symposium on Industrial
Electronics, ISIE, PP. 2392-2396, 2007.
[28] H. Polinder, F. F. A van der Pijl, G. J. de
Vilder, P. J. Tavner, “Comparison of direct-
drive and geared generator concept for wind
turbine ”, IEEE Transactions on Energy
Conversion, vol., 21, no. 3, pp725-733, Sept.
2006.
[29] Seul Ki Kim, Eung Sang Kim, Jong Bo Ahn,
“Modeling and control of a Grid connected
Wind/PV Hybrid Generation System”,
2005/2006 IEEE PES Transmission and
Distribution Conference and Exhibition, 21-24
May 2006, pp. 1202-1207.
[30] Fernando Valencaga, Pablo F. Puleston and
Pedro E. Battaiotto, “Power Control of a
Solar/Wind Generation System Without Wind
Measurement: A Passivity/Sliding Mode
Approach”, IEEE Trans. Energy Conversion,
Vol. 18, No. 4, pp. 501-507, December 2003.

Analysis and Implement of Hybrid ANN PandO Based MPPT Controller to Enhance Efficiency of Photovoltaic System

More Related Content

Similar to Analysis and Implement of Hybrid ANN PandO Based MPPT Controller to Enhance Efficiency of Photovoltaic System (20)

More from ijtsrd (20)

Recently uploaded (20)

Analysis and Implement of Hybrid ANN PandO Based MPPT Controller to Enhance Efficiency of Photovoltaic System