Journal of Ambient Intelligence and Humanized Computing

https://doi.org/10.1007/s12652-018-0961-6

ORIGINAL RESEARCH

Comparative analysis of intelligent controller based microgrid

integration of hybrid PV/wind power system
T. Hemanand1 · N. P. Subramaniam2 · M. Venkateshkumar3

Received: 13 December 2017 / Accepted: 6 August 2018

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Abstract
In present years the consumer power demand has been increased day by day due to pollution growth and new industry
establishments. The fossil fuel based power generation system unable to meet alone the consumer demand and environ-
mental issues. In this paper, we have been investigating different renewable energy sources for generate the electricity
and environmental safety. The hybrid renewable energy sources are very effective to generate the power even though
the absence of any one source. The simulation model of hybrid 60 kW PV and Wind power system developed using
Matlab Simulink. The renewable energy system is operated with MPPT techniques based ANFIS controller for improv-
ing the system efficiency. The hybrid renewable energy system is presented as interconnected Microgrid system by
using an intelligent controller. The proposed intelligent controller based phase loop locker show improvement in the
system stability during Microgrid integration simulation. The proposed system analysed with the different intelligent
controller such as fuzzy, ANN and ANFIS using Matlab Simulink environment. The simulation results are evaluated
and compared with the existing system. Finally recommends the proposed system for Microgrid integration of hybrid
renewable energy system.

Keywords  Hybrid renewable energy · Photovoltaic (PV) · Wind · Intelligent control

1 Introduction is accessible for various topologies, hold precious power

There unit many places among the ecosphere wherever the
depleted zones unit established isolated from well-built
humanities because of lack of convenience of power. In
last decades, increasing worries for global warning and
unpredictable fossil fuel prices have made renewable
energy sources as an alternative source and environment
friendly. The one achievable because of provide electric-
ity for a faraway space by victimization renewable energy
based entirely microgrid system. The planned topology
throughout this paper consists of hybrid PV—wind energy
and battery management system. a substantial literature
* T. Hemanand
hemanand.miteee@gmail.com
M. Venkateshkumar
venkatmme@ieee.org
1
Sathyabama University, Chennai, India
2
Pondicherry Engineering College, Puducherry, India
3 benefits.
Aarupadai Veedu Institute of Technology, Chennai, India
physical science for PV and Wind energy conversion
systems, Intelligent controller, MPPT techniques, Grid-
connected converter topologies etc demand (Indumathi
et al. 2012; Zhang et al. 2013). The PV and wind energy
systems unit perpetually operated with MPPT techniques
employing a raise DC–DC convertor to generating most
power at varied climate. throughout this paper, the extraor-
dinarily regarded formula ANFIS MPPT techniques unit
used for each PV and Wind Energy system for obtaining
most power at very unsteady climate. associate intelligent
controller-based voltage provide convertor is employed
to integrate hybrid PV/Wind into microgrid with biface
power flow capability and power quality improvement.
The microgrid could also be a heap of reliable to supply its
preparing to shopper with tons of smart by victimization
eco-friendly resources, less transmission power losses and
rising power quality compared with commonplace power
plants. Thus, the planned system and management ways in
which within which provides a well-designed integration
of hybrid PV/Wind into a microgrid. it’s the following

13
Vol.:(0123456789)

1. The MPPT techniques applied to each PV and energy
system to induce most power at very unsteady climate.
2. Intelligent Controller based totally Battery management
system provide} responsibility of power offer to the con-
sumer.
3. The planned ANFIS controller will operate in dis-
similar approaches of microgrid connected topolo-
gies, ensuring correct operational conditions and sleek
power transition between hybrid PV/Wind facility into
Microgrid.
The paper is organized as follows. Section 2 presents the
ANFIS based MPPT operation for PV system and analyze
system performance. Sections 3 and 4 presents the ANFIS
controller based wind / PV system power and analyze sys-
tem performance. The hybrid renewable energy with grid
integration simulation models and results are presented in
Sect. 5. Finally, evaluation of simulation results and pro-
nouncement of proposed research work is presented in
Sect. 6.
2 MPPT controller
The renewable energy sources play a significant role to meet
consumer power demand due to their ample obtainability
and a smaller amount impact of environment. The main dif-
ficulty in PV energy expansion is the investment cost of the
PV power system implementation (Vigneysh et al. 2013).
PV energy generation is not constant throughout the day due
to the change of weather. The efficiency of power genera-
tion is very low (the range of efficiency is only 9–17% in
low irradiation regions). Therefore, MPPT technologies have
an important role in PV power generation to operate in the
maximum power generation at various weather conditions.
The various MPPT methods are established with respect to
usage of equipment and cost.
2.1 ANFIS controller modelling
This section presents the simulation and control of an
ANFIS inference approach for MPPT of PV and Wind
Power system. The MPPT controller has major rule to gen-
erate maximum power due to nonlinear weather condition.
ANFIS is a graphical network representation and Sugeno
type- fuzzy system, capable by neural learning capabilities.
To illustrate the representational strength of ANFIS, the neu-
ral fuzzy control system consider here is based on Tagaki—
Sugeno—kang (TSK) fuzzy rules whose consequent part are
linear combinations of the preconditions (Shiva et al. 2017;
Gupta et al. 2016).
13
T. Hemanand et al.
2.1.1 PV ANFIS design
TSK fuzzy rules in the following forms for PV MPPT
design, Two inputs ­X1 (PV Voltage) and ­X2 (PV Current)
and one output Y (Duty Cycle).
R1: IF PV Voltage is ­A11 AND PV current is ­A21 THEN
Y = a01 + ­a11 PV Voltage + a21 PV current,
R2: IF PV Voltage is ­A21 AND PV current is ­A22 THEN
Y = a02 + ­a12 PV Voltage + a22 PV current
𝜇1f 1 + 𝜇2f 2
Y= (1)
𝜇1 + 𝜇2
Where µj are firing strength of ­Rj (j = 1, 2).
2.1.2 Wind ANFIS Design
TSK fuzzy rules in the following forms for Wind MPPT
design, Two inputs ­X1 (Wind Voltage) and ­X2 (Wind Cur-
rent) and one output Y (Duty Cycle).
R1: IF Wind Voltage is A­ 11 AND Wind current is A­ 21
1 1 1
THEN Y = a0 + ­a1 Wind Voltage + a2 Wind current.
R2: IF Wind Voltage is A­ 21 AND Wind current is A­ 22
2 2 2
THEN Y = a0 + ­a1 Wind Voltage + a2 Wind current
𝜇1f 1 + 𝜇2f 2
Y= (2)
𝜇1 + 𝜇2
Where µj are firing strength of ­Rj (j = 1, 2).
3 Simulation of ANFIS based MPPT
controller
In this method, the ANFIS logic controller is designed for
MPPT control of PV system (Vide Fig. 1). This controller
has two major parts such as ANN controller design and the
input and output membership function of fuzzy logic con-
troller and then forming the fuzzy IF-then rules. Finally,
Fig. 1  ANFIS controller based MPPT for PV system
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 2  MATLAB simulation model for ANFIS controller based MPPT for PV system

Fig. 3  ANFIS controller network for MPPT of PV system

the fuzzy controller generates the duty cycle based on input
data.
Step 1: The ANFIS controller, network has been train-
ing using input data, such as PV parameters under various
weather conditions and target data (duty Cycle) based on
changing inputs. The above process has been developed
using Neuro-Fuzzy training tools in MATLAB environment
(Vide Figs. 2, 3, 4).
Step 2: The trained data are validated and tested to
provide best solution. The ANN controller network is
developing fuzzy input and output membership func-
tions and then fuzzy IF-Then rules after completing the
processes of training, testing and validation (Venkatesh-
kumar 2017).
Step 4: Finally, ANFIS controller is implemented for
MPPT control of PV system. The ANN controller generates
the duty cycle based on input data and then the signal is fed
into a PWM generator to generate the pulse for DC–DC
converter.
3.1 Results
The ANFIS controller is implemented in MPPT simulation
model and simulation at various weather conditions and
rules are presented in Table 1. The simulation results of
PV power generation waveform are analyzed with differ-
ent solar irradiation conditions such as 250, 500, 750 and
1000 W/M2 as shown in Fig. 5.

13
 T. Hemanand et al.

Fig. 4  ANFIS training for MPPT of PV system

Table 1  Fuzzy rules – PV Fuzzy membership Current small Current medium Current high
MPPT
Voltage small Duty cycle high Duty cycle high Duty cycle high
Voltage medium Duty cycle high Duty cycle medium Duty cycle medium
Voltage high Duty cycle medium Duty cycle medium Duty cycle small

4 PMSG design with and without MPPT 5. Wind speed—base = 12 m/s

controller
A control method to control wind turbine rotor speed by
controlling the generating controlling torque which is
called MPPT (maximum Power Point Tracking) control-
ler. The blade pitching drive produces a delay in response
time with response to act accordingly with change in wind
conditions, such as turbulent and gusty winds, which plays
an influence role on the energy yield and causes subse-
quent mechanical stress on the wind turbine. Conversely,
to maximize the electric power production, the generator
rotor speed can be controlled electrically. MPPT based
control techniques are been developed with a motive of
achieving the maximum power coefficient. The generator
output power, in a variable speed wind energy system is
efficiently controlled with the help of a power electronics
based converters. In this paper, the author analyzed the
ANFIS based MPPT of Wind power system (Mokryani
et al. 2013).
The proposed PMSG design parameter as follows
1. Mechanical output power = 10,000 W
2. Maximum voltage Vmax = 230 V
3. Maximum current Imax = 43 amp
4. Base electrical generator power = 9999.77 VA
6. Rotational speed—base = 1 p.u
7. At base wind speed, maximum power = 0.8 p.u
8. Pitch angle = 0 deg
The proposed system has been simulated MATLAB Sim-
ulink environment at various weather conditions as shown
in Fig. 6. The turbine mechanical power vs generation speed
Characteristics are presented in Fig. 7.
4.1 Modeling an ANFIS based MPPT
The estimation of the wind speed using the ANFIS con-
cepts is presented here. The ANFIS is trained routinely by
least-square inference and the back-propagation algorithm.
Figure 8 shows the structure of ANFIS with two inputs and
one output. According to the designed model, the ANFIS
network could make decision to estimate maximal wind
speed to be achieved based on the inputs/outputs data used
for training.
The ANFIS controller has been designed for MPPT con-
troller for Wind Energy system as presented in Fig. 8. The
proposed ANFIS MPPT controller has two input triangle
membership function such as input one WES voltage and
second input current. The rules are presented in Table 2.
The output of fuzzy control is triangle membership function

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 5  a ANFIS based 10 kW PV system output power waveform at various irradiance. b ANFIS based 10 kW PV system output voltage wave-
form at various irradiance

Fig. 6  simulation model of PMSG based WES without MPPT controller

13
 T. Hemanand et al.

Fig. 7  Wind turbine characteristics

Fig. 8  Structure of ANFIS controller

Table 2  Fuzzy rules—wind Fuzzy membership Current small Current medium Current high
MPPT
Voltage small Duty cycle high Duty cycle high Duty cycle high
Voltage medium Duty cycle high Duty cycle medium Duty cycle medium
Voltage high Duty cycle medium Duty cycle medium Duty cycle small

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…
Fig. 9  ANFIS based MPPT controller for WES with buck converter
Fig. 10  ANFIS control system
training
such as duty cycle. ANFIS based MPPT controller reference
model is developed using ANFIS editor of MATLAB/Sim-
ulink software package (Figs. 9, 10, 11, 12, 13, 14, 15, 16).
5 Microgrid integration of hybrid PV/wind
power system
The proposed Microgrid power system model is presented
in Fig. 17. The proposed model has been simulated in
Matlab environment. The simulation has been developed
hybrid PV/Wind power and design intelligent controller
for voltage source converter (Qi et al. 2017; Liu et al.
2013) (Fig. 18).
The control of voltage source converter has phased
locked loop, Voltage regulator and current regulator as
shown in Fig. 19. The current regulator has been operated
with intelligent controller and analysis their operation with
different intelligent controller such as Fuzzy and ANN
(Mokryani et al. 2013; Qiao et al. 2011). Finally compare
the simulation results and its performance are evaluated
then choose best controller for Microgrid (Zhao Dongmei
et al. 2012; Samir et al. 2018).
5.1 Fuzzy controller for VSC
The fuzzy logic controller has been designed for current
regulator for VSC. The fuzzy controller has two input
13

Fig. 11  ANFIS control system
output
Fig. 12  ANFIS control system rules
signals and two output signals such as input (direct axis
and quadrature axis current) output (regulated direct axis
and quadrature axis current) shown in Fig. 20 (Ferraro
et al. 2017; Rana et al. 2017). The direct axis current
value is positive converter deliver the active power to
Microgrid and quadrature axis current value is negative
converter observe the reactive power from Microgrid
(Pathak et al. 2014; Zhao et al. 2017). The proposed fuzzy
control has been applied hybrid PV /Wind with Microgrid
and its voltage source converter as shown in Fig. 21. The
Matlab simulation results are presented such three-phase
voltage wave form and three phase THD value as shown
in Figs. 22, 23, 24 and 25 respectively.
13
T. Hemanand et al.
5.2 Fuzzy based results
Figures 22, 23, 24 and 25.
5.3 ANN controller for VSC
The ANN controller has been developed for current regu-
lator of VSC as shown in Fig. 26 (Farrokhabadi et al.
2018). The ANN controller has been trained by back
propagation method and provides the 70% data for train-
ing, 15% data for testing and 15% data for validation
as shown in Fig. 27. The error of ANN training data as
shown in Fig. 28. After ANN training the network has
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 13  WECS voltage and current RMS waveform

Fig. 14  WECS output power and wind speed waveform

been analysed overall results as shown in Fig.  29 and Finally, the different intelligent controller results are
finally ANN network has been developed after success- compared as shown in Table 1 and the results are evalu-
ful training for Current regulation for VSC as shown in ated with IEEE 1547.
Fig. 30. The proposed ANN controller is applied for VSC
of hybrid PV/Wind based Microgrid system (Milczarek
2017; Sedghi and Fakharian 2017). The simulation results 5.4 ANN based micro grid system
are presented such as three phase voltage waveforms and
three phase voltage THD as shown in Figs. 31, 32, 33 and Figures 31, 32, 33 and 34.
34 respectively.

13
 T. Hemanand et al.

Fig. 15  WECS generator RPM and duty cycle waveform

Fig. 16  a WECS power output waveform at various wind speed (ANFIS). b WECS power output waveform at various wind speed (ANFIS)

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 17  Proposed microgrid integration of hybrid PV/Wind power system

Fig. 18  Hybrid PV/wind power system

5.5 ANFIS controller for VSC has been designed with two inputs and two outputs namely,
error value of ­Id and ­Iq and regulated ­Id and ­Iq respectively
The ANFIS controller has been developed in MATLAB (Vide Fig. 35).
Simulink environment for current regulator. This controller

13
 T. Hemanand et al.

Fig. 19  Voltage source converter (VSC) controller

Fig. 20  Fuzzy controller membership function and its rules for current regulator of VSC

The error value of ­I d and ­I q can be calculated by the
difference between ­Id, ­Iq reference generated by voltage
regulator and I­ d, ­Iq measured. Based on training of ANN
network fuzzy input, output membership function and
fuzzy rules are generated by controller (Vide Figs. 36,
37).
The ANFIS output signal is fed into feed forward cur-
rent regulator of converter. Figure 38 presents voltage and
current waveform of ANFIS controller based grid integra-
tion of Hybrid PV–FC power system. Its total harmonics
distortions values are presented in Figs. 39, 40 and 41
respectively.
6 Conclusion
The renewable energy based Microgrid power system has
been modeled and simulated in Matlab Simulink soft-
ware. The PV and Wind system has been simulated and
controlled by ANFIS controller then analyzed simulation

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 21  Fuzzy based current regulator

Fig. 22  Microgrid integration of hybrid PV and wind power system voltage waveform

Fig. 23  Voltage at phase R—THD level

13
 T. Hemanand et al.

Fig. 24  Voltage at phase Y—THD level

Fig. 25  Voltage at phase B—THD level

Fig. 26  ANN based current regulator

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 27  ANN training, testing, validation and over all performance

Fig. 28  ANN training performane

results under weather condition. The hybrid PV/ Wind

power system is modeled and integrated with Microgrid
power system by using ANFIS controller. The proposed
system analyzed with various intelligent control such as
Fuzzy, ANN and ANFIS. The simulation results are evalu-
ated and compared with dissimilar intelligent controller
performance. The Table 3 presented simulation results of
ANFIS controller based VSC has minimum level THD
observed compared with fuzzy and ANN based VSC and
improve the power system stability as well as quality in
all three phases. Finally based on simulation results per-
formance the ANFIS controller has been recommended to
hybrid PV/Wind based Microgrid power system.

Fig. 29  Over all performance of ANN network

13
 T. Hemanand et al.

Fig. 30  proposed ANN control-

ler for VSC

Fig. 31  Microgrid integration of hybrid PV and wind power system voltage waveform

Fig. 32  Voltage at Phase R—THD level

Fig. 33  Voltage at Phase Y—THD level

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 34  Voltage at Phase B—THD level

Fig. 35  ANFIS Controller model for current regulator

Fig. 36  ANFIS Controller train-

ing for current regulator

13
 T. Hemanand et al.

Fig. 37  ANFIS controller rules for current regulator

Fig. 38  Voltage and current waveform ANFIS controller based grid integration hybrid PV–FC power system

Fig. 39  Voltage at phase R—THD level

13
Comparative analysis of intelligent controller based microgrid integration of hybrid PV/wind…

Fig. 40  Voltage at phase Y—THD level

Fig. 41  Voltage at phase B—THD level

Table 3  Comparison THD of IEEE 1st international conference on power electronics, intel-

Phase THD
proposed system for fuzzy and ligent control and energy systems (ICPEICES), Delhi, pp 1–6
ANN R (%) Y (%) B (%) Indumathi R, Venkateshkumar M, Raghavan R,(2012) Integration of
D-Statcom based photovoltaic cell power in low voltage power
Fuzzy 18.96 19.77 4.53 distribution grid. Advances in engineering, science and manage-
ANN 11.33 21.52 12.50 ment (ICAESM), International Conference on, Nagapattinam,
Tamil Nadu, pp 460–465
ANFIS 1.44 1.45 1.45
Liu S, Wu Z, Dou X, Zhao B, Zhao S, Sun C (2013) Optimal configu-
ration of hybrid solar-wind distributed generation capacity in a
grid-connected microgrid. In: Innovative Smart Grid Technolo-
References gies (ISGT), 2013 IEEE PES, Washington, DC, 2013, pp 1–6
Milczarek A (2017) Harmonic power sharing between power electron-
ics converters in islanded AC microgrid. 2017 Progress in Applied
Dongmei Z, Nan Z, Liu Y (2012) Micro-grid connected/islanding
Electrical Engineering (PAEE), Koscielisko, Poland, pp 1–7
operation based on wind and PV hybrid power system. IEEE PES
Mokryani G, Siano P, Piccolo A (2013) Fault ride-through enhance-
Innovative Smart Grid Technologies, Tianjin, 2012, pp 1–6
ment of wind turbines in distribution networks. J Ambient
Farrokhabadi M, Koenig S, Canizares CA, Bhattacharya K, Leibfried
Intell Human Comput 4:605. https​: //doi.org/10.1007/s1265​
T (2018) Battery energy storage system models for microgrid sta-
2-012-0162-7
bility analysis and dynamic simulation. IEEE Trans Power Syst
Pathak G, Singh B, Panigrahi BK (2014) Back propagation algorithm
99:1–1
based controller for autonomous wind-DG microgrid. In: Power
Ferraro P, Crisostomi E, Raugi M, Milano F (2017) Analysis of the
India international conference (PIICON), 2014 6th IEEE, Delhi,
impact of microgrid penetration on power system dynamics.
pp 1–5
IEEE Trans Power Syst 32(5):4101–4109
Qi G, Chen A, Chen J (2017) Improved control strategy of inter-
Gupta S, Garg R, Singh A (2016) Grid integrated PMSG based Wind
linking converters with synchronous generator characteristic in
energy system: modelling, control and simulation. In: 2016

13

islanded hybrid AC/DC microgrid. In: CPSS transactions on
power electronics and applications, pp 149–158
Qiao W, Sharma A, Hudgins JL, Jones EG, Rilett L (2011) Wind/
solar hybrid generation-based roadway microgrids. 2011 IEEE
power and energy society general meeting, San Diego, CA,
pp 1–7
Rana R, Singh M, Mishra S (2017) Design of modified droop con-
troller for frequency support in microgrid using fleet of electric
vehicles. IEEE Trans Power Syst 32(5):3627–3636
Samir A, Taha M, Sayed MM, Ibrahim A (2018) Efficient PV-grid
system integration with PV- voltage-source converter reactive
power support. J Eng 2:130–137
Sedghi L, Fakharian A (2017) Voltage and frequency control of an
islanded microgrid through robust control method and fuzzy
droop technique. In: 2017 5th Iranian Joint Congress on Fuzzy
and Intelligent Systems (CFIS), Qazvin, Iran, pp 110–115
Shiva C, Bhavani R, Prabha NR (2017) Power quality improvement
in a grid integrated solar PV system. In: 2017 IEEE interna-
tional conference on intelligent techniques in control, optimi-
zation and signal processing (INCOS), Srivilliputhur, pp 1–6
Venkateshkumar M (2017) Comparative analysis of hybrid intelligent
controller based mppt of fuel cell power system. In: an IEEE
International conference on smart technologies and management
for computing, communication, controls, energy and materials
(ICSTM), pp 155–159
13
T. Hemanand et al.
Venkateshkumar M, Indumathi R, Poornima P (2012) Photovoltaic cell
power generation for stand-alone applications. In: Advances in
engineering, science and management (ICAESM), 2012 interna-
tional conference on, Nagapattinam, Tamil Nadu, pp 57–62
Vigneysh T, Kumarappan N, Arulraj R (2013) Operation and control of
wind/fuel cell based hybrid microgrid in grid connected mode. In:
Automation, computing, communication, control and compressed
sensing (iMac4s), international multi-conference on, Kottayam,
pp 754–758
Zhang J, Guo D, Wang F, Zuo Y, Zhang H (2013) Research on energy
management strategy for islanded microgrid based on hybrid
storage device. In: Renewable energy research and applications
(ICRERA), 2013 international conference on, Madrid, pp 91–96
Zhao H, Hong M, Lin W, Loparo KA (2017) Voltage and frequency
regulation of microgrid with battery energy storage systems. In:
IEEE Transactions on smart grid, vol 99, pp 1–1
Publisher’s Note Springer Nature remains neutral with regard to
jurisdictional claims in published maps and institutional affiliations.