International Journal of Applied Power Engineering (IJAPE)

Vol. 14, No. 2, June 2025, pp. 432~440

ISSN: 2252-8792, DOI: 10.11591/ijape.v14.i2.pp432-440  432

Prediction of wind power with various air speed using

neuro-fuzzy logic in MATLAB

Naimur Rahman Tushar1, Md. Tanvir Ahmed Shuvo1, Dilip Kumar Das2, Suman Chowdhury1
1
Department of Electrical and Electronic Engineering, International University of Business Agriculture and Technology,
Dhaka, Bangladesh
2
Department of Mathematics, International University of Business Agriculture and Technology, Dhaka, Bangladesh

Article Info ABSTRACT

Article history: The energy crisis in Bangladesh has persisted for many years, predominantly
reliant on fossil fuels for power generation, which is both economically and
Received Mar 19, 2024 environmentally costly. It is imperative to transition away from fossil fuels
Revised Dec 14, 2024 towards more cost-effective and eco-friendly energy sources. Wind energy
Accepted Jan 16, 2025 presents a viable solution to alleviate this crisis, especially considering
Bangladesh's extensive coastline, offering great potential for harnessing
significant amounts of electricity. Extensive fepresearch has been conducted
Keywords: on the feasibility of deploying wind turbines across various coastal zones to
generate power and facilitate irrigation seasons. This research delves into the
ANFIS operational principles and performance parameters of wind turbines.
MATLAB A modified fan is utilized to assess power generation under varying air
Neuro-fuzzy logic speeds, with data analysis conducted using neuro-fuzzy logic. The findings
Turbine reveal a minimal percentage error of 0.09, underscoring the reliability of
Wind power the proposed fuzzy model in predicting wind power output based on wind
speed. This underscores the potential for leveraging wind energy as a
sustainable and reliable alternative to fossil fuels in addressing Bangladesh's
energy challenges.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Suman Chowdhury
Department of Electrical and Electronic Engineering
International University of Business Agriculture and Technology
Dhaka-1230, Bangladesh
Email: [email protected]

1. INTRODUCTION
Although Bangladesh is an agriculture-based country but in recent years it has huge investment in
small and medium level industry. For growing industrialization and urbanization, electricity demand is
increasing very fast. The government has introduced some short-term leasing programs that mostly rely on
diesel and furnace oil. Since most of the power station is using natural gas, so certainly there is a shortage of
gas supply which affects the electricity production seriously. But this initiative is very costly and the
government has to give huge subsidies. Aside from that, Kaptai has a small hydroelectric power plant with a
230 MW capacity. Moreover, it has 232 rivers whose flow rate is suitable for hydro-electric power generation
in some extent [1]. In the current situation, Bangladesh needs to switch to renewable energy for a power
solution. Wind is one of the great sources that can be used to yield renewable energy. Bangladesh is located
between 20.34- and 26.38-degrees north latitude and 88.01- and 92.41-degrees east latitude. It has a coastline
of almost 724 kilometers [2]. It has already been discovered that modest wind turbines can be installed in
coastal areas. Both cost analysis and technological benefits are needed for the investment in this sector.
Muhuri Dam, Feni, of 0.99 MW, and Maheshkhali of 2 MW wind power plants are established here. During

Journal homepage: http://ijape.iaescore.com

Int J Appl Power Eng ISSN: 2252-8792  433

the irrigation period, wind energy can be utilized for irrigation, that will be helpful for reducing energy crisis,
especially in rural areas. However, this method considered the expenses that were higher than the actual
expenditures. Wind power is the second most affordable source of electricity in Bangladesh, with a cost
estimate of BDT 6 per kWh, coming after natural gas, which costs BDT 3 per kWh [3]. Bangladesh has a
wind energy potential of around 20,000 MW, with a wind speed of less than 7 meters per second. Wind
energy research in Bangladesh is started some years back, and it has already demonstrated that certain of
Bangladesh's southern areas have a lot of potential for wind energy [4], [5]. Wind power energy can reduce
the dependence on fossil fuel [6]. Wind energy can play a vital role in abating the energy crisis [7]. Wind is
an excellent and cost-effective source of renewable energy. Bangladesh, with its extensive coastline,
experiences consistent wind year-round. This makes it an ideal location for harnessing wind energy, as it
benefits from various wind patterns throughout the year [8]. The analysis presented in this paper indicates
that a mix of renewable energy, coal, and uranium is the most effective option for large-capacity power
plants in Bangladesh to meet the country's electricity demand [9]. The thrust increases as the wind velocity
increases, but decreases as the pitch angle increases. There is an ideal pitch angle for a given wind velocity at
which the turbine generates the most power. The stall characteristics of the airfoil blade have been linked to
the effect of pitch angle on the power produced [10].
In recent years, the energy demand of Bangladesh has increased significantly for its expanding
economic development and population size [11]. From March to September, this wind blows at a speed of 3
to 6 m/s over the surface of Bangladesh. Wind speed is often lower from October to February. In June-July,
the maximum wind speed is reached. Putting up wind turbines along the coast could be a better way to help
the national grid. Aside from these locations, Bangladesh has many mountainous zones and remote islands
where wind flows at a constant speed of 2 to 5 m/s throughout the year [12]. Bangladesh can get 650 MW of
energy from a coastal area through wind power [13]. For a long coastal area, it produces a significant amount
of electricity for agricultural production [14]. Based on the wind power density (WPD) and the mapped rotor
diameter of turbines for different wind power classes, it has been determined that large-scale wind turbines
are viable in Chittagong and Jessore, medium-scale turbines in Khepupara, and small-scale turbines in Cox's
Bazar and Hatiya [15]. In the present day, to measure the potentiality of wind power neuro-fuzzy logic
system is used since this system has a good accuracy for prediction [16]. Shao et al. [17] stated in their
research presented a new wind turbine control strategy that involves using a PID controller and particle
swarm optimization to control the pitch angle, which must be regulated to capture the maximum amount of
power. Due to its advanced capabilities compared to other deep learning and statistical models, the gated
recurrent unit (GRU) model is well-suited for predicting wind turbine output power [18].
The results produced by the fuzzy-based technique are very similar to the calculated values when
compared to those obtained using the model predictive-based technique [19]. The adaptive fuzzy logic
controller (AFLC) method is widely favored due to its rapid response and superior performance compared to
traditional fuzzy logic controller (FLC) and perturb and observe (P&O) strategies [20]. Wind power site
selection is also an important factor in getting optimum power from the wind turbine. Wind power can
contribute a good role in the power generation process in Bangladesh. Now a hybrid wind solar power system is
becoming a popular scheme throughout the world. Subsequently, the hybrid power is a very lucrative power
model that is very suitable in the coastal areas of Bangladesh [21]-[25].
Wind energy optimization is very challenging in the present world. So, power generation by wind
should be analyzed in a deep manner of concern. From this aspect, this research study has been carried out. This
paper has initiated the experiment set up for the wind power system in a small scale to observe the power
performance. To investigate the forecasting of wind power, a series of data has been obtained from the practical
set up. In addition, for forecasting the wind power, a fuzzy logic algorithm has been implemented in MATLAB
Simulink environment. Finally, a brief data analysis has been presented in this paper showing the accuracy of
forecasting through graphical analysis.

2. METHODOLOGY
A modified fan is connected to a DC motor, and established the connection to the load using a
multimeter. Data has been measured using an anemometer while connected to a wind source. Data has been
input into MATLAB and employed a neuro-fuzzy logic system during simulation. Finally, outcomes have
been evaluated and put into practice. A voltage controller, shown in Figure 1 is a device or system used to
regulate and control the voltage levels in an electrical circuit. It is designed to maintain a stable and desired
voltage output despite fluctuations in the input voltage.
Data has been taken from a multimeter every time as generated in DC output voltage, output current,
and air speed by anemometer as input, and calculated power output. The ANFIS model is given as Figure 2.
An adaptive neuro-fuzzy inference system (ANFIS) shown in Figure 2, is a computational model that
combines the strengths of artificial neural networks and fuzzy logic to perform various purposes, including
Prediction of wind power with various air speed using neuro-fuzzy logic … (Naimur Rahman Tushar)
434  ISSN: 2252-8792

pattern recognition, prediction, and system control. ANFIS employs a fuzzy inference system that adapts and
learns from data, allowing it to model complex relationships between inputs and outputs.
A membership function input diagram shown in Figure 3 is a graphical representation used in fuzzy
logic systems to illustrate how numerical input values are translated into linguistic terms or fuzzy sets. It
displays the input variables on the horizontal axis, showcasing the entire range of possible values for a given
parameter. These values are then associated with various linguistic terms or fuzzy sets. Each linguistic set is
represented by a membership function, typically depicted as curves or shapes. A membership function output
diagram is a visual tool in fuzzy logic systems that illustrates how fuzzy output values, represented as
linguistic terms or fuzzy sets, are converted into crisp or numerical values. Output variables are displayed on
a horizontal axis, with each linguistic term linked to a specific membership function. This diagram aids in
understanding the transformation of fuzzy results into precise numerical values, making it essential
for decision-making and control systems in various applications. We get the input and output structure from
our model.

Figure 1. Voltage controller with LED

Figure 2. Proposed model

Figure 3. MF diagram (input)

Int J Appl Power Eng, Vol. 14, No. 2, June 2025: 432-440
Int J Appl Power Eng ISSN: 2252-8792  435

A structural diagram of an adaptive neuro-fuzzy inference system (ANFIS) shown in Figure 4

outlines the key components of this hybrid computational model. It typically includes an input layer for
numerical data, a fuzzification layer to convert inputs into fuzzy values, a rule layer that computes rule firing
strengths, a consequent layer to determine output values, a normalization layer to adjust outputs, and an
output layer for the final numerical result. ANFIS can vary in complexity depending on the problem, and its
structural diagram illustrates how it combines neural networks and fuzzy logic to make decisions based on
both quantitative and qualitative data.
Some data from our data are used as testing data and the rest data as training data. Figure 5
represents the training data error. It is noticed that some errors in the testing data which in about 0 to 6%
which is shown in Figure 6. To find out the error, the training and testing data are added first. Then training
data and finally testing the data. It is seen in the diagram below. Where the blue dots are the measured
average power data and the red dots are our true average power of our testing data. After using neuro fuzzy
logic system on training and testing data, the following diagram is obtained.

Figure 4. Structural diagram

Figure 5. Training data error

Figure 6. Testing data error

Prediction of wind power with various air speed using neuro-fuzzy logic … (Naimur Rahman Tushar)
436  ISSN: 2252-8792

A rule layer in an ANFIS model shown in Figure 7 is a crucial component responsible for
generating fuzzy rules and their corresponding membership grades. It takes the input data and processes it
through a set of fuzzy if-then rules, each with its associated membership functions, and provides an output.
These rules help in capturing the underlying relationships of the input variables and the output.
A "surface view" in the context of ANFIS typically refers to a graphical representation or
visualization of the ANFIS model's output as it relates to two input variables. A surface view is created by
plotting the model's output as a three-dimensional surface. The two input variables are typically plotted on
the x and y axes, and the ANFIS output (or the model's predictions) is represented as the z-axis or the height
of the surface as shown in Figure 8.
Statistical analysis conducted to establish the relationship between wind speed and power output,
and calibrate a predictive model in MATLAB for real-time power forecasts. This model is continuously
monitored and adjusted for accuracy, aiding in the optimization of the operation. Regular updates and
maintenance ensure the model remains effective, contributing to efficient wind energy generation and reliable
electricity production. The current and voltage by multimeter and air speed by anemometer is noted.
Figure 9 shows the experimental set up for taking the practical data for analysis through fuzzy logic
model created in MATLAB. Training data and testing sets are split to assess the model's accuracy. Fine-tune
the model parameters for optimal performance. Finally, when predicting wind power for future periods,
obtain real-time wind speed data and feed it into the trained model to estimate the power output. Regularly
update and retrain the model to account for changing conditions and improve prediction accuracy over time.
Anemometer has been used to observe the wind speed. This wind speed has been varied gradually
and respective power generation by the motor has been recorded. In this way, a data set has been obtained
from the practical set up. This data set has been incorporated in the MATLAB Simulink model to predict the
power for various wind speed. Fuzzy logic controller has been utilized in the data prediction strategy.
Furthermore, the fuzzy rules have been created by artificial intelligence network profile. Finally, the
comparison of predicted and test data has been presented at the end of this paper.

Figure 7. Diagram of average measured power in MATLAB

Figure 8. Average measured power (surface view)

Int J Appl Power Eng, Vol. 14, No. 2, June 2025: 432-440
Int J Appl Power Eng ISSN: 2252-8792  437

Figure 9. Practical setup

3. RESULTS AND DISCUSSION

Firstly, the power source is connected with the motor. Then it is connected with the load and an
ammeter in series and a voltmeter in parallel with the motor and load. Then we took the data by placing
various air speeds. As the wind speed changes, different values are obtained each time. Experimental data
shows the values of current, voltage, and power of various wind or air speed found at the experiment. The
maximum power is 780.84 mW if the speed is 8.7 m/s. Here, the minimum power we got 4.5 mW when the
speed is 2.3 m/s. We have taken a total 179 data out of 200 sample data as training data in ANFIS. Average
true power is calculated using neuro fuzzy logic system. Then the following formula has been used to find
the error of testing and some training data.

Error = [(Average True Power-Average Measured Power)/Average True Power]*100%

Table 1 shows the percentage error of all the testing data from lowest to highest. Error is minimum
0.09% for air speed 7.77 m/s and maximum 6.50% when speed is 3.15 m/s. We calculate error comparing
two output power by ANFIS in MATLAB neuro-fuzzy logic system. These data are used as testing data (21)
to the rest (179) training data. The practical data and ANFIS Simulink are almost same and percentage of
error is negligible as shown in Figure 10. This figure shows that the prediction performance has been
successfully carried out by the ANFIS predicting model.

Table 1. Testing data with percentage error (%)

SL No Input (air speed) Output (true power) Output (measured power in mW) Percentage error (%)
in (m/s) practical in mW by ANFIS Simulink by calculating output
1 3.15 16.15 17.2 6.50
2 3.18 17.4 18.5 6.32
3 3.19 18.9 20 5.82
4 3.19 19.32 20 3.51
5 3.22 20.46 21.4 4.64
6 3.85 60.4 60.2 0.33
7 3.87 62.73 61.6 1.80
8 3.91 63.14 64.5 2.15
9 3.93 65.52 66 0.73
10 5.02 180 174 3.33
11 5.04 183.96 177 3.78
12 5.06 186.944 180 3.71
13 5.08 190.18 183 3.77
14 5.11 193.214 187 3.21
15 7.66 515 505 1.94
16 7.69 520.38 510 1.99
17 7.77 524.51 524 0.09
18 7.8 531.2 529 0.41
19 7.85 535.04 539 0.74
20 7.88 541.8 545 0.59
21 7.9 545.67 548 0.43

Prediction of wind power with various air speed using neuro-fuzzy logic … (Naimur Rahman Tushar)
438  ISSN: 2252-8792

Figure 10. Testing data graph

4. CONCLUSION
The research entails the development of a MATLAB-based adaptive neuro-fuzzy inference system
(ANFIS) model for predicting wind power output under varying air speeds. This process involves two main
phases: training and testing. During the training phase, practical data is utilized to establish the intricate
relationship between air speeds and wind power generation. The ANFIS model is trained and tested using
data from the provided table to evaluate its performance. The analysis reveals a percentage error ranging
from 0.09% to 6.5% during testing, indicating a reasonably accurate prediction capability. Notably, the
testing phase demonstrates an inverse relationship between air speed and prediction error, with error
decreasing as air speed increases. The close alignment between the measured power by MATLAB and
practical values during the training phase allows the model to adapt its parameters effectively, enhancing
prediction accuracy. The testing phase serves to assess the model's generalization ability by evaluating its
performance on unseen scenarios. Experimental results indicate the generation of approximately 1 watt DC
output, with the ANFIS model successfully predicting wind power for various air speeds. For instance, the
maximum power output of 780.84 mW is observed at an air speed of 8.7 m/s, while the minimum power
output of 4.5 mW occurs at an air speed of 2.3 m/s. These findings highlight the effectiveness of the ANFIS
model in accurately predicting wind power output across different environmental conditions.

ACKNOWLEDGEMENTS
We are thankful to the Department of Electrical and Electronic Engineering for supporting us to do
our research project.

FUNDING INFORMATION
We don’t have any fund for this research.

AUTHOR CONTRIBUTIONS STATEMENT

This journal uses the Contributor Roles Taxonomy (CRediT) to recognize individual author
contributions, reduce authorship disputes, and facilitate collaboration.

Name of Author C M So Va Fo I R D O E Vi Su P Fu
Naimur Rahman Tushar ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
Md. Tanvir Ahmed ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
Shuvo
Dilip Kumar Das ✓ ✓ ✓ ✓ ✓
Suman Chowdhury ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

C : Conceptualization I : Investigation Vi : Visualization

M : Methodology R : Resources Su : Supervision
So : Software D : Data Curation P : Project administration
Va : Validation O : Writing - Original Draft Fu : Funding acquisition
Fo : Formal analysis E : Writing - Review & Editing

Int J Appl Power Eng, Vol. 14, No. 2, June 2025: 432-440
Int J Appl Power Eng ISSN: 2252-8792  439

CONFLICT OF INTEREST STATEMENT

We authors are declaring that there is no conflict of interest.

DATA AVAILABILITY
The data that support the findings of this study are available on request from the corresponding
author, [SC]. The data, which contain information that could compromise the privacy of research
participants, are not publicly available due to certain restrictions.

REFERENCES
[1] M. I. Miskat et al., “An overview of the hydropower production potential in Bangladesh to meet the energy requirements,”
Environmental Engineering Research, vol. 26, no. 6, pp. 1–13, Nov. 2021, doi: 10.4491/eer.2020.514.
[2] A. M. I. Mukut, M. Q. Islam, and M. M. Alam, “Analysis of wind characteristics in coastal areas of Bangladesh,” Journal of
Mechanical Engineering, vol. 39, no. 1, pp. 45–49, Jan. 2008, [Online]. Available:
https://www.banglajol.info/index.php/JME/article/view/1833.
[3] M. T. Babu, H. Nei, and M. A. Kowser, “Prospects and necessity of wind energy in Bangladesh for the forthcoming future,” Journal
of The Institution of Engineers (India): Series C, vol. 103, no. 4, pp. 913–929, Aug. 2022, doi: 10.1007/s40032-022-00834-8.
[4] N. A. Madlool et al., “Investigation on wind energy for grid connection in Bangladesh: case study,” IOP Conference Series:
Materials Science and Engineering, vol. 1127, no. 1, p. 012021, Mar. 2021, doi: 10.1088/1757-899X/1127/1/012021.
[5] T. Liu, Z. Huang, L. Tian, Y. Zhu, H. Wang, and S. Feng, “Enhancing wind turbine power forecast via convolutional neural
network,” Electronics, vol. 10, no. 3, p. 261, Jan. 2021, doi: 10.3390/electronics10030261.
[6] I. Akhtar, S. Kirmani, M. Ahmad, and S. Ahmad, “Average monthly wind power forecasting using fuzzy approach,” IEEE
Access, vol. 9, pp. 30426–30440, 2021, doi: 10.1109/ACCESS.2021.3056562.
[7] S. Chowdhury, A. K. Saha, and D. K. Das, “Wind energy prediction on future aspect using XGBoost time series model,” 2024 8th
International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2024, pp. 7–10, doi:
10.1109/ICECA63461.2024.10801065.
[8] A. N. M. Noman, “Wind energy prospects and the future of Bangladesh power sector,” in 2023 8th International Engineering
Conference on Renewable Energy & Sustainability (ieCRES), May 2023, pp. 1–4, doi: 10.1109/ieCRES57315.2023.10209532.
[9] A. Nath, S. Barua, and N. Mohammad, “Electric power generation-mix for Bangladesh and its future,” in 2019 International
Conference on Electrical, Computer and Communication Engineering (ECCE), 2019, pp. 1–4, doi: 10.1109/ECACE.2019.8679245.
[10] J.-Y. Ryu et al., “Evaluation of weather information for short-term wind power forecasting with various types of models,”
Energies, vol. 15, no. 24, p. 9403, Dec. 2022, doi: 10.3390/en15249403.
[11] M. Hasan et al., “A critical analysis of wind energy generation potential in different regions of Bangladesh,” Energy Reports, vol.
11, pp. 2152–2173, Jun. 2024, doi: 10.1016/j.egyr.2024.01.061.
[12] R. Abdullah and M. Islam, “Prospects of wind energy in the coastal region of Bangladesh,” International Journal of Engineering
Research & Technology (IJERT), vol. 2, no. 11, pp. 3018–3022, 2013.
[13] M. Mohandes, S. Rehman, and S. M. Rahman, “Estimation of wind speed profile using adaptive neuro-fuzzy inference system
(ANFIS),” Applied Energy, vol. 88, no. 11, pp. 4024–4032, Nov. 2011, doi: 10.1016/j.apenergy.2011.04.015.
[14] M. A. Shaikh, K. M. A. Chowdhury, S. Sen, and M. M. Islam, “Potentiality of wind power generation along the Bangladesh
coast,” in AIP Conference Proceedings, 2017, p. 020035. doi: 10.1063/1.5018553.
[15] M. S. Islam, A. Islam, and M. Z. Islam, “Wind power generation scale mapping of Bangladesh at different turbine heights,” 2014
3rd International Conference on the Developments in Renewable Energy Technology (ICDRET), 2014, pp. 1–6, doi:
10.1109/ICDRET.2014.6861735.
[16] A. E. Saleh, M. S. Moustafa, K. M. Abo-Al-Ez, and A. A. Abdullah, “A hybrid neuro-fuzzy power prediction system for wind
energy generation,” International Journal of Electrical Power & Energy Systems, vol. 74, pp. 384–395, Jan. 2016, doi:
10.1016/j.ijepes.2015.07.039.
[17] Y. Shao, J. Liu, J. Huang, L. Hu, L. Guo, and Y. Fang, “The implementation of fuzzy PSO-PID adaptive controller in pitch
regulation for wind turbines suppressing multi-factor disturbances,” Frontiers in Energy Research, vol. 9, p. 828281, Mar. 2022,
doi: 10.3389/fenrg.2021.828281.
[18] J. Jamii, M. Mansouri, and M. F. Mimouni, “Short time forecasting for wind power generation using artificial neural network,” in
2022 19th International Multi-Conference on Systems, Signals & Devices (SSD), May 2022, pp. 321–325, doi:
10.1109/SSD54932.2022.9955856.
[19] O. Lodin, N. Khajuria, S. Vishwakarma, and G. Manzoor, “Modeling and simulation of wind solar hybrid system using
MATLAB/Simulink,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 9S, pp.
218–224, 2019.
[20] D. Rekioua, S. Bensmail, C. Serir, and T. Rekioua, “Power supervision of an autonomous photovoltaic/wind turbine/battery
system with MPPT using adaptative fuzzy logic controller,” International Journal of Applied Power Engineering, vol. 12, no. 1,
pp. 90–101, Mar. 2023, doi: 10.11591/ijape.v12.i1.pp90-101.
[21] M. S. Islam, S. Rahman, and S. Chowdhury, “Investigation of hybrid power performance with solar module & wind turbine in
MATLAB,” in 2023 International Conference on Computer, Electrical & Communication Engineering (ICCECE), Jan. 2023, pp.
1–4, doi: 10.1109/ICCECE51049.2023.10085455.
[22] F. Blaabjerg and K. Ma, “Wind energy systems,” Proceedings of the IEEE, vol. 105, no. 11, pp. 2116–2131, Nov. 2017, doi:
10.1109/JPROC.2017.2695485.
[23] F. H. Khan, T. Pal, B. Kundu, and R. Roy, “Wind energy: a practical power analysis approach,” in 2021 Innovations in Energy
Management and Renewable Resources (52042), Feb. 2021, pp. 1–6, doi: 10.1109/IEMRE52042.2021.9386754.
[24] S. Das, D. Mazumder, N. Mia, and S. Rahman, “A review on power generation from wind power created by fast moving train
perspective Bangladesh,” in 2020 IEEE International Conference on Technology, Engineering, Management for Societal impact
using Marketing, Entrepreneurship and Talent (TEMSMET), Dec. 2020, pp. 1–5, doi: 10.1109/TEMSMET51618.2020.9557448.
[25] M. Hasan, P. Dey, I. J. Khan, and N.-U.-R. Chowdhury, “Assessment of promising wind energy production sites in Bangladesh
using energy pattern factor method,” in 2022 International Conference on Energy and Power Engineering (ICEPE), Nov. 2022,
pp. 1–4, doi: 10.1109/ICEPE56629.2022.10044895.

Prediction of wind power with various air speed using neuro-fuzzy logic … (Naimur Rahman Tushar)
440  ISSN: 2252-8792

BIOGRAPHIES OF AUTHORS

Naimur Rahman Tushar has done his B.Sc. in Electrical and Electronic
Engineering from International University of Business Agriculture and Technology (IUBAT),
Uttara, Dhaka, Bangladesh (www.iubat.edu). He has successfully completed his B.Sc. thesis
under the supervision of Mr. Suman Chowdhury- assistant professor. He can be contacted at
email: [email protected].

Md. Tanvir Ahmed Shuvo has done his B.Sc. in Electrical and Electronic
Engineering from International University of Business Agriculture and Technology (IUBAT),
Uttara, Dhaka, Bangladesh (www.iubat.edu). He has successfully completed his B.Sc. thesis
under the supervision of Mr. Suman Chowdhury- assistant professor. He can be contacted at
email: [email protected].

Dilip Kumar Das has joined in IUBAT-International University of Business and

Agriculture in September 2007 as a faculty member in the Mathematics Department. Before
that, he was serving in The University of Cumilla as a lecturer. He obtained his B.Sc. (Hon’s)
in Mathematics and M.Sc. (Applied Mathematics) from Dhaka University. He obtained an
M.Phil. degree from Bangladesh University of Engineering and Technology (BUET). His
research interests are renewable energy, mathematical modeling, machine learning, and
statistical analysis. He can be contacted at email: [email protected].

Suman Chowdhury is an assistant professor in the Department of Electrical and

Electronic Engineering, IUBAT-International University of Business Agriculture and
Technology, Uttara, Dhaka, Bangladesh (www.iubat.edu). He was born in Chittagong. Suman
Chowdhury completed his SSC in the year of 2005 from Chittagong Municipal Model High
School and HSC in 2007 from Chittagong Govt. City College, and then he pursued his
Bachelor of Science in Electrical and Electronic Engineering from Khulna University of
Engineering and Technology (KUET) in 2012. He achieved Merit/Technical Scholarship in
several times from KUET and others educational institution. He also completed Master of
Science (M.Sc.) in Electrical and Electronic Engineering from Dhaka University of
Engineering and Technology (DUET) in 2020. He has supervised a good number of students
in practicum and thesis. He has published over 20 research papers in international conferences
and journals. His research areas include building integrated photovoltaic, renewable energy,
biomedical engineering, digital signal processing, and image processing. He can be contacted
at email: [email protected].

Int J Appl Power Eng, Vol. 14, No. 2, June 2025: 432-440