International Journal of Power Electronics and Drive Systems (IJPEDS)

Vol. 15, No. 3, September 2024, pp. 1959~1967

ISSN: 2088-8694, DOI: 10.11591/ijpeds.v15.i3.pp1959-1967  1959

Enhancing of a wind power system control using intelligent

artificial control and multilayer inverter

Abdelmoumen Chandad1, Messaoud Hamouda2, Nedjadi Benharir1, Mohammed Bouzidi3,4

1
Department of Electrical Engineering, LAAS Laboratory, ENPO-MA, Oran, Algeria
2
Department of Energy Technology, DDI Laboratory, Ahmed Draia University, Adrar, Algeria
3
Department of Sciences and Technology, Faculty of Sciences and Technology, University of Tamanghasset, Algeria
4
Energy and Materials Laboratory, University of Tamanghasset, Tamanghasset, Algeria

Article Info ABSTRACT

Article history: The improvement of overall power quality and optimal control of reactive and
active power are issues that have attracted many researchers. The harmonic is
Received Jul 16, 2023 considered a main stressful source for energy quality. This paper proposed the
Revised Jan 3, 2024 ability of artificial intelligence at controlling the active and reactive power and
Accepted Jan 13, 2024 to reduce torque ripple and current harmonics thus improve energy quality and
the stability of system, that by using the artificial intelligence controller and a
neural network based space vector modulation with two levels inverter
Keywords: (NSVM-2L). These inverter hold the offer improved efficiency and have on
account of their capability of high voltage operation compared with traditional
Friendly output current inverters as reducing the harmonic. These results showed that the fuzzy logic
Intelligent artificial controller's dynamic performance is very superior to that of the PID controller
Multilayer inverter of DFIG. The fuzzy controller works well for helping us to minimize the rate
Optimal control of harmonic distortion of absorbed currents and for correctly adjusting active
The stability of system and reactive power and its stability of wind turbine compared to PID
controller.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Abdelmoumen Chandad
Department of Electrical Engineering, LASS Laboratory, ENPO-MA
Timokten-Aoulef-Adrar, Timokten 01043, Algeria
Email: [email protected]

1. INTRODUCTION
In numerous regions around the world, variable renewable energy generated by sources such as wind
and solar is expected to play a pivotal role in future zero-emissions electricity systems [1]. Lately, renewable
energy sources have garnered increased attention as potential alternatives for meeting domestic energy
demands [2], [3]. Due to its natural purity and abundant availability, wind power stands out as one of the most
remarkable forms of renewable energy [4]. Currently, the most commonly employed wind turbine technology
is the double-fed induction generator (DFIG) [5]. The fastest-growing renewable energy source is wind power,
which has become economically viable and technologically advanced [6]. Large-scale wind production systems
rely on double fed induction machines (DFIM) for their flexibility in reactive and active power management,
as well as torque control. These machines are a vital component of variable-speed wind turbines [7]. This is a
popular and dynamic research area, with a significant focus on controlling nonlinear systems [8]. Consequently,
modern control systems are better equipped to address these challenges, offering robustness and reduced
sensitivity, such as the artificial intelligence controller.
Modern megawatt-sized wind turbines consistently operate at variable speeds, a feat achieved through
the use of converters [4]. These converters have a substantial impact on the cost of wind turbines and are often
associated with individual generators [4]. The growing capacity and installation of wind farms necessitate the

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

1960  ISSN: 2088-8694

study and development of control mechanisms for the reactive and active power capabilities of wind farms.
Wind power plants are now required to actively participate in the power supply system [9]. The primary
objectives of these control capabilities are to automate wind turbine operation, impose safety limits, and
maximize power generation [9]. Maximizing wind energy collection through power optimization helps reduce
operating costs, minimize turbine loads for safe operation, and ensures consistent dynamic responses and
enhanced product quality. Wind turbines, whether operating at constant or variable speeds, aim to capture as
much wind energy as possible [9].
In this paper, we employ an artificial intelligence controller to optimize the reactive and active powers
of the DFIG wind turbine. We replace the traditional pulse-width modulation (PWM) technique with a neural
network-based space vector modulation with two levels (NSVM-2L) to reduce torque and flux ripples.
Additionally, we utilize fuzzy logic controllers and PID controllers to control the reactive and active power on
the stator-side. This approach significantly enhances power quality and offers outstanding performance even
when DFIG parameter values change.

2. METHOD
The study is limited to proposing two strategies aimed at optimizing the active and reactive power of
a wind turbine equipped with a doubly fed induction generator (DFIG). These strategies involve the use of a
fuzzy logic controller and a PID controller. Key components of the methodology include the adoption of a
neural network-based space vector modulation with two levels (NSVM-2L) in place of the traditional pulse-
width modulation (PWM). This substitution serves to mitigate torque and flux variations within the DFIG.
Additionally, the methodology employs both fuzzy logic and PID controllers to manage the regulation of
reactive and active power on the stator side of the DFIG.
The performance of these control strategies is assessed through simulations conducted in
MATLAB/Simulink. The results of these simulations reveal that the fuzzy logic controller yields a faster
dynamic response and lower harmonic distortion when compared to the PID controller. To test the robustness
of these control strategies, variations in DFIG parameters are introduced to assess how the controllers perform
under changing operational conditions. In this regard, the fuzzy logic controller exhibits superior robustness,
making it a favorable choice in scenarios with dynamic and variable operating conditions.

2.1. Modelling the chain of wind based on DFIM

Wind turbine modelling, the rotor power coefficient (Cp) is used to express the extractable power to
available power ratio. Therefore, the extractable power may be expressed as [3], [10], [11].

Paer = CP . Pwind
{ (1)
Paer = 0.5CP (λ). ρ. π. R2 . V13

The tip speed ratio 𝜆 may be calculated using [12].

𝛺𝑡𝑢𝑟𝑏𝑖𝑛𝑒
𝜆= .𝑅 (2)
𝑉1

Where: Ωturbine is represent turbine angular shaft speed, R is turbine radius in m, and V1 is the wind speed
in m/s.
Cp(λ, β) for rapid rotation wind turbines presented in (3), is based on experimental data [13].

K2 −K5
CP = K 1 ( − K 3 . β − K 4 ) exp ( ) + K6 . λ (3)
λ1 λ1

With,
1 0.035 1
=− + (4)
λ1 β3 +1 λ+0.08β

or: K1 = 5176 ∗ 10−4 , K 2 = 116 K 3 = 4 ∗ 10−1 K 4 = 0.5 ∗ 101 ; K 5 = 0.21 ∗ 10−2 , K 6 = 68 ∗ 10−4 .
The aerodynamic torque exerted on the slow shaft of the turbine (in N. m) is given by [14], [15]:
1 1
Taer = CP (λ). ρ. π. R2 . V13 . (5)
2 Ωturbine

Int J Pow Elec & Dri Syst, Vol. 15, No. 3, September 2024: 1959-1967
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1961

The following mathematical wind relation is used to represent the gear box, which modifies the
turbine's speed in proportion to the generator's speed. Through a mechanical shaft system made up
of a high-speed and low-speed shaft coupled by a gearbox, the induction generator is connected to the wind
turbine [3], [16]:

Taer
Tg =
G
{ Ωmec (6)
Ωturbine =
G

The total mechanical torque Tmec applied to the rotor [3], [15]:

dΩmec
Tmec = J (7)
dt

Tmec = Tg − Tem − Tvis (8)

J
where J = turbine + Jg : Total inertia appear on the shaft of the generator, Cem: Torque electromagnetic
G2
produced by DFIG-generator, Tvis: Torque of viscous friction, Tg :Torque from the Gear box, Ωmec :
Mechanical angular speed of the generator. G: gearbox ratio.
The resistance torque due to friction is modelled by a viscous friction coefficient f.

Tvis = f Ωmec (9)

f turbine
f = +fg (10)
G2

Where: f is the equivalent friction coefficient of the tree, f turbine is the coefficient of friction of the turbine,
and f g is the coefficient of the generator.

2.2. Modelling of DFIM

The equations of the DFIM vector control (d-q) with wound rotor are written as [17].

Φds = Φs
{Φ =0 (11)
qs

Lm 2 Lm
Φdr = (Lr − ). idr + Φs
LS LS
{ 2 (12)
Lm
Φqr = (Lr − ). iqr
LS

Φs Lm
ids = − . idr
Ls Ls
{ Lm (13)
iqs = − . iqr
LS

Vqs = ωs Φs = Vs
2
Lm didr Lm 2
Vdr = (Lr − ) − gωs (Lr − )iqr +R r . idr (14)
LS dt LS
Lm Lm 2 diqr Lm 2
Vqr = g Vs +(Lr − ) + gωs (Lr − ). idr + R r . iqr
{ LS LS dt LS

Lm
Ps = −Vs i
LS qr
Lm V 2
Φs = −Vs i + s
LS dr ωs LS
L (15)
Pr = g(−Vs m iqr )
L S
Lm Vs 2
{Φr = g(−Vs LS
idr +
ωs LS
)

Torque electromagnetic equation in a generator is written in (16).

Enhancing of a wind power system control using intelligent artificial control … (Abdelmoumen Chandad)
1962  ISSN: 2088-8694

Msr
Tem = p. (−Φs . iqr ) (16)
Ls

3
With Msr = 𝐿𝑚.
2

2.3. Space vector modulation (SVM)

The fundamental idea behind the SVM method is to create Vref as precisely as feasible using the
stationary vectors that are accessible to the inverter. Reference voltage Vr is generated by the inverter. The
nearest three vectors (NTVs) for Vref are formed by the vertices of this triangle, and Vref is then synthesized
using these three vectors, and repeating this process at each sample time (Ts). The SVM can best be explained
based on a two-phase representation of Figure 1 [18], [19].

Figure 1. Principle drawing SVM for a three-phase two level-VSI

2.4. Level inverter

Multilayer inverters address standard VSI drawbacks with advantages like reduced harmonics, lower
stress on power devices, decreased ratings, and a lower switching frequency [3], [20]-[22]. Using a two-level
SVM method that calculates the maximum and minimum three-phase voltages (Va, Vb, Vc) detailed in
Figure 2. Also, Figure 3 displays the NSVM technique for a 2-level inverter.

2.5. Fuzzy logic control scheme

Fuzzy logic controllers consist of three primary components: fuzzification, defuzzification, and
inference rules. In the fuzzification phase, numerical values are transformed into fuzzy values or linguistic
variables, which serve as inputs [23]. The defuzzification stage then converts these fuzzy values back into
numeric outputs [23], [24]. Inference rules utilize linguistic control rules and a rule base to represent the desired
control strategy and objective. In the case of this fuzzy logic controller, it uses error deviations and input errors
from their references over each time interval as inputs, employing a Mamdani-type fuzzy logic control system
[23], [25]. The controller interfaces with a neural network support vector machine (NSVM) system, with the
fuzzy logic controller providing inputs to the NSVM. The diagrams of Figure 4 and Figure 5 illustrate how the
FLC-NSVM and PID-NSVM systems are interconnected.

Figure 2. Schematic diagram of a two-level, three phases conventional voltage source inverter

Int J Pow Elec & Dri Syst, Vol. 15, No. 3, September 2024: 1959-1967
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1963

(a)

(b)

Figure 3. The NSVM technique by 2-level inverter (a) SVM strategy and (b) neural network layer

Figure 4. Diagram of fuzzy logic-NSVM controller for DFIG

Figure 5. Diagram of PID-NSVM controller for DFIG

2 RESULTS AND DISCUSSION

In practice, it's necessary to conduct a simulation of the wind power conversion process to
validate our theoretical research. The stator winding of the DFIG is directly connected to a 3-phase network
(398/690 V/50 Hz), and the rotor winding is driven by a 3-phase converter controlled through neural network-
based space vector modulation (NSVM). The parameters of the DFIG wind turbine are presented in Table 1.
Generally speaking, generators follow power control guidelines for active and reactive power. Fuzzy
logic controllers react faster than PID controllers. It minimizes the overshoot of the active power, but the PID
controller outperforms it in terms of reactive power (see Figure 6). Different control methods show differences
in static error and response time. The stator power tracking is satisfactory for both control types and the
response to disturbances is acceptable. Figure 7 shows the electromagnetic torque of the PID and fuzzy logic
controller, and Figure 8 shows the three-phase stator current. Compared with PID control (see Figure 8(a)),
fuzzy logic control (see Figure 8(b)) effectively reduces stator current and electromagnetic torque fluctuations.
The frequency spectrum of source current harmonics' Total harmonic distortion (THD) levels is presented.
Figure 9 display the frequency spectra for THD analysis in DFIG, with field-oriented control (FLC) and
proportional-integral-derivative (PID) control methods, respectively. Table 2 provides a comparison of THD
values in source current harmonics between DFIG systems controlled by FLC and PID. The results indicate
that the THD rate is lower in the case of FLC compared to PID.

Enhancing of a wind power system control using intelligent artificial control … (Abdelmoumen Chandad)
1964  ISSN: 2088-8694

Table 1. DFIG wind turbine parameters

Symbol Value Description Symbol Value Description
P 4 Number of poles Rs 0.012 (Ω) Stator winding resistance
J 1000 (kg.m2) Total inertia Ls 0.0137 (H) Stator inductance
fr 0.0024 (Htz) Equivalent friction coefficient of the tree Lr 0.0136 (H) Rotor inductance
R 35.255 (m) The turbine radius M 0.0135 (H) Mutual inductance
Rr 0.021 (Ω) Rotor winding Resistance g 0.03 Glissement

Table 2. The THD (%) of stator current Table 3. The THD (%) of stator current (robustness test)
FLC-controller PID-controller FLC-controller PID-controller
0.42 0.98 0.49 2.32

Figure 6. The reactions of the power of the DFIG with fuzzy controller and PID controller

Figure 7. The electromagnetic torque of the PID and fuzzy logic controller

(a) (b)

Figure 8. The three-phase stator current by PID and fuzzy logic controller (a) PID controller and
(b) fuzzy controller

Int J Pow Elec & Dri Syst, Vol. 15, No. 3, September 2024: 1959-1967
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1965

Figure 9. THD of stator current (FlC) and (PID) controller

In the context of durability testing, a robustness test was conducted by doubling the resistance
values Rr and Rs, while halving the inductances Ls, Lr, and Lm. The results of this simulation are depicted in
Figures 10, 11, and 12. These figures illustrate the impact of these modifications on the reactive power curve,
active power curve, and electromagnetic torque curve, with PID control showing a more significant influence
compared to fuzzy control (Figures 10 and 11). The results also reveal a substantial reduction in the total
harmonic distortion (THD) value of the stator current when using fuzzy control (Figure 12). A comparative
analysis of THD values is presented in Table 3, where it is evident that the THD rate achieved with fuzzy logic
control (FLC) is lower than that with PID control (PIDC). Consequently, it can be concluded that the proposed
fuzzy control method demonstrates superior robustness when compared to PID control.

Figure 10. The Power of the chain of wind based on DFIG with fuzzy controller and PID controller (RT)

Figure 11. Electromagnetic torque (test robust)

Enhancing of a wind power system control using intelligent artificial control … (Abdelmoumen Chandad)
1966  ISSN: 2088-8694

Figure 12. THD of stator current using fuzzy logic controller (RT) and PID controller (RT)

4. CONCLUSION
This paper discusses ways to enhance the efficiency of wind turbines equipped with a doubly fed
induction generator (DFIG). The system is based on a DFIM with a 2-level space vector modulation using a
neural network (NSVM-2L) inverter. Under identical operating conditions, DFIG’s reactive and active control
with fuzzy logic controller exhibits smaller overshoots, resulting in a faster response. This means that the fuzzy
control technique contributes to improving power quality and optimizing reactive and active power better than
PID control.

REFERENCES
[1] M. Yuan et al., “Would firm generators facilitate or deter variable renewable energy in a carbon-free electricity system?” Appl
Energy, vol. 279, p. 115789, Dec. 2020, doi: 10.1016/j.apenergy.2020.115789.
[2] A. Maleki, M. Rosen, and F. Pourfayaz, “Optimal Operation of a Grid-Connected Hybrid Renewable Energy System for Residential
Applications,” Sustainability, vol. 9, no. 8, p. 1314, Jul. 2017, doi: 10.3390/su9081314.
[3] F. Blouh, B. Boujidi, and M. Bezza, “Wind energy conversion system based on DFIG using three-phase AC-AC matrix converter,”
International Journal of Power Electronics and Drive Systems (IJPEDS), vol. 14, no. 3, p. 1865, Sep. 2023, doi:
10.11591/ijpeds.v14.i3.pp1865-1875.
[4] G. V. Madhav and Y. P. Obulesu, “A fuzzy logic control strategy for doubly fed induction generator for improved performance
under faulty operating conditions,” International Journal of Power Electronics and Drive Systems (IJPEDS), vol. 4, no. 4, Dec.
2014, doi: 10.11591/ijpeds.v4i4.5966.
[5] M. Edrah, K. L. Lo, and O. Anaya‐Lara, “Reactive power control of DFIG wind turbines for power oscillation damping under a
wide range of operating conditions,” IET Generation, Transmission & Distribution, vol. 10, no. 15, pp. 3777–3785, Nov. 2016, doi:
10.1049/iet-gtd.2016.0132.
[6] W. Li, G. Joos, and J. Belanger, “Real-time simulation of a wind turbine generator coupled with a battery supercapacitor energy storage
system,” IEEE Transactions on Industrial Electronics, vol. 57, no. 4, pp. 1137–1145, Apr. 2010, doi: 10.1109/TIE.2009.2037103.
[7] A. Kasbi and A. Rahali, “Doubly fed induction generator based variable speed wind conversion system control enhancement by
applying fractional order controller,” World Academy of Science, Engineering and Technology International Journal of Energy and
Power Engineering, vol. 13, no. 11, 2019.
[8] L. Jin, J. Fan, F. Du, and M. Zhan, “Research on two-stage semi-active ISD suspension based on improved fuzzy neural network
PID control,” Sensors, vol. 23, no. 20, p. 8388, Oct. 2023, doi: 10.3390/s23208388.
[9] V. M. Gopala and O. Y.P., “A new hybrid artificial neural network based control of doubly fed induction generator,” International
Journal of Electrical and Computer Engineering (IJECE), vol. 5, no. 3, p. 379, Jun. 2015, doi: 10.11591/ijece.v5i3.pp379-390.
[10] M. Singh and S. Santoso, “Dynamic models for wind turbines and wind power plants,” Golden, CO (United States), Oct. 2012. doi:
10.2172/1028524.
[11] M. T. Hagh, S. Roozbehani, F. Najaty, S. Ghaemi, Y. Tan, and K. M. Muttaqi, “Direct power control of DFIG based wind turbine
based on wind speed estimation and particle swarm optimization,” in 2015 Australasian Universities Power Engineering
Conference (AUPEC), IEEE, Sep. 2015, pp. 1–6. doi: 10.1109/AUPEC.2015.7324889.
[12] M. Aktarujjaman, M. E. Haque, K. M. Muttaqi, M. Negnevitsky, and G. Ledwich, “Control dynamics of a doubly fed induction
generator under sub- and super-synchronous modes of operation,” in 2008 IEEE Power and Energy Society General Meeting -
Conversion and Delivery of Electrical Energy in the 21st Century, IEEE, Jul. 2008, pp. 1–9. doi: 10.1109/PES.2008.4596625.
[13] A. Jain, S. Shankar, and V. Vanitha, “Power generation using permanent magnet synchronous generator (PMSG) based variable
speed wind energy conversion system (WECS): an overview,” Journal of Green Engineering, vol. 7, no. 4, pp. 477–504, 2018, doi:
10.13052/jge1904-4720.742.
[14] S. Li, A. Aitouche, and N. Christov, “Fault-tolerant control of wind turbine system using linear parameter-varying model,” Math
Probl Eng, vol. 2022, pp. 1–10, Jul. 2022, doi: 10.1155/2022/1290639.
[15] X. Wang, J. Zhou, B. Qin, Y. Luo, C. Hu, and J. Pang, “Individual pitch control of wind turbines based on SVM load estimation
and LIDAR measurement,” IEEE Access, vol. 9, pp. 143913–143921, 2021, doi: 10.1109/ACCESS.2021.3120543.
[16] A. M. Kassem, K. M. Hasaneen, and A. M. Yousef, “Dynamic modeling and robust power control of DFIG driven by wind turbine at infinite
grid,” International Journal of Electrical Power & Energy Systems, vol. 44, no. 1, pp. 375–382, Jan. 2013, doi: 10.1016/j.ijepes.2011.06.038.
[17] W. Dhyaa Eldeen Bahaa Eldeen, “Energy generation and electrical machine control parameters of DFIG in wind turbine,”
Engineering and Technology Journal, vol. 34, no. 11, pp. 2071–2085, Nov. 2016, doi: 10.30684/etj.34.11A.13.

Int J Pow Elec & Dri Syst, Vol. 15, No. 3, September 2024: 1959-1967
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1967

[18] Z. Kara and K. Barra, “Hybrid controller for variable speed wind energy conversion system with slip energy recovery using matrix
converter topology,” Periodica Polytechnica Electrical Engineering and Computer Science, vol. 59, no. 4, pp. 160–174, 2015, doi:
10.3311/PPee.8507.
[19] I. Ahmed and V. B. Borghate, “Simplified space vector modulation technique for seven‐level cascaded H‐bridge inverter,” IET
Power Electronics, vol. 7, no. 3, pp. 604–613, Mar. 2014, doi: 10.1049/iet-pel.2013.0135.
[20] R. G. Shriwastava, N. C. Ghuge, D. D. Palande, and A. Tidke, “Performance evaluation of conventional inverters driven PMSM
drive using microcontroller,” J Phys Conf Ser, vol. 2327, no. 1, p. 012001, Aug. 2022, doi: 10.1088/1742-6596/2327/1/012001.
[21] P. K. Magadum and S. Sakri, “A five level modified cascaded H-bridge inverter STATCOM for power quality improvement,”
Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 11, no. 1, Mar. 2023, doi: 10.52549/ijeei.v11i1.4430.
[22] H. Benbouhenni, “Direct power control of a DFIG fed by a seven-level inverter using SVM strategy,” International Journal of
Smart grid, vol. 3, no. 2, 2019, doi: 10.20508/ijsmartgrid.v3i2.47.g46.
[23] R. Lebied, R. Lalalou, H. Benalla, K. Nebti, and I. Boukhechem, “Ameliorate direct power control of standalone wind energy
generation system based on permanent magnet synchronous generator by using fuzzy logic control,” Electrical Engineering &
Electromechanics, no. 6, pp. 63–70, Dec. 2020, doi: 10.20998/2074-272X.2020.6.09.
[24] M. Madhusudhan, H. Pradeepa, M. V. L. Kumar, and S. K. Bilgundi, “Multimachine stability enhancement using fuzzy- logic based
pss tuning with shunt FACTS device,” Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 11, no. 1, Mar.
2023, doi: 10.52549/ijeei.v11i1.3931.
[25] C. Dumitrescu, P. Ciotirnae, and C. Vizitiu, “Fuzzy logic for intelligent control system using soft computing applications,” Sensors,
vol. 21, no. 8, p. 2617, Apr. 2021, doi: 10.3390/s21082617.

BIOGRAPHIES OF AUTHORS

Abdelmoumen Chandad was born in ADRAR (Algeria) on November 16, 1988.

He received his secondary education teacher degree (electrotechnic) in 2011 at higher school
(ENSET) Oran. He received his M.Sc. degree in 2018 at ENP-MA Oran and he is currently
working toward her Ph.D. thesis on modelling and control of a multi-source renewable energy
electrical production system at ENP-MA, Oran, Algeria. He can be contacted at email:
[email protected].

Messaoud Hamouda was born in Adrar Algeria on 25 November 1962. He is a

graduate of the University USTO in Oran (Algerai) in 1992. From the same university, he
received his M.Sc. degree in Electrotechnic (1997) and his Ph.D. in Electrotechnic (2007). He
has been managing director for seven years of the renewable energy research unit in Saharan
Medium in Adrar Algeria. He is a professor at the University of Adrar. Currently, he is a director
of Laboratory of the Sustainable Development and Informatic (LDDI). He is a member of many
scientific and industrial organizations. He has organized a significant number of conferences,
meetings, and study days on a national and international level. He is director of several doctoral
courses. His research interest’s concern: the integration of renewable energies, HVDC systems,
and the electrical discharges, optimization of energy flows in microgrids. He can be contacted
at email: [email protected].

Nedjadi Benharir received his teaching degree in Applied Sciences in Electrical

Engineering in 1975 ENSET-Oran, and state engineer in Electrical Engineer in (USTO1983).
He received his M.Sc. degree in 1987 at USTO-Oran. He became a grade class B lecturer
professor in 1988. He has been the head of Department of Electrical Engineering ENSET for
nine years, responsible for the 1983/1986 electricity laboratory, permanent member of the
CRUO (2005/2010). He is a member of many scientific and industrial organizations. His
research interests include design of software for simulating the dynamic behavior of electrical
networks. He can be contacted at email: [email protected].

Mohammed Bouzidi was born in 1981 in the city of Ulf Adrar, Algeria. He
obtained a master's degree in Electrical Engineering, specializing in control of machines and
networks, in 2015 from Bashar University, then obtained a doctorate degree in 2023 from Adrar
University. He is also an author and contributor to numerous papers. He currently works as a
lecturer at the University of Tamanrasset. His research interests include fault detection in
renewable energy systems using artificial intelligence, as well as industrial electrical materials.
He can be contacted at email: [email protected].

Enhancing of a wind power system control using intelligent artificial control … (Abdelmoumen Chandad)