![](bg6.png)
Fig. 10.b: AC three phase’s grid currents using neural
network MPPT approach (dual axis tracking).
Fig. 6, Fig. 7 and Fig. 8 show the waveforms of
the output voltage, current, and power of the PV
respectively. Here we can see that both P&O and
neural network approach were successfully able to
track the maximum power point for a PV panel at
any given irradiation. The neural network –based
MPPT algorithm can quickly and accurately find the
maximum power of each type (fixed and tracking
array) and the system achieved a true sense of the
maximum power output. The P & O algorithm
strongly depends on the initial conditions and it
presents oscillations around the optimal value. This
algorithm is bad behavior following a sudden change
in irradiation .The results show that neural network
optimization technique given better results compared
to P&O. As shown, for south facing fixed surface
solar power varies over the day, peaking at the solar
noon where tracking system has flatter hourly
energy production profile. As shown, the value of
the solar energy produced by the fixed system
approaches that of the two-axis system between 11
am and 14 pm, but it moves away during the hours
of the sunrise and the hours of the end of the
afternoon.
We can see also that the power production of a
PV system is directly related to the amount of solar
irradiance incident on the array. On average,
tracking systems yield a higher average normalized
power output under sunny conditions when
compared to stationary systems since they are
always oriented nearly perpendicular to direct beam
radiation.
In addition, this paper demonstrates the
importance and efficiency of dual tracking system.
The results indicate that the solar tracking system
generated more energy about 25% compared to the
power generated by identical fixed solar panels.
5 CONCLUSIONS
The neural network based MPPT control has clearly
demonstrated its utility and the effectiveness in
tracking the maximum power point of two identical
photovoltaic systems, the first is equipped with a
solar tracker while the second is without a tracker
and shows an excellent performance, high efficiency,
low error, very short response time, high dynamics
for both inverter and MPPT compared to classical
MPPT control.
ACKNOWLEDGMENT
This project was financially supported by the
Directorate General for Scientific Research and
Technological Development - Algerian Ministry of
Higher Education and Scientific Research.
REFERENCES
Ouchen, S., Abdeddaim, S., Betka, A., Menadi, A.,
Experimental validation of sliding mode-predictive
direct power control of a grid connected photovoltaic
system, feeding a nonlinear load, Solar Energy 137
(2016) 328–336.
Borni, A., Bouarroudj, N., Bouchakour, A. and Zaghba,
L., P&O-PI and fuzzy-PI MPPT Controllers and their
time domain optimization using PSO and GA for grid-
connected photovoltaic system: a comparative study
,Int. J. Power Electronics, Vol. 8, No. 4, 2017.
Zaghba, L., Terki, N., Borni, A., Bouchakour, A., Benbitour
Née Khennane Messaouda, Adaptive intelligent MPPT
controller comparison of Photovoltaic system under
different weather Conditions of ghardaia site (south of
Algeria), Journal of Electrical Engineering, Volume 15 /
2015 - Edition: 3.
Astudillo, D. P., Bachour, D., 2015. Variability of
measured global horizontal irradiation throughout
Qatar. Sol. Energy 119, 169–178.
Kebour, O., Arab, A. H., Abdelkader Hamid, Kamel
Abdeladim, Contribution to the analysis of a stand-
alone photovoltaic system in a desert environment,
Solar Energy 151 (2017) 68–81.
Zaghba
1
, L., Khennane, M., Terki, N., Borni, A.,
Bouchakour A., Fezzani, A., Hadj Mahamed, I., and
Oudjana, S. H., The effect of seasonal variation on the
performances of grid connected photovoltaic system in
southern of Algeria, AIP Conference Proceedings,
0 5 10 15 20 25
-20
-10
0
10
20
30
40
50
60
Time of Day
Three phases grid current, Iabc (A)
10 10.1 10.2
-20
0
20
0 5 10 15 20 25
-20
-10
0
10
20
30
40
50
60
Time of day
Three phases grid current, Iabc (A)
10 10.1 10.2
-20
0
20
Ia
Ib
Ic
Ia
Ib
Ic
Fixed array
Dual axis tracking array
ICCSRE 2018 - International Conference of Computer Science and Renewable Energies
204