TSINGHUA SCIENCE A N D TECHNOLOGY ISSN 1007-0214 12/23 pp204-208 V o l u m e 10, N u m b e r 2, April 2005

Artificial Neural Network Maximum Power Point Tracker for Solar Electric Vehicle
Theodore Amissah O C R A N , C A O Junyi CAO Binggang ( f ^ B ' J ) , SUN Xinghua ( # ^ )

R e s e a r c h a n d D e v e l o p m e n t C e n t e r for E l e c t r i c V e h i c l e , X i ' a n J i a o t o n g U n i v e r s i t y , X i ' a n 7 1 0 0 4 9 , C h i n a

Abstract:

This paper proposes an artificial neural network maximum power point tracker (MPPT) for solar

electric vehicles. The MPPT is based on a highly efficient boost converter with insulated gate bipolar transistor (IGBT) power switch. The reference voltage for MPPT is obtained by artificial neural network (ANN) with gradient descent momentum algorithm. The tracking algorithm changes the duty-cycle of the converter so that the PV-module voltage equals the voltage corresponding to the MPPT at any given insolation, temperature, and load conditions. For fast response, the system is implemented using digital signal processor (DSP). The overall system stability is improved by including a proportional-integral-derivative (PID) controller, which is also used to match the reference and battery voltage levels. The controller, based on the information supplied by the ANN, generates the boost converter duty-cycle. The energy obtained is used to charge the lithium ion battery stack for the solar vehicle. The experimental and simulation results show that the proposed scheme is highly efficient.
Key words:

artificial neural network; maximum power point tracker (MPPT); photovoltaic module; digital signal processor; solar electric vehicle

Introduction
Photovoltaic (PV) generation is gaining increased importance as a renewable source of energy. The undesirable rapid changes of solar power, which usually occur in a running vehicle, arise as a result of shade from buildings, large trees, and clouds in the sky. Conventional PV systems have difficulties in responding to rapid variations due to shade. The main drawbacks of PV systems are that the initial installation cost is considerably high and the energy conversion efficiency (from 12% to 29%) is relatively low. Furthermore, in most cases, PV systems require a power conditioner
Received: 2004-03-24 * * To whom correspondence should be addressed. E-mail: caojy@mailst.xjtu.edu.cn; Tel: 86-29-87570252

(dc-dc or dc-ac converter) for load interface. Therefore, the overall system cost could be reduced drastically by using highly efficient power conditioners, such as the maximum power point tracker (MPPT), to extract and maintain the peak power from the PV module even when the above-mentioned unfavorable conditions occur. Various methods of maximum power tracking have been considered in PV power applications^ " ^. Among the hill climbing methods , the perturb and observe (P&O) method tracks maximum power point (MPP) by repeatedly increasing or decreasing the output voltage at MPP of the PV module. This method requires calculation of dP/dFto determine the MPP ' ' . Though the method is relatively simple to implement, it cannot track the MPP when the irradiance changes rapidly. Also, the method oscillates around the MPP instead of
1 12 [1_5] [1 2 4]

Theodore Amissah OCRAN et al: Artificial Neural Network Maximum Power Point

Tracker

205

directly tracking

it. The incremental

[6 7]

conductance among the

technique (ICT) is the most accurate '

other methods. This method gives good performance under rapidly changing conditions. However, the complex calculation of dl/dV and the complicated algorithm require use of a digital signal processor (DSP), which will usually increase the total system coEhe M P P tracking method using the short circuit current of the P V module utilizes the fact that the operating current at M P P of the P V module is linearly proportional to the short circuit current of the P V modu l e ^ . Under rapidly changing atmospheric conditions, this method has a fast response speed of tracking the MPP, but the control circuit is complicated. The M P P tracking method using open circuit voltage of the solar panel
[11]

Fig. 1

Equivalent circuit of a solar cell

exp

AkT (1) are the output current and output is the generated current is the reverse saturation k is the

where 7 a n d
o

voltage of the solar array; / under a given insolation; 7

sat

utilizes the fact that the operating voltage at

current; q is the charge of an electron; N junction; is the array temperature; R array.

M P P is almost linearly proportional to open circuit voltage at M P P of the P V module (using 7 6 % of open circuit voltage as the M P P voltage). This method is very simple and cost-effective, but the reference voltage does not change between samplings. MPPTs using the fuzzy l o g i c '
[13 14]

Boltzmann constant; A is the ideality factor for a Ps

and R

sh

are the intrinsic series and shunt resistances of the solar The saturation current of the solar array varies with temperature according to the following equation: exp qE
G

and the artificial neural network

(ANN) ing the the

[ 1 5 ]

have been reported. These studies show that tracking performance as compared to where T

such modern control algorithms are capable of improvconventional methods.

r

Bk

(2)

In this paper, we propose an A N N M P P T for solar electric vehicle P V systems. The tracking algorithm changes the duty ratio of the converter so that the P V module voltage equals the voltage corresponding to the M P P at that atmospheric condition. This adjustment is carried out by using the back-propagation A N N . The reference voltage to the M P P is obtained by an offline trained A N N . The controller generates the boost converter duty-cycle.

is the reference temperature;

r

I = 17 + ^ _ ( r - 2 5 ) l L so /v ; J
8

(3) I
or

is the

saturation current at T ; also an ideality factor; 7 at 25C; Kj coefficient and

G0

is the band-gap en-

ergy of the semiconductor used in the solar array; is

sc

is the short circuit current

2

is the short-circuit current temperature is the insolation in m W / c m .

Equations (l)-(3) are used in the development of computer simulations for the solar array. The Matlab programming language is used. Figure 2 show the simulated current-voltage and power-voltage curves for the solar array at different insolations and different temperatures. These curves show that the output characteristics of the solar array are nonlinear and greatly affected by the solar radiation, temperature, and load condition. Each curve has a maximum power point (TW), which is the optimal operating point for the efficient use of the solar array.

PV Module Characteristics

The solar array characteristics significantly influence the design of the converter and the control system, so the P V characteristics will be briefly reviewed here. The solar array is a nonlinear device and can be represented as a current source model, as shown in Fig. 1. The traditional I-V characteristics of a solar array, when neglecting the internal shunt resistance, are given by the following equation:

Artificial Neural Network

A N N technology has been successfully applied to

206 5-1000 W/m'

Tsinghua

Science

and Technology,

April

2 0 0 5 , 10(2): 2 0 4 - 2 0 8

j when neuron j is a hidden unit; e. (n) is the error signal at the output of neuron j for iteration ; and the set C includes all the neurons in the outer layer of the network. The correction Aw () to the

synaptic weight w () is given by

Aw () = aAw ( -1) + {n)y ()

] t

(5)

where a is the momentum constant; is the learning-rate parameter of the back-propagation algorithm; Sj(n) is the local gradient. The error signal at the output is defined as e (n) = d (n)-y (n)
J J J

(6)

where d. {n) is the desired response or wanted targets and y. (n) is the output signal. Adjustment of the weights for these layers is given by w (n +1) = w (n) + a*w (n -1) + [n)y (n)
] i

(7) From Eqs. (4) and (6), the mean squared error performance index can be rewritten as s(n) = \(V (n)-V (n)f.
K( A

The network training is performed repeatedly until the performance index = (V f-V )
rQ A 2

falls

below a

specified value, ideally to zero. In other words > 0 implies (V -V )

re{ A 2

^ 0 , and then the connecting is identically equal to the maximp

weights of the network are adjusted in such a way that the array voltage V ence voltage F
0 40 60 UN (c) Power-voltage curves 20 80
A

mum power point voltage V . At this stage the referref

becomes equal to the maximum V .

mp

power point voltage

Fig. 2

C u r r e n t - v o l t a g e a n d p o w e r - v o l t a g e c u r v e s for different

t h e s o l a r a r r a y at d i f f e r e n t i n s o l a t i o n s a n d t e m p e r a t u r e s (S is t h e s o l a r r a d i a t i o n )

solve very complex problems. Recently, its application in various fields is increasing rapidly ' . The instantaneous sum of error squares or error energy at iteration is given by
[16 17]

<) = \{)
Z

(4)

J t C

where neuron j lies in a layer to the right of neuron i, and neuron k lies in a layer to the right of neuron

The configuration of the proposed three-layer feedforward neural network function approximator is shown in Fig. 3. The neural network is used to obtain the voltage of the maximum power V (n) of the solar panel. The network has three layers: an input, a hidden, and an output layer. The numbers of nodes are two, four, and one in the input, the hidden, and output layers, respectively. The reference-cell open circuit voltage V {n) and the time parameter (n) are supplied to the input layer of the neural network. These signals are directly passed to the nodes in the next hidden layer. The node in the output layer provides the identified maximum power point voltage V (n) . The nodes in the hidden layer get signals from the input
mp oc

Theodore Amissah OCRAN et al:

Artificial

Neural

Network

Maximum

Power

Point

Tracker

207

layer and send their output to the node in the output layer. The sigmoid activation function is utilized in the layers of the network. The training program calculates the connecting weights ^{1,1} with the bias b{\} for the input to hidden layer mapping, the connecting weights W {2,1} with bias b{2} for the hidden layer to
L

output layer mapping. During the training, the connecting weights are modified recursively until the best fit is achieved for the input-output patterns in the training data. The training of the net was accomplished off-line using Matlab.
Hidden Output

Input

^oc()
T{n)

* \ ^,{1,1}
)

W {2,1}
L

b{2}

>(>
1

2 Fig. 3

Feed-forward neural network function approximator

Experimental/Simulation Results

A PV array used for the collection of the experimental data is JDG-M-45 (Germany) type modules. The module has a maximum power output of 45 W and a 20-V open-circuit voltage at an irradiation of 1000 W/m and a 25C temperature. The PV module specifications provided by the manufacturer in Table 1.
2

7=0.1; momentum factor a =0.9; number of training iterations=10 000; error goal=0.000 001. The convergence error for the training process is shown in Fig. 4.

Table 1

E l e c t r i c a l s p e c i f i c a t i o n s for t h e P V (JDG-M-45)
m

module

M a x i m u m power, P

(W)
SC

45 2.93 20
mp

2000

S h o r t circuit current, 7

(A) (V) (V) (A)

4000 6000 Iterations error

8000

10 000

O p e n circuit v o l t a g e , V

Fig. 4

Convergence

for t h e

neural

network

oc

V o l t a g e at m a x p o w e r p o i n t , V C u r r e n t at m a x p o w e r p o i n t , 7 Size ( m m X m m X m m ) M a s s (kg)

17.1 2.64 971X441X28 5

training process

m p

The feed-forward back-propagation ANN, as shown in Fig. 3 was trained with values obtained from experimental data of the reference cell. Gradient descent algorithm was used in training as it improves the performance of the ANN, reducing the total error by changing the weights along its gradient. The training parameters are as follows: learning rate parameter
Table 2

The parameters used for the training of the ANN and the output values given by the ANN after the training can be found in Table 2. Various sets of reference cell open circuit voltage V and a time parameter (as shown in Table 2) are supplied as the input to the ANN. In order to validate the learning capability of the ANN, other sets of V different from the one in Table 2 were also supplied to the ANN, which gave out values of V as expected. The software Matlab was used in the training of the ANN.
oc oc mp

T h e results of the trained data given by the A N N H o u r of the day

9:00 Time parameter V V V

oc

9:30 -0.9 0.519 0.394 0.379

10:00 -0.8 0.516 0.392 0.388

10:30 -0.7 0.529 0.402 0.416

11:00 -0.6 0.517 0.393 0.395

11:30 -0.5 0.514 0.391 0.394

12:00 -0.4 0.516 0.392 0.392

12:30 -0.3 0.510 0.388 0.388

13:00 -0.2 0.511 0.388 0.388

13:30 -0.1 0.509 0.387 0.386

14:00 0 0.508 0.386 0.385

-1 0.555 0.422 0.421

measured measured given by A N N

mp

mp

208

Tsinghua

Science

and Technology,

April

2 0 0 5 , 10(2): 2 0 4 - 2 0 8

The weights to the hidden layer 1 from input 1 are as follows: ^{1,1} = "2.1706 -5.3865 -3.2326 -5.1766" [109.8309 -27.9435 97.7250 -8.5640_
1

LA, U S A , 2000: 115-1156. [6] T s e , H o , C h u n g S, H u i S Y . A n o v e l m a x i m u m p o w e r p o i n t t r a c k e r for P V p a n e l s u s i n g s w i t c h i n g q u e n c y m o d u l a t i o n . IEEE 17(6): 980-989. [7] Brambilla A, Gambarra M , Garutti A, Ronchi F. N e w approach to photovoltaic arrays m a x i m u m power point tracking. In: P r o c . I E E E P o w e r E l e c t r o n . S p e c . Conf., C h a r l e s ton, SC, U S A , 1999: 632-637. [8] M u t o h N , M a t u o T, O k a d a K, S a k a i M . P r e d i c t i o n - d a t a b a s e d m a x i m u m p o w e r p o i n t t r a c k i n g m e t h o d for p h o t o v o l t a i c p o w e r g e n e r a t i o n s y s t e m s . In: P r o c . I E E E P o w e r Trans. Power Electron., fre-

2002,

The weights to the output layer 2 are ^{2,1} = [-0.2039 layer 1 0.0065 is 0.0561 -0.3029]. The bias to 12.996 -54.4753 b{\} = [-60.0887

-1.5969]. The bias to layer 2 is b{2} = [-0.0397].

Conclusions

An artificial neural network MPPT for charging the battery stack of a solar (hybrid) vehicle has been proposed in this paper. An off-line ANN, trained using a back-propagation with gradient descent momentum algorithm, is utilized for online estimation of reference voltage for the feed-forward loop. Experimental data is used for the offline training of the ANN, and software Matlab is used in the training of the net. The precision of the estimation has been verified by the graph of the convergence error. The proposed method has several advantages over the conventional methods, particularly in that there is no need for voltage and current sensors, and in that it avoids a complex calculation of power. The experimental and simulation results show that the proposed scheme is highly efficient. References
[1] H u a C, L i n J, S h e n C. I m p l e m e n t a t i o n of a D S P - c o n t r o l l e d p h o t o v o l t a i c s y s t e m w i t h p e a k p o w e r t r a c k i n g . IEEE Ind. Electron., [2] 1998, 45(1): 99-107. Trans.

E l e c t r o n . S p e c . Conf., C a i r n s , A u s t r i l i a , 2 0 0 2 : 1 4 8 9 - 1 4 9 4 . [9] N o g u c h i T, T o g a s h i S, N a k a m o t o R. S h o r t - c u r r e n t p u l s e b a s e d m a x i m u m p o w e r p o i n t t r a c k i n g m e t h o d for m u l t i p l e p h o t o v o l t a i c a n d c o n v e r t e r m o d u l e s y s t e m . IEEE Ind. Electron., [10] 2002, 49(1): 217-223. improved Trans.

L e e D Y , N o h J, H y u n D S, C h o y I. A n

M P P T c o n v e r t e r u s i n g c u r r e n t c o m p e n s a t i o n m e t h o d for small scaled PV-applications. In: P r o c . IEEE Applied

P o w e r E l e c t r o n . Conf., D a l a s , T X , U S A , 2 0 0 2 : 5 4 0 - 5 4 5 . [11] E n s l i n J R, W o l f S, S n y m a n D B , S w e i g e r s W . I n t e grated photovoltaic m a x i m u m power point tracking converter. IEEE [12] Trans. Ind. Electron., 1997, 44(6): 769-773.

C h e n Y , S m e d l e y K, V a c h e r F , B r o u w e r J. A n e w m a x i mum power point tracking controller for photovoltaic

p o w e r g e n e r a t i o n . In: P r o c . I E E E A p p l i e d P o w e r E l e c t r o n . Conf., M i a m i B e a c h , F L , U S A , 2 0 0 3 : 5 6 - 6 2 . [13] N a f e h A , F a h m y F H , E l - Z a h a b A . E v a l u a t i o n of a p r o p e r c o n t r o l l e r p e r f o r m a n c e for m a x i m u m p o w e r p o i n t t r a c k i n g o f a s t a n d - a l o n e P V s y s t e m . International of Numerical [14] Veerachary Modelling, M, Senjyu 2002, 15(4): 385-398. S, U e z a t o K. Feedforward Journal

K o u t r o u l i s E , K a l a i t z a k i s K, V o u l g a r i s C. D e v e l o p m e n t of a m i c r o c o n t r o l l e r - b a s e d p h o t o v o l t a i c m a x i m u m p o w e r p o i n t t r a c k i n g c o n t r o l s y s t e m . IEEE tron., 2 0 0 1 , 1 6 ( 1 ) : 4 6 - 5 4 . Trans. Power Elec-

m a x i m u m p o w e r p o i n t t r a c k i n g of P V s y s t e m s u s i n g fuzzy c o n t r o l l e r . IEEE 38(3): 969-981. [15] H i y a m a T, K o u z u m a S, O r t m e y e r T. E v a l u a t i o n o f n e u r a l network based real time m a x i m u m p o w e r tracking controller for P V s y s t e m . IEEE 10(3): 543-548. Trans, on Energy Com., 1995, Trans. Aerosp. and Electron. Syst., 2002,

[3]

K u o Y C, L i a n g J, C h e n J F . N o v e l m a x i m u m p o w e r p o i n t t r a c k i n g c o n t r o l l e r for p h o t o v o l t a i c e n e r g y c o n v e r sion s y s t e m . IEEE 601. Trans. Ind. Electron., 2001, 48(3): 594-

[4]

S u l l i v a n C R, P o w e r s J. A h i g h - e f f i c i e n c y

maximum

[16]

B o s e . Artificial n e u r a l n e t w o r k a p p l i c a t i o n s in p o w e r e l e c t r o n i c s . In: P r o c . I E E E Ind. E l e c t r o n . Conf., D e n v e r , CO, USA, 2 0 0 1 : 1631-1638.

p o w e r p o i n t t r a c k e r for p h o t o v o l t a i c a r r a y s in a solarp o w e r e d r a c e v e h i c l e . In: P r o c . I E E E P o w e r E l e c t r o n . S p e c . Conf., Seattle, W A , U S A , 1 9 9 3 : 5 7 4 - 5 8 0 . [5] S i m o e s G, F r a n c e s c h e t t i . A rise-microcontroller [17]

H a y k i n S. N e u r a l N e t w o r k s A C o m p r e h e n s i v e F o u n d a tion, 2
n d

Edition. N e w York: Prentice Hall Inc., 1999.

b a s e d p h o t o v o l t a i c s y s t e m for i l l u m i n a t i o n a p p l i c a t i o n s . In: P r o c . I E E E A p p l i e d P o w e r E l e c t r o n . Conf., N e w O r l e a n s ,