Neural Network Integrated with Regression …psrcentre.org/images/extraimages/12. 512033.pdfAbstract...
Transcript of Neural Network Integrated with Regression …psrcentre.org/images/extraimages/12. 512033.pdfAbstract...
Abstract— This paper combined artificial neural network
and regression modeling methods to predict electrical load.
We propose an approach for specific day, week and/or month
load forecasting for electrical companies taking into account
the historical load. Therefore, a modified technique, based on
artificial neural network (ANN) combined with linear
regression, is applied on the KSA electrical network dependent
on its historical data to predict the electrical load demand
forecasting up to year 2020. This technique was compared
with extrapolation of trend curves as a traditional method
(Linear regression models). Application results show that the
proposed method is feasible and effective. The application of
neural networks prediction shows the capability and the
efficiently of the proposed techniques to obtain the predicting
load demand up to year 2020.
Keywords— Electrical load, time series prediction, neural
networks, multiple regressions.
I. INTRODUCTION
OAD forecasting problem is receiving great and growing
attention as being an important and primary tool in power
system planning and operation. Importance of load forecasting
becomes more significant in developing countries with high
growth rate such as KSA. Owing to the importance of load
forecasting, various models have been proposed for the short-
term load forecasting in the last decades, such as regression-
based methods [1-2], Box Jenkins model [3], time-series
approaches [4], Kalman filters [5], expert system techniques
[6], neural network models [7, 8, 9], fuzzy logic [10], and
fuzzy-neural network structures [11]. Recently, applications of
hybrid ANNs model with statistical methods or other
intelligent approaches have received attentions. Examples of
such systems are hybrids with Bayesian inference [12], self-
organizing map [13], wavelet transform [14], and particle
swarm optimization [15].
A price forecasting system for electric market participants
Saeed Badran is with Electrical Engineering Department
Faculty of Engineering, Al-Baha University, 15456 Al-Baha, Kingdom of
Saudi Arabia, (corresponding author to provide phone: +966504588910; fax:
+96670554557; e-mail: [email protected]).
Ossama Abouelatta, was Production Engineering and Mechanical Design
Department, Faculty of Engineering, Mansoura University, 35516 Mansoura,
Egypt. He is now with the Department of Mechanical Engineering, Faculty of
Engineering, Al-Baha University, 15456 Al-Baha, Kingdom of Saudi Arabia,
(e-mail: [email protected]).
was proposed by Lin et al. [9], to reduce the risk of price
volatility. A hybrid neural network model based on self-
organizing map has been presented by Amin-Naseri and
Soroush [13], for daily electrical peak load forecasting. The
results proved the superiority and effectiveness of their
proposed hybrid model. The results showed that the suggested
clustering approach significantly improves the forecasting
results on regression analysis too. Xiaoxing and Caixin et al.
[16] proposed a dynamic and intelligent data cleaning model
based on data mining theory. The rapid and dynamic
performance of the model makes it suitable for real time
calculation, and the efficiency and accuracy of the model is
proved by test results of electrical load data analysis.
The second kind of prediction is known as medium-term
forecasting. There are several methods of medium-term load
forecasting such as time-series approaches [17], neural
network models [18], and Fourier series approach [19].
Almeshaiei and Soltan [1], presented a pragmatic methodology
that can be used as a guide to construct electric power load
forecasting models. Some results are reported to guide
forecasting future needs of this network. A new technique is
proposed by Abu-Shikhah and Elkarmi [20] that uses hourly
loads of successive years to predict hourly loads and peak load
for the next selected time span. The proposed method can be
implemented to the hourly loads of any power system.
Pedregal and Trapero [21] developed a general multi-rate
methodology in order to forecast optimally load demand series
sampled at an hourly rate for a mid-term horizon. The results
showed that this method produces a notable reduction on the
prediction error and its variability.
The third kind of prediction is known as long-term forecasting.
The major methods for long-term load forecasting are time-
series approach [22], intelligent methods [23], neuro-fuzzy
approach [24], dynamic simulation theory [25], hierarchical
neural model [26], and support vector machines [27]. Their
results demonstrated the effectiveness of the methodology
handling this type of problems. A mathematical method is
proposed by Filik et al. [2], for modeling and forecasting
electric energy demand in which it enables the possibility of
making short-, medium-, and long-term hourly load forecasting
within a single framework. Abou El-Ela et al. [28] introduced
what so called a proposed optimization technique, for
predicting the peak load demand and planning of transmission
line systems. The application on a selected network showed
the capability and the efficiently of the proposed techniques to
Neural Network Integrated with Regression
Methods to Forecast Electrical Load
Saeed Badran, and Ossama Abouelatta
L
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
60
obtain the predicting peak load demand and the optimal
planning of transmission lines of the selected network up to
year 2017. The objective of this study is aimed to develop a
generalized method for precise load forecasting within the
horizons of short-, medium-, and long-terms, all in hourly
accuracy.
II. ELECTRIC LOAD FORECASTING
Load forecasting problem is receiving great and growing
attention as being an important and primary tool in power
system planning and operation. Importance of load forecasting
becomes more significant in developing countries such as
KSA. The accuracy of load forecasting is crucial due to its
direct influence on generation planning, and for its economic
impacts. In the modern system operation, the advance
technology of computer has been extensively applied in the
field of power system planning, monitoring and control.
Nowadays, most operation of electric utility utilizes the energy
management system. The traditional way for power engineers
to perform the system analysis is to use mathematical model.
This model is usually difficult especially when dealing with
large systems. Handling these problems with mathematical
model is therefore not realistic.
Due to the ability of ANN model to perform pattern
recognition, prediction and optimization in a fast and efficient
manner, it has become one of the main topics of interest for
many researchers to investigate its application in many fields
including power system. Some examples of utilizing ANN in
power system applications are: Load forecasting, fault
classification, power system assessment, real time harmonic
evaluation, power factor correction, load scheduling, design of
transmission lines, and power system planning.
Load forecast has been an attractive research topic for many
decades and in many countries all over the world, especially in
fast developing countries with higher load growth rate. Load
forecast can be generally classified into four categories based
on the forecasting time, Table I.
III. ARTIFICIAL NEURAL NETWORKS
An Artificial Neural Network (ANN) is a computational model
that attempts to account for the parallel nature of the human
brain. Specifically, it is a network of highly interconnecting
processing elements (neurons) operating in parallel, Fig. 1. An
ANN can be used to solve problems involving complex
relationships between variables. The particular type of ANN
used in this study is a supervised one, wherein the observation
(target) is specified, and the ANN is trained to minimize the
error between the ANN output and the target, resulting in an
optimal solution (assuming the global minimum is reached.)
This is accomplished by adjusting the connections between the
elements, which involves an adjustment to the weights
(w11,1…w
11,z). In theory, this adjustment process can be viewed
as a form of ‘learning’. Thus, the ANN is considered to be a
form of artificial intelligence. ANNs were selected for this
study owing to their ability to model non-linear relationships.
The relationship between the input and output parameters in
this study is highly non-linear.
Inputs Hidden Layer Output Layer
. .
. .
P1
w11,z b
1 b
2
a1 n
1 w2
1,1 n2 a
2
w11,1 P2
P3
Pz
a1=f1(w1p+b1) A2=f2(w2
p a1+b2)
f1 f2
Fig. 1 A 2-layer ANN with multiple inputs and single hidden and
output neurons
IV. NETWORK DESIGN
Forecasting of electricity demand has become one of the major
research fields in electrical engineering. The supply industry
requires forecasts with lead times that range from the short
term (a few minutes, hours, or days ahead) to the long term (up
to 20 years ahead). Load forecasting is however a difficult task
because of complexity of load series that have high non-
linearity relation among variables and load exhibits several
levels of seasonality. In addition, there are many important
exogenous variables that must be considered, especially
weather-related variables. One of the promising tools to
achieve a good load forecasting is the ANN which achieved
great success in dealing with non-linear problems such as load
forecasting problem.
A. Data analysis
The power system has a complicated behavior and the load
is influenced by many factors. The energy consumption served
by the utility can be generally categorized into industrial,
commercial and residential loads. The demand of commercial
and industrial activities basically relies on the level of
production, which is somewhat steady and relatively easy to be
estimated.
There are many factors that affect load changes. They can
be generally classified as calendar, weather and random
factors. Fig. 2 shows hourly load variations from 1/1/2006 to
31/12/2006 of Jeddah city in KSA. Fig. 2(a) shows the hourly
TABLE I
CLASSIFICATION OF LOAD FORECAST BASED ON THE FORECASTING TIME
Load
forecast Period Importance
Long 1-10 Years
To calculate and to allocate the
required future capacity.
To plan for new power stations to
face customer requirements.
Plays an essential role to determine
future budget.
Medium 1-week to few
months
Fuel allocation and maintenance
schedules.
Short 1-hour to 1-week
Accurate for power system
operation.
To evaluate economic dispatch,
hydro-thermal co-ordination, unit
commitment, transaction.
To analysis system security among
other mandatory function.
Very short 1-minute - 1- hour Energy management systems (EMS).
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
61
electric load variation whereas Fig. 2(b) shows the same data
after applying moving average filter to clear the presentation
of data. It can be observed that the load during summer is
higher than that in other seasons. Seasonal variation is mainly
due to temperature variance.
Jan. Feb. March April May June July Aug. Sept. Oct. Nov. Dec.1000
2000
3000
4000
5000
Time (Month)
Ele
ctric
load
(M
W)
2006
(a) Hourly load over.
Jan. Feb. March April May June July Aug. Sept. Oct. Nov. Dec.1000
2000
3000
4000
5000
Time (Month)
Ele
ctric
load
(M
W)
2006
(b) Hourly load over one year after applying moving average filter.
Fig. 2 Hourly load over one year (2006)
A detailed (zoomed) 1-D plot of one day period of years
from 2002 to 2006 is shown in Fig. 3. It must be noted that for
a lower complexity model, it is better to take the starting hour
of the day as 8:00 AM, which typically corresponds to the
minimum demand hour. Comparing Fig. 3(a) and (b), one can
see that the daily load shown in Fig. 3(b) is more useful in
terms of providing a simpler model. This strategy was already
applied in presenting the mesh plot of Fig. 4.
Load is generally higher during weekdays because there are
more social activities. In KSA as any Islamic country,
weekend is Friday and many of private sector and
governmental institutions consider Thursday and Friday as
weekends. As a result, the weekly load curve will be
completely different between Islamic countries and European
countries. Fig. 5(a) plots hourly load data for one week of
years from 2002 to 2006 in Jeddah, KSA. Fig. 5(b) plots
hourly load data for one week of years from 1988 to 2006 in
Jeddah, KSA.
B. Data preparations
Successful operation of load forecasters using ANN requires
an appropriate training data set and training algorithm. The
training data set should cover all ranges of the input patterns
sufficiently to provide the network knowledge to recognize
and generalize the relations among the variables in the
problem. In this work, a historical data from the city of Jeddah
in KSA from 1/1/1988 to 31/12/2006 were used.
C. Data preparations
Load forecasting is important for energy suppliers, financial
institutions, and other participants in electric energy
generation, transmission, distribution, and markets. The three
load forecasting types, which are short-, medium-, and long-
term, are very important for power planning and operation.
0.0 4.0 8.0 12.0 16.0 20.0 24.01000
1200
1400
1600
1800
2000
2200
2400
2600
2800
Time (Hours)
Ele
ctr
ic load (
MW
)
2002
2003
2004
2005
2006
(a) The day assumed to start mid-night.
8.0 12.0 16.0 20.0 24.0 4.0 8.01000
1200
1400
1600
1800
2000
2200
2400
2600
2800
Time (Hours)
Ele
ctr
ic load (
MW
)
2002
2003
2004
2005
2006
(b) The day assumed to start 8:00 AM.
Fig. 3 Hourly load data in 1-D time plot for one day of years from
2002 to 2006
05
1015
2025
1980
1990
2000
2010500
1000
1500
2000
2500
3000
Time (Hours)Year
Ele
ctr
ic load (
MW
)
(a) The day assumed to start mid-night.
8.0 12.0 16.0 20.0 24.0 4.0 8.0
1980
1990
2000
2010500
1000
1500
2000
2500
3000
Time (Hours)Year
Ele
ctr
ic load (
MW
)
(b) The day assumed to start 8:00 AM.
Fig. 4 2-D representation of hourly consecutively load data of years
from 1998 to 2006 for one day
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
62
Fri Sat Sun Mon Tue Wen Thr 1000
1200
1400
1600
1800
2000
2200
2400
2600
2800
3000
Time (Hours)
Ele
ctr
ic load (
MW
)
2002
2003
2004
2005
2006
(a) 1-D representation of hourly consecutively load data for one week
of years from 2002 to 2006.
FriSat
SunMon
TueWen
Thr
1980
1990
2000
20100
500
1000
1500
2000
2500
3000
Time (Hours)Year
Ele
ctr
ic load (
MW
)
(b) 2-D representation of hourly consecutively load data for one week
of years from 1998 to 2006.
Fig. 5 Weekly cycle of load changing characteristics.
In neural network, learning, which extracts information from
the input data, is a crucial step that is badly affected through
the selection of initial weights and the stopping criteria of
learning. If a well-designed neural network is poorly trained,
the weight values will not be close to their optimum and the
performance of the neural network will suffer. In general,
initial weight is implemented with a random number generator
that provides a random value. To stop the training process, we
could either limit the number of iterations or set an acceptable
error level for the training phase.
The training and validation procedures for specific network
architectures were repeated in order to handle uncertainties of
the initial weights and stopping criteria. In the preliminary
investigation it was found that about 300 trials were enough to
find the best result. The performance efficiencies of each trial
were recorded and compared.
V. ELECTRIC LOAD FORECASTING
This work provides a unified approach that enables the
“hourly” resolution property for all of the mentioned forecast
ranges. The proposed method consists of a nested combination
of two methods for modeling and forecasting electric loads.
The two methods are: neural network and linear regression
models. The procedure of work could be summarized as
follows:
1. A neural network was applied using electric load data
from year 2002 to year 2006 to predict hourly load for one
day, one week, one month and one year. Fig. 6 show the
regression output of neural network training regression.
2. A linear regression models were derived for all cases (one
day, one week, one month and one year). An example for the
estimated maximum, minimum and average values are shown
in Fig. 7.
3. Then, the electric load was calculated as the predicted
neural network (Step 1) shifted by the predicted average value
calculated using (Step 2). Fig. 8 shows a graphical user
interface used to predict electric load.
500 1000 1500 2000 2500
500
1000
1500
2000
2500
Target
Ou
tpu
t ~
= 0
.91
*Ta
rge
t +
1.1
e+
00
2
Training: R=0.95568
Data
Fit
Y = T
500 1000 1500 2000 2500
500
1000
1500
2000
2500
Target
Ou
tpu
t ~
= 0
.91
*Ta
rge
t +
1e
+0
02
Validation: R=0.95217
Data
Fit
Y = T
500 1000 1500 2000 2500
500
1000
1500
2000
2500
Target
Ou
tpu
t ~
= 0
.9*T
arg
et
+ 1
.4e
+0
02
Test: R=0.93722
Data
Fit
Y = T
500 1000 1500 2000 2500
500
1000
1500
2000
2500
Target
Ou
tpu
t ~
= 0
.91
*Ta
rge
t +
1.1
e+
00
2
All: R=0.95238
Data
Fit
Y = T
Fig. 6 Neural network training regression plot.
Fig. 7 Maximum, average and minimum electric load from year 1988
to year 2006 during one working day.
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
63
Fig. 8 Graphical user interface of Electric load forecaster.
There is no guarantee that coefficients which are close to
optimal values will be found during the learning phase even
though the number of iterations is capped at a predefined
value. Therefore, the performances of the proposed models are
measured with four efficiency terms. Each term is estimated
from the predicted values of the model and the measured
discharges (targets). The accuracy of the proposed method is
tested using hourly actual load values for the years 1988–2006.
The forecasting results are obtained for the proposed model
variations and different years in terms of mean absolute
percentage Error (MAPE) and correlation coefficient (R),
whose definitions are given in (1) and (2), respectively.
Overall, the model responses are more precise if MAPE and R
are found to be close to 0 and 1, respectively.
N
i a
af
L
LL
NMAPE
1
1 (1)
2
1
2
1
2
1
)(
)()(
N
i
af
N
i
af
N
i
af
LL
LLLL
R (2)
where: N = Number of observations
Lf = Forecasted load (MW)
La = Actual load (MW)
Each model will be checked by two types of error to
guarantee the maximum accuracy and to ensure that the
forecasted load is near as possible to the actual load. This will
add more complications to the problem but in the same time it
adds more guarantee for the forecasting accuracy. Table II lists
MAPE and R for hourly loads of years between 1988 and 2006
for linear regression and neural network models. Comparing
the average MAPE and R for daily loads of years between
1988 and 2006, it was found that these values are less in case
of neural network than those resulting from linear regression
method.
VI. ELECTRIC LOAD FORECASTING
One of the primary tasks of an electric utility is to accurately
predict load requirements at all times. Results obtained from
load forecasting process are used in planning and operation.
Neural Network can learn to approximate any function just
by using example data that is representative of the desired task.
They are model free estimators, which are capable of solving
complex problem based on the presentation of a large number
of training data. Neural Networks estimate a function without
mathematical description of how the outputs functionally
depend on the inputs. They represent a good approach that is
potentially robust and fault tolerant. In this work, an electric
forecasting method based on neural network integrated with
simple linear regression model was implemented using
MATLAB. The system performs better results than some other
systems. The accuracy can further be improved if we take
more than one factor (calendar, temperature, humidity and
random factors) as input, which is large enough to incorporate
all the effects which can be quantified.
REFERENCES
[1] E. Almeshaiei, H. Soltan, “A methodology for Electric Power Load
Forecasting”, Alexandria Engineering Journal, vol. 50, pp. 137–144,
2011.
[2] Ü. B. Filik, Ö. N. Gerek, M. Kurban, “A novel modeling approach for
hourly forecasting of long-term electric energy demand”, Energy
Conversion and Management, vol. 52, pp. 199–211, 2011.
[3] T. Hill, M. O’Connor, W. Remus, “Neural networks models for time
series forecasts”, Manage. Sci. pp. 1082–1092, 1996.
[4] N. Amjady, “Short-term hourly load forecasting using time series
modeling with peak load estimation capability”, IEEE Trans. Power
Syst., vol. 16, pp. 798–805, 2001.
[5] G. D. Irisarri, S. E. Widergren, P. D. Yehsakul, “On-line load
forecasting for energy control center application”, IEEE Trans. Power
Appar. Syst., vol. 101, pp. 71–78, 1982.
TABLE II
MAPE AND R FOR HOURLY LOADS OF YEARS BETWEEN 1988 AND 2006 IN
CASE OF LINEAR REGRESSION MODEL.
Year MAPE R
Reg. NN % Imp. Reg. NN % Imp.
1988 14.32 2.44 82.97 0.88 0.94 5.88
1989 14.35 3.38 76.47 0.88 0.95 7.76
1990 14.01 3.11 77.81 0.88 0.94 5.67
1991 14.03 3.28 76.64 0.88 0.94 5.76
1992 13.92 3.14 77.42 0.89 0.94 5.54
1993 13.39 3.33 75.10 0.90 0.95 5.39
1994 13.38 5.06 62.19 0.90 0.93 3.54
1995 13.04 4.13 68.31 0.91 0.95 4.84
1996 12.59 4.15 67.02 0.91 0.93 2.15
1997 12.41 4.92 60.37 0.92 0.93 1.08
1998 12.12 3.89 67.93 0.92 0.93 0.97
1999 12.13 5.27 56.56 0.92 0.88 -4.42
2000 12.62 4.94 60.87 0.92 0.91 -0.22
2001 11.98 4.58 61.80 0.92 0.93 1.71
2002 12.14 4.57 62.37 0.91 0.94 2.46
2003 12.15 5.89 51.58 0.91 0.95 4.41
2004 12.09 5.37 55.55 0.91 0.94 2.46
2005 11.58 7.58 34.55 0.91 0.96 5.40
2006 11.84 8.04 32.14 0.92 0.95 3.88
Ave. 12.85 4.58 63.56 0.90 0.94 3.38
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
64
[6] S. Rahman, O. Hazim, “Load forecasting for multiple sites:
Development of an expert system-based technique”, Electr. Power Syst.
Res., vol. 39, pp. 161–169, 1996.
[7] N. Kandil, R. Wamkeue, M. Saad, S. Georges, “An efficient approach
for short-term load forecasting using artificial neural networks”, Electr.
Power Energy Syst., vol. 28, pp. 525–530, 2006.
[8] Y. Cai, J.-Z. Wang, Y. Tang, Y.-C. Yang, “An efficient approach for
electric load forecasting using distributed ART (adaptive resonance
theory) & HS-ARTMAP (Hyper-spherical ARTMAP network) neural
network”, Energy, vol. 36, pp. 1340-1350, 2011.
[9] W.-M. Lin, H.-J. Gowa, M.-T. Tsai, “An enhanced radial basis function
network for short-term electricity price forecasting”, Applied Energy,
vol. 87, pp. 3226–3234, 2010.
[10] X. Yang, J. Yuan, J. Yuan, H. Mao, “An improved WM method based
on PSO for electric load forecasting”, Expert Systems with Applications,
vol. 37, pp. 8036–8041, 2010.
[11] A. G. Bakirtzis, J. B. Theocharis, S. J. Kiartzis, K. J. Satsois, “Short
term load forecasting using fuzzy neural networks”, IEEE Trans. Power
Syst., vol. 10(3), pp. 1518–1524, 1995.
[12] P. Lauret, E. Fock, R. N. Randrianarivony, J.-F. M. Ramsamy,
“Bayesian neural network approach to short time load forecasting”,
Energy Convers. Manage, vol. 49, no. 5, pp. 1156–1166, 2008.
[13] M. R. Amin-Naseri, A. R. Soroush, “Combined use of unsupervised and
supervised learning for daily peak load forecasting”, Energy Convers.
Manage, vol. 49, no. 6, pp. 1302–1308, 2008.
[14] N. Tai, J. Stenzel, H. Wu, “Techniques of applying wavelet transform
into combined model for short-term load forecasting”, Electr. Power
Syst. Res., vol. 76, pp. 525–533, 2006.
[15] W.-C. Hong, “Application of chaotic ant swarm optimization in electric
load forecasting”, Energy Policy, vol. 38, pp. 5830–5839, 2010.
[16] Z. Xiaoxing, S. Caixin, “Dynamic intelligent cleaning model of dirty
electric load data”, Energy Conversion and Management, vol. 49, pp.
564–569, 2008.
[17] E. H. Barakat, “Modeling of nonstationary time-series data. Part II.
Dynamic periodic trends”, Electr. Power Energy Syst., vol. 23, pp. 63–
68, 2001.
[18] M. Ghiassi, D. K. Zimbra, H. Saidane, “Medium term system load
forecasting with a dynamic artificial neural network model”, Electric
Power Systems Research, vol. 76, pp. 302–316, 2006.
[19] E. González-Romera, M. A. Jaramillo-Morán, D. Carmona-Fernández,
“Monthly electric energy demand forecasting with neural networks and
Fourier series”, Energy Convers. Manage, vol. 49, pp. 3135–3142,
2008.
[20] N. Abu-Shikhah, F. Elkarmi, “Medium-term electric load forecasting
using singular value decomposition”, Energy, vol. 36, pp. 4259-4271,
2011.
[21] D. J. Pedregal, J. R. Trapero, “Mid-term hourly electricity forecasting
based on a multi-rate approach”, Energy Conversion and Management,
vol. 51, pp. 105–111, 2010.
[22] H. L. Wills, H. N. Tram, “Load forecasting for transmission planning”,
IEEE Trans. Power Syst., vol. 103, pp. 561–568, 1984.
[23] G. P. Alexander, O. Esmaeil, J. Muthusami, A. D. Patton, A. F. Atiya,
“Development of an intelligent long-term electric load forecasting
systems”, IEEE Trans. Power Syst., vol. 11, no. 2, pp. 858–863, 1996.
[24] K. Padmakumari, K. P. Mohandas, S. Thiruvengadam, “Long term
distribution demand forecasting using neuro fuzzy computations”,
Electr. Power Energy Syst., vol. 21, pp. 315–322, 1999.
[25] N. X. Jia, R. Yokoyama, Y. C. Zhou, Z. Y. Gao, “A flexible long-term
load forecasting approach based on new dynamic simulation theory –
GSIM”, Electr. Power Energy Syst., vol. 23, pp. 549–556, 2001.
[26] O. A. S. Carpinteiro, R. C. Leme, A. C. Z. Souza, C. A. M. Pinheiroa, E.
M. Moreira, “Long-term load forecasting via a hierarchical neural model
with time integrators”, Electr. Power Syst. Res., vol. 77, pp. 371–378,
2007.
[27] W. C. Hong, “Electric load forecasting by support vector model”, Appl.
Math. Model, vol. 33, pp. 2444–2454, 2009.
[28] A. A. Abou El-Ela, A. A. El-Zeftawy, S. M. Allam, G. M. Atta, “An
optimization planning technique for Suez Canal Network in Egypt”,
Electric Power Systems Research, vol. 80, pp. 196–203, 2010.
Saeed M. Badran joined the Department of
Electrical Engineering, Faculty of Engineering,
Albaha University, Albaha, KSA in 2009. He is
working as the dean Graduate Studies, Albaha
University and the dean of faculty of
engineering at the same university. Dr. Badran
graduated from the Electrical Engineering
Department of Bridgeport University,
Connecticut State, USA with B.Sc. in 1982. He
graduated from the Electrical Engineering
Department of Bridgeport University,
Connecticut State, with M.Sc. M.Sc. in 1983
and from the Biomedical Engineering and Systems Department, Toledo
University, Ohio state, with M.Sc. in 1986. He moved to West Virginia
University in USA and obtained his Ph.D. in Electrical Engineering in 1990..
In 1403 H, he joined Faculty of Applied Science and Engineering,
University of Umm Al-Qura, Makkah as a lecturer. Therefore, he joined again
to West Virginia University in USA as an assistant research in 1988-1989. He
worked in Electrical and Computer Engineering, University of Umm Al-Qura,
Makkah, in 1411 H. Dr. Badran joined King Fahd University of Petroleum &
Minerals as a visitor Professor in 1416 H – 1418 H. In 1997, he worked as a
consultant at Aramco, KSA.
Dr. Badran came back to Electrical Engineering and Computer
Department, University of Umm Al-Qura as an associate professor in 1420H
and head of the department from 1420H to 1422 H. He was at Putra
University, Malaysia, as a visitor Professor from 1429 H to 1430 H.
Ossama B. Abouelatta joined the Department
of Mechanical Engineering, Faculty of
Engineering, Albaha University, Albaha, KSA
in 2008. He graduated from the Production
Engineering and Mechanical Design
Department of Mansoura University with B.Sc.
and M.Sc. in 1986 and 1991, respectively. He
moved to Czech Technical University in Prague
(Czech Republic) in March 1996 and obtained
his Ph.D. in Manufacturing Engineering in
2000. In 1999, he joined Center for Precision
Technologies, University of Huddersfield, UK
as a visiting scholar, where he was responsible
for the extraction of critical points of the
surface topography..
He joined Production Engineering and Mechanical Design Department,
Faculty of Engineering, Mansoura University, Egypt as an demonstrator in
1986, as an assistant lecturer in 1992, as an assistant professor in 2000 and
finally as an associate professor in 2006. In 2007, he joined the Higher Delta
Institute for Engineering and Technology, Mansoura, Egypt. He taught many
under- and post-graduate mechanical engineering courses as metrology,
measurements, computer application and simulation, and manufacturing
engineering.
Dr. Abouelatta published more than sixty papers in refereed journals and
conferences. His present research interests include, surface characterization,
computer aided measurements and simulation, and biomedical applications
and measurements. He is a member of the International Committee on
Measurements and Instrumentation (ICMI) and an International Scientific
Committee of the International Symposium on Measurement Technology and
Intelligent Instruments (ISMTII) conference.
International Conference on Electrical, Electronics and Biomedical Engineering (ICEEBE'2012) Penang (Malaysia) May 19-20, 2012
65