SlideShare ist ein Scribd-Unternehmen logo
1 von 4
Downloaden Sie, um offline zu lesen
Ankita Shrivastava et al Int. Journal of Engineering Research and Application
ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527

RESEARCH ARTICLE

www.ijera.com

OPEN ACCESS

Short- Term Load Forecasting Using Artificial Neural Network
Techniques
Ankita Shrivastava1 and Arti Bhandakkar2
1(
2(

PG Scholar, Department of Electrical & Electronics Engineering, SRIT, Jabalpur)
Associate Professor, Department of Electrical & Electronics Engineering, SRIT, Jabalpur)

ABSTRACT
This paper proposes a neural network approach for forecasting short- term loads. Three ANN- techniques –
Radial Basis Function Neural Network, Feed forward Neural Network and Cascade- Forward Neural Network
are discussed in this paper. Their performances are evaluated through a simulation study. Historical Load Data
from the Load Dispatch Centre Jabalpur are used for training, testing and showing the good performance of the
proposed method. The proposed model can forecast the load profile with a lead time of one to seven days.
Keywords- Artificial Intelligence, Artificial Neural Network, Back-Propagation, Load Forecasting, Power
Quality.

I.

INTRODUCTION

Load Forecasting is an important component
for power system energy management system. Load
forecasting means predicting the future load with the
help of historical load data available. It is very
important for the planning, operation and control of
power system. It plays a vital role in the deregulated
electric industry [1].
A good forecast reflects current and future
trends in the power system. The accuracy of a forecast
is crucial to any electric utility. That is why, accurate
models for load forecasting are essential for the
operation and planning of a utility company [2].
Since in power system the next day’s power
generation must be scheduled every day, day- ahead
short- term load forecasting (STLF) is a necessary
daily task for power dispatch. Its accuracy affects the
economic operation and reliability of the system
greatly [3].
Short- term load forecasts helps in estimating
the load flows. This helps in making decisions that can
prevent overloading and the result deeply influence
the power systems’ safety and economy [4].
The short- term forecasts are not only needed for
control and scheduling of power system but also used
as inputs to load flow study or contingency analysis
i.e. for load management program. The short term
forecasting is also primarily used for the generation
dispatch, capacitor switching, feeder reconfiguration,
voltage control, and automatic generation control
(AGC) [5].
A little increase in the percentages of shortterm prediction accuracy may bring many benefits in
terms of economy and reliability of power system.
Therefore, precise short- term load forecasting not
only enhances the reliability of power supply but also
increases economic benefits [6].

www.ijera.com

The research work in this area is still a challenge to
the electrical engineering scholars because of its high
complexity. How to estimate the future load with the
historical data has remained a difficulty up to now,
especially for the load forecasting of holidays, days
with extreme weather and other anomalous days. But
with the recent development of new mathematical and
artificial intelligence tools, it is potentially possible to
improve the forecasting results [7].
Load Forecasting can be performed using
many techniques such as similar day approach,
various regression models, time series, statistical
methods, fuzzy logic, artificial neural networks, expert
systems, etc. But application of artificial neural
network in the areas of forecasting has made it
possible to overcome the limitations of the other
methods mentioned above used for electrical load
forecasting [8].

II.

ARTIFICIAL NEURAL NETWORK

Neural networks are essentially non-linear
circuits that have the demonstrated capability to do
non-linear curve fitting. The outputs of an artificial
neural network are some linear or non-linear
mathematical function of its inputs [9].
ANN is usually formed from many hundreds
or thousands of simple processing units, connected in
parallel and feeding forward in several layers. Because
of the fast and inexpensive personal computers
availability, the interest in ANN’s has blossomed in
the current digital world. The basic motive of the
development of the ANN is to make the computers do
what a human being cannot do. The three-layer fully
connected feed-forward neural network which is
generally used for load forecasting. It comprises of an
input layer, one hidden layer and an output layer.
Signal system is allowed only from the input layer to
the hidden layer and from the hidden layer to the
1524 | P a g e
Ankita Shrivastava et al Int. Journal of Engineering Research and Application
ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527

www.ijera.com

output layer. Input variables come from historical
data, which are date, hour of the day, past system load,
temperature and humidity, corresponding tothe factors
that affect the load. The outputs are the forecasting
results. The number of inputs, the number of hidden
nodes, transfer functions, scaling schemes, and
training methods affect the forecasting performance
and, hence, need to be chosen carefully [10].
In applying a neural network to load forecasting,
one must select one of a number of architectures (e.g.
Hopfield, back propagation, Boltzmann machine), the
number and connectivity of layers and elements, use
of bi-directional or uni-directional links and the
number format (e.g. binary or continuous) to be used
by inputs and outputs.
Figure 2: Architecture of Radial Basis Function
Network
The input of a RBF network can be modelled
as a vector of real numbers
. The output of
the network is then a scalar function of the input
vector,

Figure 1: Structure of ANN
This is the structure of ANN. There are three
layers namely, input layer, hidden layer and output
layer.

, and is given by

Also,
And,

Where,

III.

NEURAL NETWORK TRAINING
AND TESTING

In this section three types of neural network
architectures are presented for short term load
forecasting.
1.

Radial Basis Function Network
A radial basis function network is an artificial
neural
network that
uses radial
basis
functions as activation functions. Radial basis function
(RBF) networks typically have three layers: an input
layer, a hidden layer with a non-linear RBF activation
function and a linear output layer.
The diagram below shows the radial basis function
neural network architecture with input x and output y.
The weights are so adjusted to give the targeted output
as needed by the system.

www.ijera.com

N = the number of neurons in the hidden layer
=the center vector for neuron i
= the weight of neuron i in the linear output
neuron.
The parameters
,
,
are determined in a
manner that optimizes the fit between
and the data
[11].
2.

Feed forward back-propagation (FB) Neural
Network
Feed-forward BP Network consists of input,
hidden and output layers. In a feed forward network
information always moves in one direction; it never
goes backwards. Back-propagation learning algorithm
was used for training these networks. During training,
calculations are carried out from input layer towards
the output layer, and error values are fed back to the
previous layer [12]. The most popular artificial neural
network architecture for load forecasting is back
propagation. This network uses continuously valued
functions and supervised learning. That is, under
supervised learning, the actual numerical weights
assigned to element inputs are determined by
matching historical data (such as time and weather) to
desired outputs (such as historical loads).

1525 | P a g e
Ankita Shrivastava et al Int. Journal of Engineering Research and Application
ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527

www.ijera.com

Tan-sigmoid transfer function was used to
reach the optimized status. The performance of
cascade forward back propagation and feed forward
back propagation were evaluated using Mean Square
Error (MSE) [13].
2

IV.

RESULTS AND DISCUSSIONS

The acceptable criteria for a particular model
is based upon the
i.
Mean Square Error (MSE)
ii.
Training Time
iii.
Detection Time
Figure 3: Architecture of Feed forward BackPropagation Network
Feed forward networks often have one or
more hidden layers of sigmoid neurons followed by an
output layer of linear neurons. Multiple layers of
neurons with nonlinear transfer functions allow the
network to learn nonlinear and linear relationships
between input and output vectors. The linear output
layer lets the network produce values outside the
range –1 to +1. On the other hand, outputs of a
network such as between 0 and 1 are produced, then
the output layer should use a sigmoid transfer function
(tansig) [13].
Cascade Forward Back propagation Network
Cascade forward back propagation model is
similar to feed-forward networks, but include a weight
connection from the input to each layer and from each
layer to the successive layers. While two- layer feedforward networks can potentially learn virtually any
input-output relationship, feed-forward networks with
more layers might learn complex relationships more
quickly. The function newcf creates cascade-forward
networks .
Cascade forward back propagation ANN
model is similar to feed forward back propagation
neural network in using the back propagation
algorithm for weights updating, but the main nature of
this network is that each layer of neurons is related to
all previous layer of neurons. For example, a three
layer network has connections from layer 1 to layer 2,
layer 2 to layer 3, and layer 1 to layer 3. The threelayer network also has connections from the input to
all three layers [12].

1. Performance of RBF Network
Training with RBF network for 98 epochs
taking goal=0.01 and spread=1 gives good
performance in terms of MSE(mean square error)
equal to 1.62.

3.

Figure 5: Performance of RBF Neural Network
Here MSE= 1.62, Training Time= 1.5744 and
Detection Time= 0.0175.
2. Performance of FBPNN
For different numbers of neurons the system
has been trained and tested but the exact forecast is
obtained for 12,12 neurons.

Figure 6: Performance of FBPNN
Here MSE= 1.7032e+004, Training Time=
2.4981 and Detection Time= 0.0206.
3.

Figure 4: Architecture of Cascade forward BackPropagation Network
www.ijera.com

Performance of Cascade Forward BP
Network
For different numbers of neurons the system
has been trained and tested but we get the exact
forecast for 15, 15 neurons.
1526 | P a g e
Ankita Shrivastava et al Int. Journal of Engineering Research and Application
ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527

[6]

[7]

[8]
Figure 7: Performance of CF-BP Network
Here MSE = 3.2392e+004, Training Time =
15.5890 and Detection Time = 0.0254.

V.

CONCLUSIONS

The result of the three neural network models
(RBFNN, FFBPNN, CFBPNN) used for short term
load forecast for Jabalpur region, shows that the
networks has good performances and
accurate
prediction is achieved. Its forecasting reliabilities were
evaluated by computing the mean square error (MSE)
between the exact and predicted values.
The results suggest that ANN model with the
developed structure can perform good prediction with
least error and finally this neural network could be an
important tool for short term load forecasting as well
as this work incorporates additional information such
as Hour of the Day, Days of the month, and different
weather conditions into the network so as to obtain a
more representative forecast of future load.

REFERENCES
[1]

[2]

[3]

[4]

[5]

Hong Chen, Claudio A. Canizares, Ajit
Singh, “ANN- based Short- Term Load
Forecasting
in
Electricity
Markets”,
University of Waterloo, Canada
Sanjib Mishra, Sarat Kumar Patra, “Short
Term Load Forecasting using a Neural
Network trained by A Hybrid Artificial
Immune System”, 2008 IEEE Region 10
Colloquium and the Third International
Conference on Industrial and Information
Systems, Kharagpur, India December 8- 10,
2008
J.P.S. Catalao, S.J.P.S. Mariano, V.M.F.
Mendes, L.A.F.M. Ferreira, “Short Term
electricity prices forecasting in a competitive
market: A neural network approach”,
ScienceDirect, Electric Power Systems
Research 77 (2007) 1297- 1304
Ajay Gupta, Pradeepta K. Sarangi, “Electrcal
Load Forecasting Using Genetic Algorithm
Based Back- Propagation Method”, ARPN
Journal of Engineering and Applied Sciences,
vol. 7, no.8, August 2012
Shu Fan, Yuan- Kang Wu, Wei- Jen Lee,
Ching- Yin Lee, ”Comparative Study on
Load Forecasting Technologies for Different

www.ijera.com

[9]

[10]

[11]
[12]

[13]

www.ijera.com

Geographical Distributed Loads”, proc of
IEEE 2011
Eugene A. Feinberg, Dora Genethliou, State
University of New York, Stony Brook,
“Chapter 12 LOAD FORECASTING”
K.Y. Lee, Y.T. Cha, J.H. Park, “Short- Term
Load Forecasting Using an Artificial Neural
Network”, Transactions on Power Systems,
vol. 7, No. 1, February 1992
Muhammad Buhari, Sanusi Sani Adamu,
“Short-Term Load Forecasting Using
Artificial Neural Network”, Proc. of the
International MultiConference of Engineers
and Computer Scientists 2012 Vol I, IMECS
2012, March 14- 16,2012, Hong Kong
Gautham P. Das, Chandrasekar S., Piyush
Chandra Ojha, “ Artificial Neural Network
Based Short Term Load Forecasting for the
Distribution Utilities” Kalki Communication
Technologies
Ltd.
Available
at
www.kalkitech.com
Fatemeh Mosalman, Alireza Mosalman, H.
Mosalman Yazdi, M. Mosalman Yazdi, “One
day- ahead load forecasting by artificial
neural network”, Scientific Research and
Essays Vol. 6 (13), pp. 2795- 2799, 4 July,
2011.
Available
at
www.academicjournals.org/SRE
http://en.wikipedia.org/RadialBasisFunction
(accessed on 28.9.2013).
H.Demuth, M. Beale and M.Hagan. “Neural
Network Toolbox User‟s Guide”. The
MathWorks, Inc., Natrick, USA. 2009
Dheeraj S. Badde, Anil k. Gupta, Vinayak K.
Patki, “Cascade and Feed Forward Back
propagation Artificial Neural Network
Models for Prediction of Compressive
Strength of Ready Mix Concrete”, IOSR
Journal of Mechanical and Civil Engineering
(IOSR-JMCE) ISSN: 2278-1684, PP: 01-06
www.iosrjournals.org Second

1527 | P a g e

Weitere ähnliche Inhalte

Was ist angesagt?

Short term load forecasting using hybrid neuro wavelet model
Short term load forecasting using hybrid neuro  wavelet modelShort term load forecasting using hybrid neuro  wavelet model
Short term load forecasting using hybrid neuro wavelet modelIAEME Publication
 
Design and implementation a prototype system for fusion image by using SWT-PC...
Design and implementation a prototype system for fusion image by using SWT-PC...Design and implementation a prototype system for fusion image by using SWT-PC...
Design and implementation a prototype system for fusion image by using SWT-PC...IJECEIAES
 
Neural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesNeural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesJonathan D'Cruz
 
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...Cemal Ardil
 
Energy aware clustering protocol (eacp)
Energy aware clustering protocol (eacp)Energy aware clustering protocol (eacp)
Energy aware clustering protocol (eacp)IJCNCJournal
 
A review on energy efficient clustering routing
A review on energy efficient clustering routingA review on energy efficient clustering routing
A review on energy efficient clustering routingeSAT Publishing House
 
1.meena tushir finalpaper-1-12
1.meena tushir finalpaper-1-121.meena tushir finalpaper-1-12
1.meena tushir finalpaper-1-12Alexander Decker
 
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...Editor IJCATR
 
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkPresentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkArzam Muzaffar Kotriwala
 
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...Novel approach for hybrid MAC scheme for balanced energy and transmission in ...
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...IJECEIAES
 
IRJET- Chaos based Secured Communication in Energy Efficient Wireless Sensor...
IRJET-	 Chaos based Secured Communication in Energy Efficient Wireless Sensor...IRJET-	 Chaos based Secured Communication in Energy Efficient Wireless Sensor...
IRJET- Chaos based Secured Communication in Energy Efficient Wireless Sensor...IRJET Journal
 
An Adaptive Cluster Based Routing Protocol for WSN
An Adaptive Cluster Based Routing Protocol for WSNAn Adaptive Cluster Based Routing Protocol for WSN
An Adaptive Cluster Based Routing Protocol for WSNEswar Publications
 
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...Editor IJCATR
 

Was ist angesagt? (17)

Short term load forecasting using hybrid neuro wavelet model
Short term load forecasting using hybrid neuro  wavelet modelShort term load forecasting using hybrid neuro  wavelet model
Short term load forecasting using hybrid neuro wavelet model
 
Design and implementation a prototype system for fusion image by using SWT-PC...
Design and implementation a prototype system for fusion image by using SWT-PC...Design and implementation a prototype system for fusion image by using SWT-PC...
Design and implementation a prototype system for fusion image by using SWT-PC...
 
G013124354
G013124354G013124354
G013124354
 
Neural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesNeural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variables
 
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...
A multi-layer-artificial-neural-network-architecture-design-for-load-forecast...
 
E010323842
E010323842E010323842
E010323842
 
Energy aware clustering protocol (eacp)
Energy aware clustering protocol (eacp)Energy aware clustering protocol (eacp)
Energy aware clustering protocol (eacp)
 
A review on energy efficient clustering routing
A review on energy efficient clustering routingA review on energy efficient clustering routing
A review on energy efficient clustering routing
 
1.meena tushir finalpaper-1-12
1.meena tushir finalpaper-1-121.meena tushir finalpaper-1-12
1.meena tushir finalpaper-1-12
 
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...
An Adaptive Energy Aware Clustering Based Reliable Routing for in-Network Agg...
 
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkPresentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
 
G018134149
G018134149G018134149
G018134149
 
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...Novel approach for hybrid MAC scheme for balanced energy and transmission in ...
Novel approach for hybrid MAC scheme for balanced energy and transmission in ...
 
IRJET- Chaos based Secured Communication in Energy Efficient Wireless Sensor...
IRJET-	 Chaos based Secured Communication in Energy Efficient Wireless Sensor...IRJET-	 Chaos based Secured Communication in Energy Efficient Wireless Sensor...
IRJET- Chaos based Secured Communication in Energy Efficient Wireless Sensor...
 
An Adaptive Cluster Based Routing Protocol for WSN
An Adaptive Cluster Based Routing Protocol for WSNAn Adaptive Cluster Based Routing Protocol for WSN
An Adaptive Cluster Based Routing Protocol for WSN
 
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...
An Improved Energy Efficient Wireless Sensor Networks Through Clustering In C...
 
1909 1913
1909 19131909 1913
1909 1913
 

Andere mochten auch

JustinHoltResume2014 (1)
JustinHoltResume2014 (1)JustinHoltResume2014 (1)
JustinHoltResume2014 (1)Justin Holt
 
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_FinalGuillermo (Bill/Gil) Echeverria
 
How I learned to stop fucking and love MarionetteJS
How I learned to stop fucking and love MarionetteJSHow I learned to stop fucking and love MarionetteJS
How I learned to stop fucking and love MarionetteJSKamol Treewatchararat
 
3 pasos para implementar mapas mentales en tu lectura
3 pasos para implementar mapas mentales en tu lectura3 pasos para implementar mapas mentales en tu lectura
3 pasos para implementar mapas mentales en tu lecturaJhosi Deyay Yaranga
 
Soneither
Soneither Soneither
Soneither Papraiz
 
Aprendizaje significativo
Aprendizaje significativoAprendizaje significativo
Aprendizaje significativoKatherin Lemus
 
Versi office apa yang saya gunakan
Versi office apa yang saya gunakanVersi office apa yang saya gunakan
Versi office apa yang saya gunakanAhmad Ibrahim
 
J055即刻「資」援─學習資源「e」網通
J055即刻「資」援─學習資源「e」網通J055即刻「資」援─學習資源「e」網通
J055即刻「資」援─學習資源「e」網通moby moby
 

Andere mochten auch (20)

Iw3515281533
Iw3515281533Iw3515281533
Iw3515281533
 
Ja3515591563
Ja3515591563Ja3515591563
Ja3515591563
 
Ix3515341540
Ix3515341540Ix3515341540
Ix3515341540
 
Jg3515961599
Jg3515961599Jg3515961599
Jg3515961599
 
Is3515091514
Is3515091514Is3515091514
Is3515091514
 
Jf3515881595
Jf3515881595Jf3515881595
Jf3515881595
 
Jd3515761580
Jd3515761580Jd3515761580
Jd3515761580
 
Iy3515411552
Iy3515411552Iy3515411552
Iy3515411552
 
Jb3515641568
Jb3515641568Jb3515641568
Jb3515641568
 
Iz3515531558
Iz3515531558Iz3515531558
Iz3515531558
 
Jc3515691575
Jc3515691575Jc3515691575
Jc3515691575
 
JustinHoltResume2014 (1)
JustinHoltResume2014 (1)JustinHoltResume2014 (1)
JustinHoltResume2014 (1)
 
Water
WaterWater
Water
 
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final
20150114_Jan 14 Board Work Session Pre-Read -why process improvement_Final
 
How I learned to stop fucking and love MarionetteJS
How I learned to stop fucking and love MarionetteJSHow I learned to stop fucking and love MarionetteJS
How I learned to stop fucking and love MarionetteJS
 
3 pasos para implementar mapas mentales en tu lectura
3 pasos para implementar mapas mentales en tu lectura3 pasos para implementar mapas mentales en tu lectura
3 pasos para implementar mapas mentales en tu lectura
 
Soneither
Soneither Soneither
Soneither
 
Aprendizaje significativo
Aprendizaje significativoAprendizaje significativo
Aprendizaje significativo
 
Versi office apa yang saya gunakan
Versi office apa yang saya gunakanVersi office apa yang saya gunakan
Versi office apa yang saya gunakan
 
J055即刻「資」援─學習資源「e」網通
J055即刻「資」援─學習資源「e」網通J055即刻「資」援─學習資源「e」網通
J055即刻「資」援─學習資源「e」網通
 

Ähnlich wie Iv3515241527

Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Cemal Ardil
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
 
Medium term load demand forecast of Kano zone using neural network algorithms
Medium term load demand forecast of Kano zone using neural network algorithmsMedium term load demand forecast of Kano zone using neural network algorithms
Medium term load demand forecast of Kano zone using neural network algorithmsTELKOMNIKA JOURNAL
 
Artificial Neural Network Based Load Forecasting
Artificial Neural Network Based Load ForecastingArtificial Neural Network Based Load Forecasting
Artificial Neural Network Based Load ForecastingIRJET Journal
 
IRJET- Three Phase Line Fault Detection using Artificial Neural Network
IRJET- Three Phase Line Fault Detection using Artificial Neural NetworkIRJET- Three Phase Line Fault Detection using Artificial Neural Network
IRJET- Three Phase Line Fault Detection using Artificial Neural NetworkIRJET Journal
 
Prediction of Extreme Wind Speed Using Artificial Neural Network Approach
Prediction of Extreme Wind Speed Using Artificial Neural  Network ApproachPrediction of Extreme Wind Speed Using Artificial Neural  Network Approach
Prediction of Extreme Wind Speed Using Artificial Neural Network ApproachScientific Review SR
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS cscpconf
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKSAUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKScsandit
 
Auto mobile vehicle direction in road traffic using artificial neural networks
Auto mobile vehicle direction in road traffic using artificial neural networksAuto mobile vehicle direction in road traffic using artificial neural networks
Auto mobile vehicle direction in road traffic using artificial neural networkscsandit
 
A survey research summary on neural networks
A survey research summary on neural networksA survey research summary on neural networks
A survey research summary on neural networkseSAT Publishing House
 
Intelligent methods in load forecasting
Intelligent methods in load forecastingIntelligent methods in load forecasting
Intelligent methods in load forecastingprj_publication
 
Solar Irradiance Prediction using Neural Model
Solar Irradiance Prediction using Neural ModelSolar Irradiance Prediction using Neural Model
Solar Irradiance Prediction using Neural ModelDr. Amarjeet Singh
 
Efficiency of Neural Networks Study in the Design of Trusses
Efficiency of Neural Networks Study in the Design of TrussesEfficiency of Neural Networks Study in the Design of Trusses
Efficiency of Neural Networks Study in the Design of TrussesIRJET Journal
 
A SURVEY RESEARCH SUMMARY ON NEURAL NETWORKS
A SURVEY  RESEARCH SUMMARY ON NEURAL NETWORKSA SURVEY  RESEARCH SUMMARY ON NEURAL NETWORKS
A SURVEY RESEARCH SUMMARY ON NEURAL NETWORKSPedro Craggett
 
Distance protection scheme for transmission line using back propagation neura...
Distance protection scheme for transmission line using back propagation neura...Distance protection scheme for transmission line using back propagation neura...
Distance protection scheme for transmission line using back propagation neura...eSAT Publishing House
 
Implementation of recurrent neural network for the forecasting of USD buy ra...
Implementation of recurrent neural network for the forecasting  of USD buy ra...Implementation of recurrent neural network for the forecasting  of USD buy ra...
Implementation of recurrent neural network for the forecasting of USD buy ra...IJECEIAES
 

Ähnlich wie Iv3515241527 (20)

Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
 
Y4502158163
Y4502158163Y4502158163
Y4502158163
 
Medium term load demand forecast of Kano zone using neural network algorithms
Medium term load demand forecast of Kano zone using neural network algorithmsMedium term load demand forecast of Kano zone using neural network algorithms
Medium term load demand forecast of Kano zone using neural network algorithms
 
Artificial Neural Network Based Load Forecasting
Artificial Neural Network Based Load ForecastingArtificial Neural Network Based Load Forecasting
Artificial Neural Network Based Load Forecasting
 
IRJET- Three Phase Line Fault Detection using Artificial Neural Network
IRJET- Three Phase Line Fault Detection using Artificial Neural NetworkIRJET- Three Phase Line Fault Detection using Artificial Neural Network
IRJET- Three Phase Line Fault Detection using Artificial Neural Network
 
Prediction of Extreme Wind Speed Using Artificial Neural Network Approach
Prediction of Extreme Wind Speed Using Artificial Neural  Network ApproachPrediction of Extreme Wind Speed Using Artificial Neural  Network Approach
Prediction of Extreme Wind Speed Using Artificial Neural Network Approach
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKSAUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS
 
Auto mobile vehicle direction in road traffic using artificial neural networks
Auto mobile vehicle direction in road traffic using artificial neural networksAuto mobile vehicle direction in road traffic using artificial neural networks
Auto mobile vehicle direction in road traffic using artificial neural networks
 
A survey research summary on neural networks
A survey research summary on neural networksA survey research summary on neural networks
A survey research summary on neural networks
 
Intelligent methods in load forecasting
Intelligent methods in load forecastingIntelligent methods in load forecasting
Intelligent methods in load forecasting
 
Solar Irradiance Prediction using Neural Model
Solar Irradiance Prediction using Neural ModelSolar Irradiance Prediction using Neural Model
Solar Irradiance Prediction using Neural Model
 
Efficiency of Neural Networks Study in the Design of Trusses
Efficiency of Neural Networks Study in the Design of TrussesEfficiency of Neural Networks Study in the Design of Trusses
Efficiency of Neural Networks Study in the Design of Trusses
 
A SURVEY RESEARCH SUMMARY ON NEURAL NETWORKS
A SURVEY  RESEARCH SUMMARY ON NEURAL NETWORKSA SURVEY  RESEARCH SUMMARY ON NEURAL NETWORKS
A SURVEY RESEARCH SUMMARY ON NEURAL NETWORKS
 
Distance protection scheme for transmission line using back propagation neura...
Distance protection scheme for transmission line using back propagation neura...Distance protection scheme for transmission line using back propagation neura...
Distance protection scheme for transmission line using back propagation neura...
 
Implementation of recurrent neural network for the forecasting of USD buy ra...
Implementation of recurrent neural network for the forecasting  of USD buy ra...Implementation of recurrent neural network for the forecasting  of USD buy ra...
Implementation of recurrent neural network for the forecasting of USD buy ra...
 
N020698101
N020698101N020698101
N020698101
 

Kürzlich hochgeladen

Building Your Own AI Instance (TBLC AI )
Building Your Own AI Instance (TBLC AI )Building Your Own AI Instance (TBLC AI )
Building Your Own AI Instance (TBLC AI )Brian Pichman
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1DianaGray10
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Will Schroeder
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Adtran
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarPrecisely
 
20230202 - Introduction to tis-py
20230202 - Introduction to tis-py20230202 - Introduction to tis-py
20230202 - Introduction to tis-pyJamie (Taka) Wang
 
COMPUTER 10: Lesson 7 - File Storage and Online Collaboration
COMPUTER 10: Lesson 7 - File Storage and Online CollaborationCOMPUTER 10: Lesson 7 - File Storage and Online Collaboration
COMPUTER 10: Lesson 7 - File Storage and Online Collaborationbruanjhuli
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024D Cloud Solutions
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?IES VE
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxGDSC PJATK
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfinfogdgmi
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6DianaGray10
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioChristian Posta
 
Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024SkyPlanner
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UbiTrack UK
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdfPedro Manuel
 

Kürzlich hochgeladen (20)

Building Your Own AI Instance (TBLC AI )
Building Your Own AI Instance (TBLC AI )Building Your Own AI Instance (TBLC AI )
Building Your Own AI Instance (TBLC AI )
 
20150722 - AGV
20150722 - AGV20150722 - AGV
20150722 - AGV
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity Webinar
 
20230104 - machine vision
20230104 - machine vision20230104 - machine vision
20230104 - machine vision
 
20230202 - Introduction to tis-py
20230202 - Introduction to tis-py20230202 - Introduction to tis-py
20230202 - Introduction to tis-py
 
COMPUTER 10: Lesson 7 - File Storage and Online Collaboration
COMPUTER 10: Lesson 7 - File Storage and Online CollaborationCOMPUTER 10: Lesson 7 - File Storage and Online Collaboration
COMPUTER 10: Lesson 7 - File Storage and Online Collaboration
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptx
 
201610817 - edge part1
201610817 - edge part1201610817 - edge part1
201610817 - edge part1
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdf
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and Istio
 
Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdf
 

Iv3515241527

  • 1. Ankita Shrivastava et al Int. Journal of Engineering Research and Application ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527 RESEARCH ARTICLE www.ijera.com OPEN ACCESS Short- Term Load Forecasting Using Artificial Neural Network Techniques Ankita Shrivastava1 and Arti Bhandakkar2 1( 2( PG Scholar, Department of Electrical & Electronics Engineering, SRIT, Jabalpur) Associate Professor, Department of Electrical & Electronics Engineering, SRIT, Jabalpur) ABSTRACT This paper proposes a neural network approach for forecasting short- term loads. Three ANN- techniques – Radial Basis Function Neural Network, Feed forward Neural Network and Cascade- Forward Neural Network are discussed in this paper. Their performances are evaluated through a simulation study. Historical Load Data from the Load Dispatch Centre Jabalpur are used for training, testing and showing the good performance of the proposed method. The proposed model can forecast the load profile with a lead time of one to seven days. Keywords- Artificial Intelligence, Artificial Neural Network, Back-Propagation, Load Forecasting, Power Quality. I. INTRODUCTION Load Forecasting is an important component for power system energy management system. Load forecasting means predicting the future load with the help of historical load data available. It is very important for the planning, operation and control of power system. It plays a vital role in the deregulated electric industry [1]. A good forecast reflects current and future trends in the power system. The accuracy of a forecast is crucial to any electric utility. That is why, accurate models for load forecasting are essential for the operation and planning of a utility company [2]. Since in power system the next day’s power generation must be scheduled every day, day- ahead short- term load forecasting (STLF) is a necessary daily task for power dispatch. Its accuracy affects the economic operation and reliability of the system greatly [3]. Short- term load forecasts helps in estimating the load flows. This helps in making decisions that can prevent overloading and the result deeply influence the power systems’ safety and economy [4]. The short- term forecasts are not only needed for control and scheduling of power system but also used as inputs to load flow study or contingency analysis i.e. for load management program. The short term forecasting is also primarily used for the generation dispatch, capacitor switching, feeder reconfiguration, voltage control, and automatic generation control (AGC) [5]. A little increase in the percentages of shortterm prediction accuracy may bring many benefits in terms of economy and reliability of power system. Therefore, precise short- term load forecasting not only enhances the reliability of power supply but also increases economic benefits [6]. www.ijera.com The research work in this area is still a challenge to the electrical engineering scholars because of its high complexity. How to estimate the future load with the historical data has remained a difficulty up to now, especially for the load forecasting of holidays, days with extreme weather and other anomalous days. But with the recent development of new mathematical and artificial intelligence tools, it is potentially possible to improve the forecasting results [7]. Load Forecasting can be performed using many techniques such as similar day approach, various regression models, time series, statistical methods, fuzzy logic, artificial neural networks, expert systems, etc. But application of artificial neural network in the areas of forecasting has made it possible to overcome the limitations of the other methods mentioned above used for electrical load forecasting [8]. II. ARTIFICIAL NEURAL NETWORK Neural networks are essentially non-linear circuits that have the demonstrated capability to do non-linear curve fitting. The outputs of an artificial neural network are some linear or non-linear mathematical function of its inputs [9]. ANN is usually formed from many hundreds or thousands of simple processing units, connected in parallel and feeding forward in several layers. Because of the fast and inexpensive personal computers availability, the interest in ANN’s has blossomed in the current digital world. The basic motive of the development of the ANN is to make the computers do what a human being cannot do. The three-layer fully connected feed-forward neural network which is generally used for load forecasting. It comprises of an input layer, one hidden layer and an output layer. Signal system is allowed only from the input layer to the hidden layer and from the hidden layer to the 1524 | P a g e
  • 2. Ankita Shrivastava et al Int. Journal of Engineering Research and Application ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527 www.ijera.com output layer. Input variables come from historical data, which are date, hour of the day, past system load, temperature and humidity, corresponding tothe factors that affect the load. The outputs are the forecasting results. The number of inputs, the number of hidden nodes, transfer functions, scaling schemes, and training methods affect the forecasting performance and, hence, need to be chosen carefully [10]. In applying a neural network to load forecasting, one must select one of a number of architectures (e.g. Hopfield, back propagation, Boltzmann machine), the number and connectivity of layers and elements, use of bi-directional or uni-directional links and the number format (e.g. binary or continuous) to be used by inputs and outputs. Figure 2: Architecture of Radial Basis Function Network The input of a RBF network can be modelled as a vector of real numbers . The output of the network is then a scalar function of the input vector, Figure 1: Structure of ANN This is the structure of ANN. There are three layers namely, input layer, hidden layer and output layer. , and is given by Also, And, Where, III. NEURAL NETWORK TRAINING AND TESTING In this section three types of neural network architectures are presented for short term load forecasting. 1. Radial Basis Function Network A radial basis function network is an artificial neural network that uses radial basis functions as activation functions. Radial basis function (RBF) networks typically have three layers: an input layer, a hidden layer with a non-linear RBF activation function and a linear output layer. The diagram below shows the radial basis function neural network architecture with input x and output y. The weights are so adjusted to give the targeted output as needed by the system. www.ijera.com N = the number of neurons in the hidden layer =the center vector for neuron i = the weight of neuron i in the linear output neuron. The parameters , , are determined in a manner that optimizes the fit between and the data [11]. 2. Feed forward back-propagation (FB) Neural Network Feed-forward BP Network consists of input, hidden and output layers. In a feed forward network information always moves in one direction; it never goes backwards. Back-propagation learning algorithm was used for training these networks. During training, calculations are carried out from input layer towards the output layer, and error values are fed back to the previous layer [12]. The most popular artificial neural network architecture for load forecasting is back propagation. This network uses continuously valued functions and supervised learning. That is, under supervised learning, the actual numerical weights assigned to element inputs are determined by matching historical data (such as time and weather) to desired outputs (such as historical loads). 1525 | P a g e
  • 3. Ankita Shrivastava et al Int. Journal of Engineering Research and Application ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527 www.ijera.com Tan-sigmoid transfer function was used to reach the optimized status. The performance of cascade forward back propagation and feed forward back propagation were evaluated using Mean Square Error (MSE) [13]. 2 IV. RESULTS AND DISCUSSIONS The acceptable criteria for a particular model is based upon the i. Mean Square Error (MSE) ii. Training Time iii. Detection Time Figure 3: Architecture of Feed forward BackPropagation Network Feed forward networks often have one or more hidden layers of sigmoid neurons followed by an output layer of linear neurons. Multiple layers of neurons with nonlinear transfer functions allow the network to learn nonlinear and linear relationships between input and output vectors. The linear output layer lets the network produce values outside the range –1 to +1. On the other hand, outputs of a network such as between 0 and 1 are produced, then the output layer should use a sigmoid transfer function (tansig) [13]. Cascade Forward Back propagation Network Cascade forward back propagation model is similar to feed-forward networks, but include a weight connection from the input to each layer and from each layer to the successive layers. While two- layer feedforward networks can potentially learn virtually any input-output relationship, feed-forward networks with more layers might learn complex relationships more quickly. The function newcf creates cascade-forward networks . Cascade forward back propagation ANN model is similar to feed forward back propagation neural network in using the back propagation algorithm for weights updating, but the main nature of this network is that each layer of neurons is related to all previous layer of neurons. For example, a three layer network has connections from layer 1 to layer 2, layer 2 to layer 3, and layer 1 to layer 3. The threelayer network also has connections from the input to all three layers [12]. 1. Performance of RBF Network Training with RBF network for 98 epochs taking goal=0.01 and spread=1 gives good performance in terms of MSE(mean square error) equal to 1.62. 3. Figure 5: Performance of RBF Neural Network Here MSE= 1.62, Training Time= 1.5744 and Detection Time= 0.0175. 2. Performance of FBPNN For different numbers of neurons the system has been trained and tested but the exact forecast is obtained for 12,12 neurons. Figure 6: Performance of FBPNN Here MSE= 1.7032e+004, Training Time= 2.4981 and Detection Time= 0.0206. 3. Figure 4: Architecture of Cascade forward BackPropagation Network www.ijera.com Performance of Cascade Forward BP Network For different numbers of neurons the system has been trained and tested but we get the exact forecast for 15, 15 neurons. 1526 | P a g e
  • 4. Ankita Shrivastava et al Int. Journal of Engineering Research and Application ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1524-1527 [6] [7] [8] Figure 7: Performance of CF-BP Network Here MSE = 3.2392e+004, Training Time = 15.5890 and Detection Time = 0.0254. V. CONCLUSIONS The result of the three neural network models (RBFNN, FFBPNN, CFBPNN) used for short term load forecast for Jabalpur region, shows that the networks has good performances and accurate prediction is achieved. Its forecasting reliabilities were evaluated by computing the mean square error (MSE) between the exact and predicted values. The results suggest that ANN model with the developed structure can perform good prediction with least error and finally this neural network could be an important tool for short term load forecasting as well as this work incorporates additional information such as Hour of the Day, Days of the month, and different weather conditions into the network so as to obtain a more representative forecast of future load. REFERENCES [1] [2] [3] [4] [5] Hong Chen, Claudio A. Canizares, Ajit Singh, “ANN- based Short- Term Load Forecasting in Electricity Markets”, University of Waterloo, Canada Sanjib Mishra, Sarat Kumar Patra, “Short Term Load Forecasting using a Neural Network trained by A Hybrid Artificial Immune System”, 2008 IEEE Region 10 Colloquium and the Third International Conference on Industrial and Information Systems, Kharagpur, India December 8- 10, 2008 J.P.S. Catalao, S.J.P.S. Mariano, V.M.F. Mendes, L.A.F.M. Ferreira, “Short Term electricity prices forecasting in a competitive market: A neural network approach”, ScienceDirect, Electric Power Systems Research 77 (2007) 1297- 1304 Ajay Gupta, Pradeepta K. Sarangi, “Electrcal Load Forecasting Using Genetic Algorithm Based Back- Propagation Method”, ARPN Journal of Engineering and Applied Sciences, vol. 7, no.8, August 2012 Shu Fan, Yuan- Kang Wu, Wei- Jen Lee, Ching- Yin Lee, ”Comparative Study on Load Forecasting Technologies for Different www.ijera.com [9] [10] [11] [12] [13] www.ijera.com Geographical Distributed Loads”, proc of IEEE 2011 Eugene A. Feinberg, Dora Genethliou, State University of New York, Stony Brook, “Chapter 12 LOAD FORECASTING” K.Y. Lee, Y.T. Cha, J.H. Park, “Short- Term Load Forecasting Using an Artificial Neural Network”, Transactions on Power Systems, vol. 7, No. 1, February 1992 Muhammad Buhari, Sanusi Sani Adamu, “Short-Term Load Forecasting Using Artificial Neural Network”, Proc. of the International MultiConference of Engineers and Computer Scientists 2012 Vol I, IMECS 2012, March 14- 16,2012, Hong Kong Gautham P. Das, Chandrasekar S., Piyush Chandra Ojha, “ Artificial Neural Network Based Short Term Load Forecasting for the Distribution Utilities” Kalki Communication Technologies Ltd. Available at www.kalkitech.com Fatemeh Mosalman, Alireza Mosalman, H. Mosalman Yazdi, M. Mosalman Yazdi, “One day- ahead load forecasting by artificial neural network”, Scientific Research and Essays Vol. 6 (13), pp. 2795- 2799, 4 July, 2011. Available at www.academicjournals.org/SRE http://en.wikipedia.org/RadialBasisFunction (accessed on 28.9.2013). H.Demuth, M. Beale and M.Hagan. “Neural Network Toolbox User‟s Guide”. The MathWorks, Inc., Natrick, USA. 2009 Dheeraj S. Badde, Anil k. Gupta, Vinayak K. Patki, “Cascade and Feed Forward Back propagation Artificial Neural Network Models for Prediction of Compressive Strength of Ready Mix Concrete”, IOSR Journal of Mechanical and Civil Engineering (IOSR-JMCE) ISSN: 2278-1684, PP: 01-06 www.iosrjournals.org Second 1527 | P a g e