Scribd
Upload
83 views16 pages

Introduction To Artificial Neural Networks and Its Application

Artificial neural networks (ANNs) are inspired by biological neurons and are composed of many artificial neurons linked together. ANNs can be trained to perform complex functions like pattern recognition and prediction. They have various applications in power systems including load forecasting, economic dispatch, fault diagnosis, and transient stability assessment. Load forecasting using ANNs involves training a network on historical load data to predict future loads. The network is trained using backpropagation to adjust weights to minimize forecasting error.

Uploaded by

Sanjay Negi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
83 views16 pages

Introduction To Artificial Neural Networks and Its Application

Artificial neural networks (ANNs) are inspired by biological neurons and are composed of many artificial neurons linked together. ANNs can be trained to perform complex functions like pattern recognition and prediction. They have various applications in power systems including load forecasting, economic dispatch, fault diagnosis, and transient stability assessment. Load forecasting using ANNs involves training a network on historical load data to predict future loads. The network is trained using backpropagation to adjust weights to minimize forecasting error.

Uploaded by

Sanjay Negi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Introduction to Artificial Neural

Networks and Its Application In


Power System

sanjay negi
07237
EEE
Contents:

• Biological Inspiration
• Artificial Neurons and Neural Network
• Activation Function
• Application Of ANN
Inspiration From Neurobiology

• Many input single output unit

• If the sum of the input signals


surpasses a certain threshold, then
neuron sends electrical signal along
the axon.
Artificial Neurons (Mathematical Representation )

• The synapses of the neuron


are modeled as weights.
• The strength of the
connection between an
input and a neuron is noted
by the value of the weight.
• An adder sums up all the
The McCulloch-Pitts model
inputs modified by their
respective weights.
• Finally, an activation
function controls the
amplitude of the output of
the neuron.
Activation Functions

• This function act as squashing function .


• Threshold Function: this function can takes on a value of
0 if the summed input is less than a certain threshold
value (v), and the value 1 if the summed input is greater
than or equal to the threshold value.
• Piecewise-Linear function: This function again can take
on the values of 0 or 1, but can also take on values
between that.
• sigmoid function: This function can range between 0 and
1 but sometime it is useful to take -1 to 1 range.
Artificial Neural Network
• An artificial neural network is composed of many
artificial neurons that are linked together according to a
specific network architecture. The objective of the neural
network is to transform the inputs into meaningful
outputs.

Output
input
• Weight settings determine the behaviour of a network

• How can we find the right weights?


• One way is to set the weights explicitly, using a priori
knowledge.

• Another way is to train the neural network by feeding it


teaching patterns and letting it change its weights according
to some learning rule.
• The learning situations in neural networks may be classified
into three distinct sorts. These are
• Supervised learning
• Unsupervised learning
• Reinforcement learning
Application of ANN In Power System
• Load forecasting
• Economic dispatch
• Fault diagnosis/fault location
• Transient stability problems
• Security assessment
Load Forecasting

• This can only be done if, among other vital factors, there is a
good and accurate system in place for forecasting the load
that would be in demand by electricity customers.
• Also Such forecasts will be highly useful in proper system
planning and operations.
Load Forecasting Using Neural Networks

• The back-propagation algorithm is a supervised learning


algorithm used to change or adjust the weights of the neural
network.
• In back-propagation, the gradient vector of the error surface is
calculated. This vector points along the direction of steepest
descent from the current point, so that a movement over a
short distance along it decreases the error. A sequence of
such moves will eventually find a minimum error point.
• In this fig. basically two load
patterns were observable: one
for weekends (Saturday and
Sunday) and another for week
days (Monday through Friday).
• After the neural network is
trained on the input data set, a
new data set is presented at its
input, and the network
provides a forecast of the load
for the next one hour.
References
• Ajith Abraham .“Artificial Neural Networks” .Oklahoma State
University, Stillwater, OK, USA
• Carlos Gershenson. [email protected] . “Artificial
Neural Networks for Beginners”
• Bakirtzis, A.G., Petridis, V., Kiartzis, S.J., Alexiadis, M.C., and
Maissis, A.H. 1996. “A Neural Network Short Term Load
Forecasting Model ”. IEEE Transactions on Power Systems. 11:
858-863.
• M. Tarafdar Haque, and A.M. Kashtiban. “Application of
Neural Networks in Power Systems; A Review”
THANKYOU

You might also like