Site Matching of Wind Turbine Generators Using Artificial Neural Network (ANN)
Site Matching of Wind Turbine Generators Using Artificial Neural Network (ANN)
Site Matching of Wind Turbine Generators Using Artificial Neural Network (ANN)
Advantages
Chitradurga (Jogmatti)
Davangere (Arasingudi)
(Anaburu)
Gadag( kappatgudda )
Introduction 8
Once the details of wind resource is known for potential wind power
site, efficient wind energy system demands optimum matching of wind
turbine to the site to obtain higher plant factor.
Wind turbine power output 9
Present work
Artificial neural network 16
Network architecture
The manner in which the neurons of a neural
network are structured is initially linked with the
learning algorithm used to train the network. Thus
the learning algorithm (rules) used in the design of
neural network are being structured.
In general there are four different class of
architecture.
1.Single layer feed forward networks.
2.Multilayer feed forward networks.
3.Recurrent networks.
4.Lattice structures. 17
Single layer feed forward networks
X1 Y1
X2 Y2
X3 Y3
18
Multilayer feed forward network
19
Learning process
Learning is a process by which the free parameters of a
neural network are adapted through a continuing process
of stimulation by the environment in which the network is
embedded.
This definition of learning process implies the following
sequence of events
1.The neural network is stimulated by an environment.
2.The neural network undergoes changes as a result of this
stimulation.
3.The neural network responds new way to the
environment, because of the changes that have occurred
in its internal structure.
20
Training of ANN
Objective Of Training`
2
P
3
4
Vc
Vc
5
6
Vr
Vr
7
8
Vf
Vf
10
10 22
23
24
25
26
27
28
29
Conclusion 30
Reference
31
Wikipedia
Non conventional energy sources by
G.D.Rai
32
Land Preservation: Wind farms are spaced over 33