Professional Documents
Culture Documents
Transient Stability Assessment of A Power System Using Probabilistic Neural Network
Transient Stability Assessment of A Power System Using Probabilistic Neural Network
Transient Stability Assessment of A Power System Using Probabilistic Neural Network
ISSN 1546-9239
2008 Science Publications
Corresponding Author: Noor Izzri Abdul Wahab, Department of Electrical, Electronic and System Engineering, Faculty of
Engineering, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor D. E., Malaysia
Tel: +60 (3) 89464433
1225
d 2 i
= Pmi Pei
dt 2
pR
Input layer
Pattern layer
Class 1
Class 2
Output layer
pj
(1)
p1
IW1,1
Radial basis
function
pj
pR
dist
.*
it is known that,
i
= i
dt
(2)
i
= Pmi P ei
dt
(3)
where:
I = Rotor angle of machine i
I = Rotor speed of machine i
Pmi = Mechanical power of machine i
Pei = Electrical power of machine i
MI = Moment of inertia of machine i
A time domain simulation program can solve these
equations through step-by-step integration by producing
time response of all state variables.
PROBABILISTIC NEURAL
NETWORK THEORY
a = radbas( IW1,1 p b)
(4)
PNN which is a class of Radial Basis Function
(RBF) network is useful for automatic pattern
where, radbas is the radial basis activation function
recognition, nonlinear mapping and estimation of
which can be written in general form as,
probabilities of class membership and likelihood
1226
(6)
En
100
n =1 N
N
(7)
Load C
(5)
(8)
18 kv 18/230
230/13.8 13.8 kv
230 kv
230 kv
Load A
Load B
230 kv
16.5 kv
16.5/230
-0.2
Rotor angle
-0.4
-0.6
synz-syn1
-0.8
for all faults. Next, the repetitions are due to the faults
that occur on the same line. The FCT of the same line
are set at four different times, two for stable cases and
two for unstable cases. At the start of the fault, same
values of data are recorded for all the four faults. A few
milliseconds after the fault, the recorded data differ
from each other due to different FCT settings. For the
repetitions of data recorded, one data out of the four
different FCT settings are kept. These data are denoted
as data for stable cases. The data collected are
normalized so that they have zero mean and unity
variance.
-1
-1.2
-1.4
Time (sec)
No. of features
2
3
6
12
6
29
(a)
50
0
Rotor angle
-50
-100
-150
-200
-250
-300
0
3
Time (sec)
(b)
1228
Desired
output
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1229
PNN29
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
PNN11
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
Test
data
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
Desired
output
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
PNN29
1
1
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
PNN11
1
1
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
Desired
output
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
MLPNN29
1
1
2
2
2
2
1
1
X
1
X
2
2
2
2
1
1
1
1
1
X
X
X
2
2
1
1
1
1
1
X
2
2
2
2
1
1
1
1
MLPNN11
1
1
2
2
2
2
1
1
1
2
1
2
2
2
2
1
1
1
1
1
X
X
1
2
2
1
1
1
1
1
X
2
2
2
2
1
1
1
1
Test
data
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
Desired
output
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
MLPNN29
1
2
2
2
2
1
1
1
1
1
2
2
2
2
2
X
X
X
X
1
1
1
1
1
1
2
2
2
2
X
1
1
1
1
2
2
2
2
2
MLPNN11
1
X
2
2
2
X
1
1
1
1
2
2
2
2
2
X
X
1
1
1
1
1
1
1
1
2
2
2
2
X
1
1
1
X
2
2
2
2
2
1230
MLPNN11
11
0.069
14 (11.9%)
REFERENCES
Pothisarn, C. and S. Jiriwibhakorn, 2003, Critical
clearing time determination of EGAT system using
artificial neural networks. IEEE Power Engineering
Society General Meeting, 2: 735-738.
Sanyal, K. K., 2004, Transient stability assessment
using neural network. IEEE International
Conference on Electric Utility Deregulation,
Restructuring and Power Technologies, 2: 633-637.
Bettiol, A.L., A. Souza, J.L. Todesco and
J.R. Tesch Jr., 2003. Estimation of critical clearing
times using neural networks. IEEE Bologna Power
Tech Conference, 3: 6.
Krishna, S. and K.R. Padiyar, 2000. Transient
stability assessment using artificial neural
networks. IEEE International Conference on
Industrial Technology, 1: 627-632.
Silveira, M.C.G., A.D.P. Lotufo and C.R. Minussi,
2003. Transient stability analysis of electrical
power systems using a neural network based on
fuzzy ARTMAP. IEEE Bologna PowerTech
Conference, 3: 7.
Boudour, M. and A. Hellal, 2005. Combined use of
supervised and unsupervised learning for power
system dynamic security mapping. Eng. Appl.
Artificial Intel., 18 (6): 673-683.
1232