BPSO&1-NN algorithm-based variable selection for power system stability identification

International Journal of Advanced Engineering, Management and Science (IJAEMS) [Vol-6, Issue-9, Sep-2020]
https://dx.doi.org/10.22161/ijaems.69.3 ISSN: 2454-1311
www.ijaems.com Page | 432
BPSO&1-NN algorithm-based variable selection
for power system stability identification
N. N. Au, V. V. Cuong, T. T. Giang, L. T. Nghia, T. V. Hien
Faculty of Electrical and Electronics Engineering, HCMC University of Technology and Education, Ho Chi Minh City, Viet Nam
Abstract— Due to the very high nonlinearity of the power system, traditional analytical methods take a lot
of time to solve, causing delay in decision-making. Therefore, quickly detecting power system instability
helps the control system to make timely decisions become the key factor to ensure stable operation of the
power system. Power system stability identification encounters large data set size problem. The need is to
select representative variables as input variables for the identifier. This paper proposes to apply wrapper
method to select variables. In which, Binary Particle Swarm Optimization (BPSO) algorithm combines
with K-NN (K=1) identifier to search for good set of variables. It is named BPSO&1-NN. Test results on
IEEE 39-bus diagram show that the proposed method achieves the goal of reducing variables with high
accuracy.
Keywords— Identification, Power system, BPSO, Variable selection, K-NN.
I. INTRODUCTION
Modern power systems suffer from operating pressure
very close to a stable boundary limit, while power systems
are always faced with abnormal agitation that can easily
cause instability (Makarov, Reshetov, Stroev, & Voropai,
2005). Due to the very high nonlinearity of the power
system, traditional analytical methods take a lot of time to
solve, causing delay in decision-making. Therefore,
quickly detecting power system instability helps the
control system to make timely decisions become the key
factor to ensure stable operation of the power system.
In recent years, the identification method has been applied
as an alternative to solving difficult problems that
traditional methods of analysis cannot solve in terms of
computational (Dong, Rui, & Xu, 2012; Mitra, Benidris,
Nguyen, & Deb, 2017; Oliveira, Vieira, Bezerra, Martins,
& Rodrigues, 2017; Zhang, Xu, Dong, Meng, & Xu,
2011). By learning the database, the nonlinear input/output
relationship between the electrical system operating
parameters and stability can be quickly calculated.
However, if the identifier works fast, the number of input
variables must be characteristic variables. Therefore, the
selected variables must be characteristic, eliminate
redundant variables and cause noise.
The selection of variables of previously published works
mainly applies the filter method that has to go through
many stages (Dong et al., 2012; Kalyani & Swarup, 2013;
Swarup, 2008). With this method, the first is based on the
statistical criteria to filter out the good variables first, then
ask the identifier to evaluate the accuracy to find the
appropriate set of variables. This article recommends a
wrapper method to select variables. In which, BPSO
(Binary Particle Swarm Optimization) algorithm combined
with K-NN (K=1) identifier to perform the process of
searching for good set of variables. It is named BPSO&1-
NN. This helps to reduce the step of finding the variable
set compared to the filter method and improves the
automation of the process of finding the variable set. Test
results on IEEE 39-bus diagram show that the proposed
method achieves the goal of variable reduction with high
accuracy.
II. VARIABLE SELECTION
In the design stages of a stable diagnostic model of the
power system using the identification method, the
selection of characteristic variables is very important
because it directly affects the diagnostic accuracy of the
model. This also helps to reduce the number of
measurement sensors, reducing computation time for the
model. This step defines a specific set of variables that
represent the database for training. These initial
characteristic variables are the input variable representing
the operating parameters of the power system and covering
the operating status of the power system. The
characteristic variable of the power system in transient
mode or dynamic mode is the change in generator

capacity, change of load capacity, change of power on
transmission lines, voltage drop at nodes, ... right at the
time of the incident. The output variable is labeled binary.
‘0’ is unstable and ‘1’ is stable.
Filter method:
The Filter method applies the search algorithm with the
statistical standard function such as Fisher, Divergence, ...
to guide the search strategy for the best set of variables to
achieve the target value (J) (Dong et al., 2012; Kalyani &
Swarup, 2013; Swarup, 2008). The process of searching
for the set of variables by the filter method is presented as
Figure 1. This method shows that the result is a set of
variables meeting statistical standards but does not show
the identification accuracy and the number of necessary
variables. Therefore, the filter method needs to add an
identification accuracy assessment to select the last set of
variables.
Fig. 1: Diagram of Filter method
Wrapper method:
Fig. 2: Diagram of Wrapper method
The Wrapper method is presented as in Figure 2. However,
this method differs from the Filter method in that the target
function considering the identity accuracy. Thus, this
method results in a set of variables to be selected with a
specific identification accuracy.
The fitness function for selecting variables is presented in
formulas (1), (2), and (3).
ErrsF
Fitness
TotalF sF
=
−
(1)
(%) (%)
AccSample
AccsF
TotalSample
=
(2)
(%) 1ErrsF AccsF= − (3)
where:
Finess is the objective function.
AccsF is the identification accuracy of the selected set
of variables.
AccSample is the number of the correct identifier.
TotalSample is the total number of samples.
TotalF: the total number of variables in the data set.
sF is the number of selected variables.
ErrsF is the identification error of the selected variable.
III. BPSO ALGORITHM IN VARIABLE
SELECTION
PSO (Particle Swarm Optimization) is the optimal search
algorithm proposed by Kennedy and Eberhart (Kennedy &
Eberhart, 1995). In the PSO, each candidate answer of the
problem is encoded as an instance that moves through the
search space. The whole herd seeks the optimal solution by
updating the position of each individual based on their
own experience and on neighboring individuals.
Generally, the vector xi = (xi1, xi2, ..., xiD) used in the PSO
represents the position of the i th instance. The vector vi =
(vi1, vi2,…, viD) is used in the PSO to represent the velocity
of the i th instance. D is the size of the search space.
During the search, the best position for each previous
individual was recorded as pbest. The best location of the
herd is the gbest. The herd was randomly generated from
the population. Finding the best solution by updating the
velocity and position of each individual according to
equations (4) and (5).
1 1t t t
id id idx x v+ +
= +
(4)
1
1 1
2 2
* *(p )
*(p )
t t t
id id i id id
t
i gd id
v w v c r x
c r x
+
= + − +
+ −
(5)
Where: t is the t th iteration of the search process. d is the
size in the search space, dD. c1, c2 are acceleration
constants. r1i, r2i are random values, valid in the range
[0,1]. pid and pgd represent pbest and gbest particles of size

d. w is the inertial weight. is the velocity, limited to the
maximum velocity vmax,
t
idv [-vmax, vmax].
The original PSO algorithm applied to the problem of
continuity. Kennedy and Eberhart developed the BPSO
algorithm for the discrete problem (Kennedy & Eberhart,
1997). The velocity in BPSO represents the element that
can take the value 1. Equation (4) is still used to update the
velocity while xid, pid get the value 0 or 1. The function
sigmoid s(vid) is used to convert the value of vid into a
range of values (0,1). The BPSO updates each instance's
position using equations (6) and (7).
1,if () ( )
0,
id
id
rand s v
x
otherwise

= 

(6)
1
( )
1 id
id v
s v
e−
=
+
(7)
The function rand() is a random function whose value is
distributed in (0,1).
BPSO
Begin
Data set, kfold; D: dimensionality of search space
N : the population size; T : maximum iterations;
c1, c2, vmax, w
Randomly initialise the position and velocity of each
particle;
while t ≤T
evaluate fitness of each particle according to
Equation (1);
for i=1 to N
update the pbest of particle i;
update the gbest of particle i;
end
for i=1 to N
for d=1 to D
update the velocity of particle i according to
Equation (4);
update the position of particle i according to
Equations (6) and (7);
end
end
end
calculate the classification error of the selected feature
subset;
return the position of gbest (the selected feature
subset);
return the classification error of the selected feature
subset;
end
IV. RESULTS
Features and samples:
The study was tested on the IEEE 39-bus scheme. It
includes 39 buses, 19 loads, 10 generators. The diagram
IEEE 39-bus scheme is shown as Fig. 2. It was used in
many published works. The off-line simulation was
implemented to collect data for training. Load levels are
(20,30,…,120)% normal load. The setting fault clearing
time (FCT) is 50ms (Glover, Sarma, & Overbye, 2012). In
this paper, all kinds of faults such as single phase to
ground, double phase to ground, three phases to ground
and phase-to-phase short-circuit are considered. Faults are
tested in any buses and in each of 5% distances of long
transmission lines of the test systems. For each of the
considered load samples, the generator samples have been
got accordingly by running optimal power flow (OPF) tool
of Power-World software.
The input and output feature are
x{delVbus,delPLoad,delPflow} and y{1,0}. Total of input
features is 104, x{104(39+19+46)}. The number of output
feature is one, y{1,0}. From simulating results, there are
1167 samples that include 834 S samples and 783 U
samples. The K-NN (K=1) is used as a classifier for
evaluating accurate classification because of its simplicity.
Assessment of classification error is a cross-assessment
method. It is a 10-fold cross-validation.
Fig. 2: The IEEE 39-bus diagram
Feature selection results:
The BPSO&1-NN algorithm works with different N
values, namely 10, 20, 30, 40, and 50. The values of w are

0.4, 0.5, 0.6, 0.7, 0.8, and 0.9. The number of iterations is
100 for the program executions, T=100. The values of c1
and c2 are selected unchanged during program execution,
c1=2, c2=2. The program is also executed on Matlab 2018a
software. Identification tool, 1-NN, is supported from this
software.
The convergence characteristics of BPSO&1-NN variable
selection algorithm are shown as Fig. 3 to Fig. 8. The
results of the selected number of variables, the value of the
best fitness function and the test error are presented in
Table 1.
Table 1. Best results during the implementation of BPSO
program with w = 0.9, N = 50, the number of variables in
the set of variables is 23, the identification error is 5.07%.
Thus, the algorithm BPSO&1-1NN has reduced the
number of variables from 104 to 23 variables. The number
of variables is reduced by 78% while test accuracy reaches
94.93%. This is the accepted result in previously published
(Abdelaziz & El-Dessouki, 2013; Amjady & Majedi,
2007; Dong et al., 2012; Haidar, Mustafa, Ibrahim, &
Ahmed, 2011; Kalyani & Swarup, 2013; Karami &
Esmaili, 2013).
Table 1. Results of BPSO algorithm
w N f Best Fitness ErrsF(%)
0.4 10 32 7.3868e-04 5,07
20 32 7.2150e-04 5,07
30 33 7.3166e-04 5,01
40 30 6.7693e-04 5,13
50 37 7.1073e-04 5,01
0.5 10 33 7.1424e-04 5,19
20 32 6.9573e-04 5,26
30 33 7.0553e-04 5,07
40 34 7.2445e-04 5,07
50 31 7.3703e-04 5,26
0.6 10 33 7.2295e-04 4,95
20 32 7.2150e-04 5,19
30 36 7.3666e-04 5,01
40 33 6.5327e-04 4,89
50 36 6.9119e-04 5,13
0.7 10 31 7.0315e-04 5,13
20 35 7.1702e-04 5,26
30 30 6.9364e-04 5,26
40 29 7.0089e-04 5,13
50 26 6.6600e-04 4,95
0.8 10 32 6.6138e-04 5,07
20 30 6.6021e-04 4,89
30 33 6.5327e-04 5,26
40 30 6.6857e-04 5,07
50 27 6.1843e-04 5,26
0.9 10 32 6.6996e-04 5,44
20 27 6.2646e-04 5,38
30 27 6.1040e-04 5,13
40 23 5.9552e-04 5,13
50 23 6.1079e-04 5,07
Fig. 3: Convergence characteristics of BPSO&1-NN,
w=0,4
w=0,5
w=0,6

w=0,7
w=0,8
w=0,9
V. CONCLUSION
The paper successfully applied BPSO algorithm combined
with 1-NN identifier in the variable selection approach to
the problem of identifying stability of power system. Test
results on IEEE-39 bus diagram showed that the number of
variables decreased significantly, but the test accuracy still
met expectations. This achieved result will be the driving
force for the research and application of evolutionary
algorithms to select variables for the problem of
identifying stability of power systems.
ACKNOWLEDGEMENTS
This work belongs to the project grant No: T2020-26TĐ
funded by Ho Chi Minh City University of Technology
and Education, Vietnam.
REFERENCES
[1] Abdelaziz, A. Y., & El-Dessouki, M. A. (2013). Transient
Stability Assessment using Decision Trees and Fuzzy
Logic Techniques. International Journal of Intelligent
Systems and Applications, 5(10), 1–10.
https://doi.org/10.5815/ijisa.2013.10.01
[2] Amjady, N., & Majedi, S. F. (2007). Transient stability
prediction by a hybrid intelligent system. IEEE
Transactions on Power Systems, 22(3), 1275–1283.
https://doi.org/10.1109/TPWRS.2007.901667
[3] Dong, Z. Y., Rui, Z., & Xu, Y. (2012). Feature selection for
intelligent stability assessment of power systems. 2012
IEEE Power and Energy Society General Meeting, 1–7.
https://doi.org/10.1109/PESGM.2012.6344780
[4] Glover, J. D., Sarma, M. S., & Overbye, T. (2012). Power
System Analysis and Design. In Global Engineering:
Christopher M.Shortt (Fifth Edit).
https://doi.org/10.1145/633615.810652
[5] Haidar, A. M. A., Mustafa, M. W., Ibrahim, F. A. F., &
Ahmed, I. A. (2011). Transient stability evaluation of
electrical power system using generalized regression neural
networks. Applied Soft Computing Journal, 11(4), 3558–
3570. https://doi.org/10.1016/j.asoc.2011.01.028
[6] Kalyani, S., & Swarup, K. S. (2013). Pattern analysis and
classification for security evaluation in power networks.
International Journal of Electrical Power and Energy
Systems, 44(1), 547–560.
https://doi.org/10.1016/j.ijepes.2012.07.065
[7] Karami, A., & Esmaili, S. Z. (2013). Transient stability
assessment of power systems described with detailed
models using neural networks. International Journal of
Electrical Power and Energy Systems, 45(1), 279–292.
https://doi.org/10.1016/j.ijepes.2012.08.071
[8] Kennedy, J., & Eberhart, R. (1995). Particle Swarm
Optimization. IEEE International Conference , Perth, WA,
Australia, (ISBN: 0-7803-2768-3), 1942–1948.
[9] Kennedy, J., & Eberhart, R. C. (1997). Discrete binary
version of the particle swarm algorithm. Proceedings of the
IEEE International Conference on Systems, Man and
Cybernetics, 5, 4104–4108.
https://doi.org/10.1109/icsmc.1997.637339
[10] Makarov, Y. V., Reshetov, V. I., Stroev, V. A., & Voropai,
N. I. (2005). Blackout prevention in the United States,
Europe, and Russia. Proceedings of the IEEE, 93(11),
1942–1954.https://doi.org/10.1109/JPROC.2005.857486
[11] Mitra, J., Benidris, M., Nguyen, N., & Deb, S. (2017). A
Visualization Tool for Real-Time Dynamic Contingency
Screening and Remedial Actions. IEEE Transactions on
Industry Applications, 53(4), 3268–3278.
https://doi.org/10.1109/TIA.2017.2686353

[12] Oliveira, W. D., Vieira, J. P. A., Bezerra, U. H., Martins, D.
A., & Rodrigues, B. das G. (2017). Power system security
assessment for multiple contingencies using multiway
decision tree. Electric Power Systems Research, 148, 264–
272. https://doi.org/10.1016/j.epsr.2017.03.029
[13] Swarup, K. S. (2008). Artificial neural network using
pattern recognition for security assessment and analysis.
Neurocomputing, 71(4–6), 983–998.
https://doi.org/10.1016/j.neucom.2007.02.017
[14] Zhang, R., Xu, Y., Dong, Z. Y., Meng, K., & Xu, Z.
(2011). Intelligent systems for power system dynamic
security assessment: Review and classification. 2011 4th
International Conference on Electric Utility Deregulation
and Restructuring and Power Technologies (DRPT), 134–
139. https://doi.org/10.1109/DRPT.2011.5993876

BPSO&1-NN algorithm-based variable selection for power system stability identification

More Related Content

What's hot (19)

Similar to BPSO&1-NN algorithm-based variable selection for power system stability identification (20)

Recently uploaded (20)

BPSO&1-NN algorithm-based variable selection for power system stability identification