pantaz d. vadim
TRANSCRIPT
-
8/13/2019 Pantaz d. Vadim
1/8
Electric Power Systems Research 95 (2013) 192199
Contents lists available at SciVerse ScienceDirect
Electric Power Systems Research
journal homepage: www.elsevier .com/ locate /epsr
A new classification for power quality events in distribution systems
Okan Ozgonenela,, Turgay Yalcin a, Irfan Guney b, Unal Kurt c
a Ondokuz MayisUniversity, Electrical& Electronic Eng. Depart., Kurupelit, Samsun, TurkeybAcibademUniversity, Dean of Engineering Faculty, GulsuyuMah. Fevzi Cakmak Cad. No. 1, Maltepe, Istanbul, TurkeycAmasyaUniversity, Technology Faculty, Electrical & Electronic Eng. Depart., Amasya, Turkey
a r t i c l e i n f o
Article history:
Received 19 January 2012
Received in revised form 22 July 2012Accepted 18 September 2012
Available online 13 October 2012
Keywords:
Power quality disturbances
Hilbert Huang Transform
Ensemble Empirical Mode Decomposition
Support Vector Machines
One-against-all method
a b s t r a c t
This paper presents the performance evaluation of support vector machine (SVM) with one against all
(OAA) and different classification methods for power quality monitoring. The first aim of this study is
to investigate EEMD (ensemble empirical mode decomposition) performance and to compare it with
classical EMD (empirical mode decomposition) for feature vector extraction and selection ofpower qual-
ity disturbances. Feature vectors are extracted from the sampled power signals with the Hilbert Huang
Transform (HHT) technique. HHT is a combination ofEEMD and Hilbert transform (HT). The outputs of
HHT are intrinsic mode functions (IMFs), instantaneous frequency (IF), and instantaneous amplitude (IA).
Characteristic features are obtained from first IMFs, IF, and IA. The ten featuresi.e., the mean, standard
deviation, singular values, maxima and minimaofboth IF and IA are then calculated. These features are
normalized along with the inputs ofSVM and other classifiers.
Crown Copyright 2012 Published by Elsevier B.V. All rights reserved.
1. Introduction
Power monitoring has taken on an important role in power sys-tems. Power quality (PQ); or, more specifically, a power quality
disturbance, is generally defined as any change in power (voltage,
current, or frequency) that interferes with the normal operation
of electrical equipment. Power quality concerns various kinds of
electric disturbances such as voltage sag/swell, flicker, impulse,
harmonics, DC component of voltage, oscillatory transients, elec-
tromagnetic interference (EMI), and power system outage [1,2].
However, more generally, PQ disturbances can be classified as in
three groups. These are Frequency and amplitude variations and
transient phenomena. Amplitude variations cover voltage vari-
ations under normal operating conditions, excluding faults and
interruptions, short and long interruptions, voltage sags (dips)
and swells, and voltage fluctuations known as flicker. Transient
phenomena cover voltage unbalance and voltage/current wave-
form disturbances [3].
To analyze these disturbances, data areoften available as a form
of sampled time function that is represented by a time series of
amplitudes. When dealing with such data, the Fourier transform
(FT)-based approach is most often used. FT assumes periodicity of
a given signal and loses the time axis account; however, it is not
Corresponding author. Tel.: +90 362 4377204.E-mail addresses:[email protected](O. Ozgonenel),
[email protected](T. Yalcin), [email protected](I. Guney),
[email protected] (U. Kurt).
capable of providing time information about signal disturbances.
Short time Fourier transform (STFT) provides both time and fre-
quency information, but it suffers severely from the Heisenberguncertainty principle [4], causing it to undergo a trade-off
between time resolution and frequency resolution. This is one of
the reasons for the creation of the wavelet transform (or multires-
olution analysis in general), which can give good time resolution
for high-frequency events, and good frequency resolution for low-
frequencyevents, which is thetype of analysis best suitedfor many
real signals. Wavelet transform [5], which is a popular signal anal-
ysis method, offers continuous and discrete wavelet transforms
(CWT and DWT) [6] and wavelet packet transform (WPT) [7,8] for
the feature extraction of signals.
Many classification algorithms have been developed by
researchers for classification of power electrical disturbances. Inte-
grated Fourier linear combiner and fuzzy expert systems [9] were
used for the classification of transient disturbance waveforms
in power system. S-Transform and two dimensional timetime
(TT) transform [10] have been implemented for electrical fault
identification. In [10], transient disturbance waveforms in power
system were investigated by S-transform with together TT trans-
form methods. It is reported that ST with together TT transform
approaches was able to identify disturbed waveforms. An adaptive
neural network approach for the estimation of harmonic distort-
ions and power quality in power networks was also implemented
[11]. A hybrid system to automatically detect, locate, and classify
disturbances affecting power quality in an electrical power system
is also presented [12]. The least absolute value (LAV) state esti-
mation algorithm has been used to measure the flicker voltage
0378-7796/$ see front matter. Crown Copyright 2012 Published by Elsevier B.V. All rights reserved.
http://dx.doi.org/10.1016/j.epsr.2012.09.007
http://localhost/var/www/apps/conversion/tmp/scratch_8/dx.doi.org/10.1016/j.epsr.2012.09.007http://localhost/var/www/apps/conversion/tmp/scratch_8/dx.doi.org/10.1016/j.epsr.2012.09.007http://www.sciencedirect.com/science/journal/03787796http://www.elsevier.com/locate/epsrmailto:[email protected]:[email protected]:[email protected]:[email protected]://localhost/var/www/apps/conversion/tmp/scratch_8/dx.doi.org/10.1016/j.epsr.2012.09.007http://localhost/var/www/apps/conversion/tmp/scratch_8/dx.doi.org/10.1016/j.epsr.2012.09.007mailto:[email protected]:[email protected]:[email protected]:[email protected]://www.elsevier.com/locate/epsrhttp://www.sciencedirect.com/science/journal/03787796http://localhost/var/www/apps/conversion/tmp/scratch_8/dx.doi.org/10.1016/j.epsr.2012.09.007 -
8/13/2019 Pantaz d. Vadim
2/8
O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199 193
Fig. 1. Basic stages of the classification process.
magnitude [13], while the Simulated Annealing (SA) optimiza-tion algorithm has been used for measuring the voltage flicker
magnitude, frequency and the harmonics contents of the volt-
age signal for power quality analysis [14]. An algorithm to detect
the fundamental frequency is proposed. It is based on the chirp-z
transform (CZT) spectral analysis and is able to observe all stan-
dards in force because of its accuracy and working characteristics
[15]. Wavelet multi-resolution decomposition, which combines
frequency domain with time-domain analysis for power disturb-
ance feature extraction, is also proposed [16]; moreover, a wavelet
norm entropy-based effective feature extraction method for power
quality disturbance classification problem has been studied by
[17]. Multi-wavelet based neural networks with learning vector
quantization networks are used for power quality disturbances
as a powerful classifier [18]. Fuzzy ARTMAP, back propagationalgorithm (BPA) and Radial Basis Function (RBF) networks, in
combination with S Transform, Wavelet transform, and Hilbert
Transform (HT) for classifying power faults, have also been used
[19].
On the contrary, unlike many of the aforementioned decompo-
sition methods, EMD is intuitiveand direct, with thebasicfunctions
based on and derived from the data. The assumptions for this
method are: (a) the signal has at least one pair of extrema; (b) the
characteristic time scale is defined by thetime between the succes-
sive extrema; and (c) if there are no extrema, and only inflection
points, then the signal can be differentiated to realize the extrema,
whose IMFs can be extracted. Integration may be employed for
reconstruction.The time between the successive extrema was used
byHuang et al. [20] as it allowed the decomposition of signals thatwere allpositive, allnegative, or both. This implied that thedatadid
not have to have a zero mean. This also allowed a finer resolution
of the oscillatory modes.
Thispaper presents a hybrid powerqualitymonitoring approach
based on EEMD and SVM. EEMD and basic statistical calcula-
tions of its outputs are used for feature extraction. Moreover,
SVM is used for classifying the analyzed power disturbances.
To show the performance of the proposed methods, different
well-known classifiers are tested. Among all the tested classifica-
tion algorithms, the suggested analytical procedures, followed by
SVM-OAA, give a reliable solution for classifying non-stationary
power disturbances. The proposed PQ monitoring approach is
easy to implement and presents reliable solution with high accu-
racy.
2. Materials andmethods
The suggested classification process is shown in Fig. 1.
As seen in Fig. 1, all major power quality issues such as voltage
sag/swell, flicker, harmonics, transients, DC offset, electromag-
netic interference (EMI), and interruptions have been investigated.
Training procedure has been achieved by using synthetically gen-
erated data. Moreover, the supply frequency and flicker frequency
are randomly chosen between 49.5Hz and 50.5Hz and between
8 Hz and 25Hz, respectively. Sampling frequency is set at 25.6kHz
in compliance with the real-time data. This yields a 32003 datamatrix for a three-phase system. The testing procedure was com-
pleted by using real-time data supplied by TUBITAK (The Scientific
and Technological Research Council of Turkey). The data collected
by the National Power Quality Monitors (NPQMC) during an eventbreaking normal operating conditions are transferred by means
of a network infrastructure which is formed in the NPQMC. The
data collected in the center are kept in databases and file systems
after processing them on time and location basis to consider their
distribution in the country.
EEMD is mainly a signal processing technique to extract dis-
tinctive features; namely, IMFs. Feature selection requires a series
of calculations based on statistics such as maxima, minima, sin-
gular value, standard deviation, and mean. Next, the singular
value decomposition (SVD) technique is used for calculating some
additional properties of the features singular values. SVD was cho-
sen simply because the data matrix is not square. It has been
observed that additional properties of the feature vectors increase
the performance of the classification algorithm. Finally, SVM witha one-against-all (OAA) approach is used for classification of PQ
events.
Sections 2.12.4 give the mathematical background of the pro-
posed feature extraction and selection algorithms.
2.1. EMD
EMD is a self-adaptive signal-processing method that has been
successfully applied in non-stationary signal processing. The EMD
method is based upon the local characteristic time scale of the sig-
nal and could decompose the complicated signal function into a
number of IMFs. IMFs reflect the intrinsic and real physical infor-
mation of analyzed the signals. Moreover, the superposition of IMF
components can reconstruct the analyzed signal (Eq. (1)). EMD
-
8/13/2019 Pantaz d. Vadim
3/8
194 O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199
Fig. 2. A flowchart of EMD algorithm.
method is a sifting process; to decompose one IMF component
requires many sifting cycles. Thesifting process actually servestwo
purposes: to eliminate riding waves and to make the wave profiles
more symmetrical with respect to zero (Fig. 2).
The EMD algorithm used in this study comprises the following
steps:
(i) Identify all the extrema (maxima and minima) of the signal,x(t).
(ii) Generate the upper and lower envelope by the cubic spline
interpolation of the extrema points developed in step (i).
(iii) Calculate the mean function of the upper and lower envelope,
m(t).
(iv) Calculate the difference signald(t) =x(t)m(t).( v) If d(t) becomes a zero-mean process, then the iteration stop
and d(t) is an IMF1, named c1(t); otherwise, go to step (i) and
replacex(t) withd(t).
(vi) Calculate the residue signal r(t) =x(t) c1(t).(vii) Repeat the procedure from steps (i) to (vi) to obtain IMF2,
named c2(t). To obtaincn(t), continue steps (i)(vi) aftern iter-
ations. The process is stopped when the final residual signal
r(t) is obtained as a monotonic function.
At the end of the procedure, we have a residue r(t) and a collec-
tion ofn IMF, named from c1(t) to cn(t). Now, the original signal can
be represented as:
x(t) =n
i=1
ci(t) + r(t) (1)
Often, r(t) is regarded as cn+1(t) [20].
The sifting process should be applied with care, for carrying the
process to an extreme could make the resulting IMF a pure fre-
quency modulated signal of constant amplitude. To guarantee that
theIMF componentsmaintain enough physical senseof bothampli-
tude and frequency modulations, a criterion should be defined for
the sifting process to stop. This can be accomplished by limiting
size of the standard deviation (SD), it is similar to the Cauchy con-
vergence test, computed from the two consecutive sifting results
as
SD =T
t=0
di1(t) di(t)2d2
i1(t)
(2)
where di(t) is proto (candidate)-mode function.
A typical value for SD can be set between 0.2 and 0.3. As a com-
parison the two Fourier spectra, computed by shifting only five out
of 1024 points from the same data, can have an equivalent SD of
0.20.3calculated point-by-point. Therefore,SD valueof 0.20.3for
the sifting procedure is a very rigorous limitation for the difference
between siftings [20].
In Fig.2, Extrema
-
8/13/2019 Pantaz d. Vadim
4/8
O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199 195
Fig. 3. (a) Feature vectors (IMFs)for a voltage sagsignal with EMD. (b) Feature vectors (IMFs)for a voltage sagsignal with EEMD.
An equivalent expression gives the correlation coefficient as the
mean of the products of the standard scores. Based on a sample
of paired data (Xi, Yi), the sample Pearson correlation coefficient is
defined in Eq. (5).
R = 1n 1
ni=1
Xi X
X
Yi Y
Y
(5)
where (Xi X)/X, X and Xare the standard score, sample mean,and sample standard deviation ofX. Table 1 shows theR values for
EMD and EEMD.
Table 1 also proves that EEMD has better resolution for the ana-
lyzed PQ events.
2.4. Hilbert-Huang TransformationMethod (HHT)
HHT represents the original signalX(t) into the time frequency
domain by combining the empirical mode decomposition with the
Hilbert transform. The advantage of using HHT for feature extrac-
tion procedure can be summarized in Table 2.
EMD can decompose signal into a finite number of n IMFs
(Cj, j = 1,2,3...,n), which extract the energy associated with variousintrinsic time scales and residual rn; this step is called the sifting
Table 1
Relation with first IMFs and current power signal.
Cross-Correlation EMD EEMD
IMFhealthy state 0.9762 1.0000
IMFvoltage sag 0.8819 0.9081
IMFvoltage swell 0.9300 0.9685
IMFvoltage flicker 0.9700 0.9950
IMFharmonics (3, 5, 7) 0.7855 0.7861
IMFtransient 0.5685 0.6104
IMFdc component 0.9244 0.9357
IMFEMI 0.5334 0.6429
IMFoutage 0.9313 0.9856
-
8/13/2019 Pantaz d. Vadim
5/8
196 O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199
Table 2
Comparison of frequently used mathematical methods for feature extraction [20,21].
Fourier STFT Wavelet HHT
Basis Non-adaptive Non-adaptive Non-adaptive Adaptive
Frequency Convolution: Global Convolution: Regional Convolution: Regional Differentiation: Local
Presentation Energy-frequency Energy-time-frequency Energy-time-frequency Energy-time-frequency
Non-linear No No No Yes
Non-stationary No No Yes Yes
Feature Extraction No Discrete: No Continuous: Yes Discrete: No Continuous: Yes Yes
Theoretical base Theory complete Theory complete Theory complete empirical
process described as in Eq. (6). IMFs, as a class of functions, satisfy
two definitions. In the whole data set, the number of extrema and
the number of zero-crossings must be either equal or differ at most
byone.At any point, the mean value of the envelope defined by the
local maxima and minima is zero.
TheHilbert transform is then applied to each IMF component Cj:
vj(t) =1
+
cj()
t d (6)
where cj(t) and vj(t) are real part and imaginary part of an analytic
signalzj(t):
zj(t) = cj(t)+jvj(t)zj(t) =Aj(t) exp(jwj(t))
(7)
With amplitude, (IA), andphase defined by the expressions:
IA(t) =
cj(t)2 + vj(t)2
j(t) = arctan
vj(t)
cj(t)
(8)Therefore, the instantaneous frequency (IF), was given by:
IF(t) = dj(t)dt
(9)
Thus, the original data can be expressed in the following form:
x(t) =n
j=1
Aj(t) exp
i
wj(t) dt
(10)
Figs. 4 and 5 show IA and IF curves for healthy and voltage sag
signals. Fig. 6 shows the IA values for all analyzed PQ events.
3. Singular valuedecomposition (SVD)
SVD is used for calculating singular values and increases the
accuracy of the classification algorithm. Singular values give more
Fig. 4. Instantaneous amplitude (IA) for healthy and voltage sag signal.
information for identification of the system. SVD is a part ofhierar-
chical classification on multiple feature groups in this study.
For any real mn matrixA, there exist orthogonal matrices
U= [u1, u2,...,um] Rmm,
V= [v1, v2,...,vm] Rnn,(11)
such that:
A = UVT (12)
where = diag(1, 2,...,min(m,n))) Rmn and 1 2 ...
min(m,n)0.
The iis the ith singular value ofA in non-increasing order andthe vectors uiand viare the ith left singular vector and the ith right
singular vector ofA for i=min(m,n), respectively [22]. The singular
values of matrix A are unique, while the singular vectors corre-
sponding to distinct singular values are uniquely determined up to
the sign.
Fig. 5. Instantaneous frequency (IF) for healthy and voltage sag signal.
Fig. 6. IA corresponding to first IMF for all disturbances.
-
8/13/2019 Pantaz d. Vadim
6/8
O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199 197
Fig. 7. Singular values for training data set.
Fig. 7 shows singular values for analyzed power signals. Fig. 7only shows 3 sets of data over 90 training data sets. In Fig. 7, SV1
represents singular values for the healthy signal, SV2 for voltage
sag, SV3 for voltage swell, SV4 for flicker, SV5 for harmonics, SV6
for transients, SV7 for DC component, SV8 for EMI and finally SV9
for the voltage interruption signal.
4. Support vectormachines (SVMs)
SVMs are a class of learning machines that find optimal hyper-
planes among different classes of input data or training data in a
high dimensional feature space F, and new test data can be clas-
sified using the individual hyper-planes. The optimal hyper-plane,
found during a trainingphase, makes the smallest number of train-
ing errors [23]. Fig. 8 illustrates an optimal hyper-plane for twoclasses of training data.
Let {xi,yi}, i=1,2,. . .,Nbe N training data vectors xi with classlabel yi. Given an input vectorx, an SVM constructs a classifier of
the form:
f(x) = sign
Ni=1
aiyiK(xi, x)+ b
(13)
where {ai} are non-negative Lagrange multipliers, each of which
corresponds to a training data, b is a bias constant, and K(.,.)
is a kernel satisfying the conditions ofMercers theorem [24,25].
Fig. 8. Optimal hyperplane.
Frequently used kernel functions are the polynomial kernelK(xi, xj) = (xi.xj + 1)d and Gaussian Radial Basis Function (RBF),K(xi, xj) = e|xixj|
2/22 .
The problem of finding the optimal hyperplane is specified by
the following quadratic programming problem:
Minimizing:
W(a) = N
i=1
ai +1
2
Ni=1
Nj=1
aiajyiyjK(xi, xj) (14)
subject to:
Ni=1
aiyi= 0 (15)
0 ai C, i = 1, 2,...,N
The above quadratic programming problem can be solved with
traditional optimization techniques. The vectors for which ai > 0
after optimization are called support vectors.
4.1. One-against-allmethod
For a k-class problem, the one-against-all method constructs k
SVM models. The ith SVM is trained with all of the training exam-
plesinthe ith class with positive labelsand theothers with negative
labels. The final output of the one-against-all method is the class
that corresponds to the SVM with the highest output value. Given
a set of training examples D{(x1, y1), (x2, y2),..., (xN, yN)}, wherethe ith samplexi Rn andyj {1,...,k} is the class ofxjthe ith SVMsolves the following optimization problem [2628] (where c> 0 is
a regularization parameter for the tradeoff between model com-
plexity and training error, and imeasuresthe (absolute)difference
betweenf(x) = (wi)T(x)+ bi andyi.):
min1
2(wi)
Twi + c
N
i=1
ij (16)
-
8/13/2019 Pantaz d. Vadim
7/8
198 O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199
Table 3
Comparisons of the performances of the one-against-all (OAA) and the one-against-one (OAO) SVM classifiers.
Total numberof training/testingsegments Classification (SVM) One Against All (OAA)OneAgainst One (OAO)
90/25 HS VSG VSW VF VH VTR VDC EMI VI
HS 32 0 0 0 0 0 0 0 0
VSG 1 22 0 0 0 0 0 0 0
VSW 0 0 22 1 0 0 0 0 0
VF 0 0 0 32 0 0 0 0 0
VH 0 0 0 0 33 0 0 0 0
VTR 0 0 0 0 0 43 0 1 0
VDC 0 0 0 0 0 0 33 0 0
EMI 0 0 0 0 0 1 0 32 0
VI 0 0 0 0 0 0 0 0 22
HS:healthy state,VSG: voltagesag,VSW:voltageswell,VF:voltageflicker, VH:voltage harmonics, VTR: voltagetransients, VDC:DCvoltage,EMI:electro magneticinterference.
Table 4
Number of measurement point [2931].
Number of measurement points
Voltage level Load type
Heavy Industry Industry + urban Urban only Total
NB NF NB NF NB NF NB NF
33 kV 8 16 17 28 14 16 39 60
154 kV 3 5 10 13 9 9 22 27
380 kV 1 1 4 7 0 0 5 8
Total 12 22 31 48 23 25 66 95
NB: numberof buses, NF: number of feeders.
subject to
(wi)T(xj) + bi 1 ij, yj= i
(wi)T(xj) + bi > 1 + ij, yj /= i
ji 0;j = 1,...,N
(17)
The decision function of the ithSVM is
f(x)=
(wi)T(x)+
bi (18)
A point x is in the class that corresponds to the largest value of
the decision functions: the class of
x = argmaxi=1,...,k(wi)T(x) + bi (19)A comparative study is carried out in the next section that com-
pares the performances of the OAO (one-against-one) and OAA
(one-against-all) decomposition methods in training the proposed
multiclass SVMs. The results of the application of the proposed
algorithm to the data set are presented in Table 3.
Diagonal elements represent the correctly classified PQ
disturbances while non-diagonal elements represent incorrect
classification results (Table 3).
5. Experimental results anddiscussions
To evaluate the performance of the proposedpower quality clas-
sification algorithm, a total of 115 PQ disturbance data were used.
The PQ signals in each class were divided into 90 training sets and
25 test sets. The polynomial kernel is used as the kernel function
and the parameter d is chosen as 2 in the SVM classifier. The exact
number of the training and testing segments for each PQ event
is shown in Table 2. Testing data were obtained from TUBITAK.
This is an ongoing project and is devoted to taking the nationwide
power quality figures of the Turkish Electricity Transmission Sys-
temthroughfield measurements carried outby application-specific
mobile monitoring equipment. In this project, PQ measurements
are being carried out according to IEC 610004-30, except for a
continuous seven-day sampling rate in the selected locations. In
the transmission system, most of the bus bars have more than one
incoming and outgoing feeder. Therefore, the number of measure-
ment points can be taken as the number of feeders for currents and
as the number of bus bars for voltages. The classification of these
points as heavy industry, urban + industrial, and urban sites are
given in Table 4, with respect to voltage level. It is noted that there
are more than 95 incoming and outgoing feeders at 33 measured
transformer substations [2931]. The real-time data are acquired
in 3 s, which corresponds to 150 periods.
The most accurate multi classifiers (OAA) for each PQ datasetare indicated by red font. As seen from Table 2, the OAA method
(Error = 0 %, Precision = 100%) is superior to the OAO method
(Error= 16%, Precision = 84%). Therefore, the OAA decomposition
methodis chosen for the multiclass SVM in this study.According to
the results of the test data, the effectiveness of the proposed SVM
algorithmis madesuitableby increasing the RBF kernel parameters
standard deviation (sigma0.1 to 1).The polynomial kernel is worse
than the RBF kernel due to the CPU time. It has been observed that
additional properties of the feature vectors such as singular values
increase the performance of classification algorithm. The perfor-
mance of SVM algorithm with OAA and OAO is calculated as 100%
and 84%, respectively. Nevertheless, the performance of SVM algo-
rithm decreases dramatically without using singular values of IF
and IA values and is calculated as 80% with OAA and 56% with OAO,respectively. Table 5 gives a comparison of the different classifiers
on the training and testing data.
Table 5
Comparison of performances of the different classifiers.
Classifier Error Accuracy Time (s)
SVM-Linear 0.4000 0.6000 2.136
SVM-Poly d= 2 0.0000 1.000 12.711
SVM-RBF sigma = 0.1 0.2800 0.7200 8.208
SVM-RBF sigma = 1 0.0000 1.000 10.686
Gauss Mixture Model 0.2555 0.7444 1.493
AdaBoost + Naive Bayes 0.0400 0.9600 3.529
Bagging + Naive Bayes 0.1600 0.8400 2.577
-
8/13/2019 Pantaz d. Vadim
8/8
O. Ozgonenel et al./ Electric Power Systems Research95 (2013) 192199 199
6. Conclusion
In this paper, a different PQ monitoring approach based on
EEMD, HHT, andSVM wasproposed. EEMD wasused forsignal con-
ditioning technique and two distinctive features, IA and IF, were
obtained by HHT. Then a series of statistical calculations was per-
formed to form feature matrix. The algorithm is found capable of
classifying many PQ disturbances with a high accuracy.
SVM with radial basis (sigma= 1) kernel function was used for
the decision-making unit and presented high accuracy among the
other classifiers. The proposed algorithm was applied to two sets
of data, one for generated data on a computer and the other for
the data obtained from TUBITAK. Practical applications showed
that the proposed hybrid algorithm can be used in power quality
monitoring software.
The analysis and results presented in this work clearly show the
potentialcapability of the suggested hybrid algorithmin classifying
the distorted PQ waveforms.
Acknowledgement
The authors wouldlike to thankTUBITAKfor supplyingreal-time
data.
References
[1] M.D.L. Angrisani, P. Daponte, A. Testa, A measurement method based on thewavelet transform for power quality analysis, IEEE Transactions on PowerDelivery 13 (4) (1988) 990998.
[2] D. Granados-Lieberman, R.J. Romero-Troncoso, R.A. Osornio-Rios, A. Garcia-Perez, E. Cabal-Yepez, Techniques and methodologies for power qualityanalysis and disturbances classification in power systems: a review, IET Gen-eration, Transmission & Distribution 5 (4) (2011) 519529.
[3] C . Mus cas, Powe r qu ality mon itor ing in mo der n electr ic distribu tionsystems, IEEE Instrumentation and Measurement Magazine 13 (2010)1927.
[4] P.J. Loughlin, J.W. Pitton, E. Les, Atlas, Proper time-frequency energy distribu-tionsand the Heisenberg uncertainty principle, in: Proceedings of The IEEE-SPInternational Symposium, Victoria, BC, Canada, 1992, pp. 151154.
[5] I. Daubechies, TenLectureson Wavelets, SIAM,Philadelphia, PA, 1992.
[6] S. Mallat, A theory for multiresolution signal decomposition: thewavelet representation, IEEE Transactions on Pattern Analysis 11 (1989)674693.
[7] R.R. Coifman, M.V. Wickerhauser, Entropy-based algorithms for best basisselection, IEEE Transactions on Information Theory 38 (1992) 713718.
[8] P. Kailasapathi, D. Sivakumar, Methods to analyze power quality disturbances,European Journal of Scientific Research 47 (1) (2010) 616.
[9] P.K. Dash, R.K. Jena, M.M.A. Salama, Power quality monitoring using an inte-grated Fourier linear combiner and fuzzy expert system, International JournalofElectrical Power 21 (1999) 497506.
[10] S. Suja,Jovitha Jerome, Pattern recognition of power signal disturbances usingS Transform and TT Transform, International Journal of Electrical Power 32(2010) 3753.
[11] P.K. Dash,S.K.Panda,A.C.Liew, B.Mishra, R.K. Jena,A new approachtomonitor-ing electric power quality, Electric Power Systems Research 46 (1998) 1120.
[12] M. Oleskovicz, D.V. Coury, O.D. Felho, W.F. Usida, A. driano, A.F.M. Carneiro,Leandro R.S. Pires, Power quality analysisapplying a hybrid methodology withwavelet transforms and neural Networks,Electric Power Systems Research 31(2009) 206212.
[13] S.A. Soliman, M.E. El-Hawary, Measurement of power systems voltage andflicker levels for power quality analysis: a static LAV state estimation based
algorithm, International Journal of Electrical Power 22 (2000) 447450.[14] S.A. Soliman, A.H. Mantaway, M.E. El-Hawary, Simulated annealing optimiza-
tion algorithm for power systems quality analysis, International Journal ofElectrical Power 26 (2004) 3136.
[15] M. Aiello, A. Cataliotti, S. Nuccio, A Chirp-Z transform-based synchronizer forpower system measurements, IEEETransactions on Instrumentation and Mea-surement 54 (2005) 10251032.
[16] G. Zheng,Shi Mei-Xiang,D. Liu,J. Yao,MiaoZhu-Mei, Power qualitydisturbanceclassification based on rule-based and wavelet-multi-resolution decomposi-tion, Proc. 2002 Int. Conf. Mach. Learn.Cybernetics 4 (2002)21372141.
[17] M. Uyar, S. Yildirim, M. Tunay Gencoglu, An effective wavelet-based featureextractionmethod for classification of power quality disturbance signals,Elec-tric Power Systems Research 78 (2008) 17471755.
[18] S. Kaewarsa, K. Attakitmongcol, T. Kulworawanichpong, Recognition of powerquality events by using multiwavelet based neural Networks, Electric PowerSystems Research 30 (2008) 254260.
[19] T. Jayasree, D. Devaraj, R. Sukanesh, Power quality disturbance classifica-tion using Hilbert transform and RBF Networks, Neurocomputing 73 (2010)14511456.
[20] N.E. Huang, Z.Shen,S.R.Long, M.C. Wu,H.H. Shih, Q.Zheng, N.C. Yen, C.C. Tung,H.H.Liu, Theempirical modedecomposition andthe Hilbert spectrumfor non-linear andnon-stationarytime series analysis, Proceedings of the Royal SocietyA-Mathematical Physical and Engineering Sciences 454 (1998) 903995.
[21] Z. Wu, N.E. Huang, Ensemble empirical mode decomposition: a noise-assisteddata analysismethod, Advances in Adaptive Data Analysis 1 (2009)141.
[22] G.H. Golub, C.F.V. Loan, Matrix Computations, The Johns Hopkins UniversityPress, Baltimore, MD, 1996.
[23] C. Cortes, V. Vapnik, Support-vector networks, Machine Learning 20 (1995)273297.
[24] V.N. Vapnik, Statistical Learning Theory, Wiley,New York, 1998.[25] Chih-Wei Hsu, Chih-Jen Lin, A comparison of methods for multiclass support
vector machines, IEEETransactionson Neural Networks13 (2)(2002)415425.[26] J.C. Platt, N. Cristianini, J. Shawe-Taylor, Large margin DAGs for multi-class
classification, Advances in Neural Information Processing Systems 12 (2000)547553.
[27] C.W. Hsu, C.J. Lin, A comparison of methods for multi-class support vectormachines, IEEE Transactions on Neural Networks 13 (2002) 415425.
[28] R. Rifkin, A. Klautau, In defense of one-vs-all classification, Journal of MachineLearning Research 5 (2004) 101141.[29] E.Ozdemirci,Y. Akkaya,et al.,Mobile monitoringsystemto takePQsnapshotsof
Turkish electricity transmissionsystem, in: Instrumentation and MeasurementTechnology Conference Proceedings, British Columbia, Canada, 2008, pp. 16.
[30] T. Demirci, A. Kalaycioglu, et al., National power quality monitoring networkand assessment center for the Turkish electricity transmission system: recentdevelopments,in: Signal Processing, Communicationand ApplicationsConfer-ence, Antalya, Turkey, 2008, pp. 14.
[31] http://www.guckalitesi.gen.tr/en/about/scope.php (last accessed 22.07.2012).