2. LIDULA AND RAJAPAKSE: PATTERN RECOGNITION APPROACH FOR DETECTING POWER ISLANDSāPART I 3071
Fig. 2. Basic model of the transient-based islanding detection technique.
complex set of features, including, total harmonic distortion of
current/voltage, gradient of the product of voltage and power
factor, etc. for classiļ¬cation. It has a misclassiļ¬cation rate
of 16.67% in islanding detection, which gives only 83.33%
islanding detection accuracy.
The method proposed in this paper differs from the previous
methods: this paper examines the use of a DT classiļ¬er in
identifying the islanding condition, instead of depending on
the threshold values determined by trial and error; furthermore,
it uses several wavelet coefļ¬cients corresponding to different
frequency bands of the current and voltage signal transients,
instead of using a complex set of indices.
II. PROPOSING ISLANDING DETECTION METHOD
The basic model of the passive islanding detection method
proposed in this paper is illustrated in Fig. 2. Transient wave-
forms of the currents and voltages in a power network contain
unique signatures that reveal the cause of the corresponding
transient event. The proposing islanding detection method is
based on the hypothesis that the transients generated during the
islanding event contain such a signature, and a classiļ¬er can be
developed to distinguish islanding events from the other distur-
bances. However, the event-speciļ¬c characteristics embedded in
the transient waveforms are not directly distinguishable. There-
fore, they need to be preprocessed to extract features that assist
fast classiļ¬cation response. Wavelet transformation is thus used
for this purpose. Reference [19] by the authors of this paper ex-
amines the use of different pattern-recognition techniques for
classifying islanding and nonislanding events using transient
signals. This paper concludes that DT performs better than prob-
abilistic neural networks or support vector machines. Based on
the conclusions arrived in [19], DT was used as the classiļ¬ca-
tion technique in this paper.
III. DT CLASSIFIER AND CART ALGORITHM
Pattern recognition involves different mathematical ap-
proaches to classify data (patterns) based either on a priori
knowledge or on statistical information extracted from the
patterns. There are ļ¬ve main components associated with a
classiļ¬cation problem:
1) Class (dependent variable): categorical outcome;
2) Features (independent variables): predictors/input vari-
ables;
3) Learning dataset: includes values of the Class and the cor-
responding Features;
4) Test dataset: used to test trained classiļ¬erās accuracy;
5) Misclassiļ¬cation cost: inherent cost associated with mis-
classifying future data.
Fig. 3. Example DT structure.
DT is a logical model constructed based on the training data,
and represented as a binary tree. The DT starts with the āRoot,ā
which contains whole training dataset. Each āInternal Nodeā
tests an attribute and each āArcā corresponds to an attribute
value. āTerminal Nodeā represents the predicted class [20]ā[22].
Fig. 3 shows a sample structure of a DT of a two-class problem.
Classiļ¬cation and regression trees (CART) [21]ā[24] is a
nonparametric technique that produces either classiļ¬cation or
regression trees, depending on whether the dependent variable
is categorical or numeric, respectively. The CART algorithm
generates DTs based on a splitting rule. The basic idea of the
splitting rule is to choose a split among all possible splits at
each node so that the resulting child nodes are the āpurest.ā The
splitting rule is processed in three steps as follows.
1) Find the best split of each predictor variable.
2) Find the best split of node.
3) Assign the class.
A brief explanation of the aforementioned steps is given in
the Appendix. A detailed explanation of the CART algorithm
can be found in [21]ā[24]. The CARTĀ® Pro V6 commercial soft-
ware [22] was used to develop the DT classiļ¬er. The āGini rule,ā
which works well with noisy data was selected as the splitting
rule. The concept behind the Gini rule is to search the learning
dataset for the largest class and to isolate it from the rest of the
data. The mathematical representation of the Gini rule is also
given in Appendix A. Besides the classiļ¬cation tree with sur-
rogates, CART provides a ranking of input features based on
each variableās contribution to the overall tree. It is determined
by looking at every node in which a variable appears as a pri-
mary splitter or as a surrogate splitter and totaling the accuracies
throughout the tree. Variable importance is presented by scaling
the values relative to the best performing variable, which is the
variable that minimizes the Gini impurity the most at every node
it considers to be a splitter.
IV. FEATURES USED FOR CLASSIFICATION
Wavelet transform is considered as an effective tool for
processing transient signals, which are nonstationary in nature.
Using the discrete wavelet transform (DWT), it is possible to
decompose a signal into several signals in different frequency
bands, which are known as wavelet coefļ¬cients. Due to the
wavelet transformās nature of adapting the time width of the
3. 3072 IEEE TRANSACTIONS ON POWER DELIVERY, VOL. 25, NO. 4, OCTOBER 2010
Fig. 4. Test system.
mother wavelet to its frequency, it is better suited to analyze
transients compared to other frequency-domain techniques,
such as windowed Fourier transform (WFT) [25]ā[31]. More-
over, DWT allows extracting a range of frequencies through a
single coefļ¬cient; the computational cost of obtaining the same
set of information through WFT would be much higher. A good
comparison of WFT and DWT can be found in [28].
The DWT of a sampled signal is mathematically deļ¬ned
as
(1)
where is the discretized mother wavelet given by
(2)
and are ļ¬xed real values, and and are
positive integers. The DWT analyzes a signal by decomposing
the signal into a coarse approximation and detail information.
The coarse approximation is decomposed again to obtain the
details of the next level, and so on. At each level of this suc-
cessive decomposition, the parameter in (2) is incremented
to increase the frequency resolution. Good reviews of wavelets
can be found in [27]ā[29].
V. SIMULATION RESULTS AND ANALYSIS
Simulation studies were carried out using PSCAD/EMTDC
power system simulation software. The distribution network de-
rived from the CIGRE MV benchmark system [32] shown in
Fig. 4 was simulated. It is a system with two DGs: a 1.5-MVA
induction generator (DG1) connected to bus-7 with 0.48 MVars
of capacitive compensation and a 1-MW, 100-kVar synchronous
generator (DG2) connected to bus-9. All loads in the network
were simulated as constant impedances. The system has two
switches S1, S2 (which are kept normally open), making it pos-
sible to change the network conļ¬guration from radial to ring
operation.
Two classes of events, namely ānon-islandingā and āis-
landingā were considered. The non-islanding cases simulated
include: 1) normal operation; 2) temporary faults, including
three phase to ground, three phase, line to line, and line to
ground; 3) switching of loads; and 4) switching of DGs. The
islanding cases simulated include: 1) opening of the breaker
B1; 2) opening of the feeder breakers B2 and B3, after fault
on Bus-2; and 3) opening of breakers B3, B4, and B5 after the
fault on Bus-3. The data were collected at different loading
conditions and under different system conļ¬gurations obtained
by opening and closing switch S1.
A total of 348 islanding and 539 non-islanding cases were
simulated and the three-phase currents and voltages measured
at the terminals of both DGs were recorded. Nearly 85% of the
data, which includes 279 islanding cases and 479 non-islanding
cases, were used for training. The remaining cases were used as
testing data. Testing data were extracted randomly from each
category of events described before to ensure testing against
all types of transient events. In testing the performance of the
proposed relay, the cross-validation procedure discussed in [19]
was applied to avoid the errors that could occur due to relying
on a particular data set.
A. Feature Extraction
As discussed in Section IV, the DWT was used to extract
the features for the classiļ¬ers. The DWT was performed on-
line in the PSCAD simulation program using the DWT compo-
nent developed in [33]. Phase current and voltage signals were
sampled at 10 kHz. The DWT was performed on the sampled
waveforms with the Daubechieās 4 (Db4) mother wavelet. The
approach for selecting the mother wavelet and sampling fre-
quency was a trial-and-error procedure combined with prior ex-
perience. The successful application of Db4 for characterizing
power system transients is reported in many studies [29]ā[31],
[33]. A comparison of the islanding detection performance with
several mother wavelets types during the preliminary investiga-
tions conļ¬rmed the suitability of Db4 mother wavelet. Further-
more, during the initial investigations, three sampling frequen-
cies: 20 kHz, 10 kHz, and 5 kHz, were considered [19], [34]. The
choice of 10-kHz sampling frequency for detailed studies was
based on the accuracy of classiļ¬cation, speed of detection, and
hardware cost/capability required for real-time implementation.
The frequency bands ļ¬ltered out by DWT at each level are in
accordance with the Mallat algorithm and Nyquistās rule. Table I
presents the frequency bands ļ¬ltered out along with the size
of mother wavelet at each level of DWT output. According to
[35], and of (2) are set to 2 and 1, respectively, in ap-
plying Mallatās algorithm. This results in a geometric scaling of
and translation by , which decom-
pose the input signal into subbands with a bandwidth that in-
creases exponentially with frequency. This scaling gives the
DWT logarithmic frequency coverage in contrast to the uniform
frequency coverage of Fourier transformation.
The original signals and the detail wavelet coefļ¬cients of the
current and voltage measured in phase- at DG1 (induction gen-
erator) terminals for 1) an islanding event, 2) a line-to-ground
high impedance fault, and 3) a load trip situation are shown in
Fig. 5(a) and (b). The disturbance is applied at 11.5 s, and DWT
coefļ¬cients are shown on an expanded scale that covers a time
window of 0.03 s, extending from 11.5 s to 11.53 s. In addi-
tion to the obvious variations in the range of amplitudes, there
4. LIDULA AND RAJAPAKSE: PATTERN RECOGNITION APPROACH FOR DETECTING POWER ISLANDSāPART I 3073
TABLE I
DB4 MOTHER WAVELET AT 10-kHz SAMPLING FREQUENCY
Fig. 5. (a). Original and DWT detail wavelet components of current signals.
(b). Original and DWT detail wavelet components of voltage signals.
are other noticeable differences between the islanding and non-
islanding events. Furthermore, it is clear that different nonis-
landing events themselves hold identities. Thus, an approach,
Fig. 6. Feature extraction methodology.
such as a simple threshold, cannot be used to distinguish be-
tween islanding and nonislanding events. Consequently, a more
sophisticated method, involving pattern recognition, is required.
Direct use of wavelet coefļ¬cients, which are essentially wave-
forms, as inputs to a classiļ¬er (in this case, to a DT) is imprac-
tical. Thus, energies associated with the wavelet coefļ¬cients in a
time window that encompass the transient were used as features
for the classiļ¬er. Wavelet energy is obtained by integrating the
square of the wavelet coefļ¬cient over a time window of 0.01 s.
The analysis uses a moving window, thus preserving the tem-
poral information. This time window length was selected after
preliminary investigations as a compromise between the accu-
racy and response time.
At each decomposition level, the energies of the three phases
were added to form a combined āthree-phase energyā value in
the particular frequency band. This feature extraction method is
illustrated in Fig. 6. Only the decomposition of Phase-a current
is shown in detail to reduce the complexity of the ļ¬gure. The
so-calculated āthree-phase energyā values of the currents and
voltages create a 12-D feature space (6 levels of currents 6
levels of voltages) for each generator, if the output of six levels
from the DWT is used.
B. Initial Classiļ¬er and Feature Selection
Initially, a DT was trained for DG1 using all 12 features.
When a DT is trained, the CART software produces an output
such as Table II, which indicates the importance of each input
feature to the classiļ¬cation process as a percentage of the values
relative to the best performing variable. In Table II, EVD and
EID denote the energy values of the level wavelet coefļ¬-
cient of the voltages and the currents, respectively. An analysis
of Table II shows that the relevancy of some of the features is
very low and they can be omitted without signiļ¬cantly reducing
the accuracy. After analyzing the tables for DG1 and DG2, it
was found that using only up to four decomposition levels is
sufļ¬cient.
C. DT-Based Classiļ¬er
Two different approaches were tested: 1) the development
of two separate classiļ¬ers for DG1 (induction generator) and
DG2 (synchronous generator) by training the classiļ¬ers sepa-
rately with the data measured at the respective generators and
2) the development of a single classiļ¬er using the waveforms
measured at both generators (DG1 and DG2).
1) Training a Separate Classiļ¬er for Each Generator:
Table III summarizes the results of the classiļ¬er trained for
induction generator (DG1) to identify islanding. The overall
5. 3074 IEEE TRANSACTIONS ON POWER DELIVERY, VOL. 25, NO. 4, OCTOBER 2010
TABLE II
IMPORTANCE OF FEATURES IN TRAINING A CLASSIFIER FOR DG1 TO IDENTIFY
ISLANDING USING A 12-D FEATURE SPACE
TABLE III
DT CLASSIFIER TRAINED FOR DG1
TABLE IV
DT CLASSIFIER TRAINED FOR DG2
TABLE V
DT CLASSIFIERāTRAINED FOR DG1 AND DG2
classiļ¬cation accuracy (accurate classiļ¬cation of islanding and
nonislanding as a percentage of the total data set) achieved in
testing the classiļ¬er was 99.22%. The depth of the DT (number
of nodes from the root to the farthest terminal node) was eight
nodes.
The results obtained with the classiļ¬er trained for the syn-
chronous generator (DG2) are summarized in Table IV. An
overall classiļ¬cation accuracy of 100% was achieved in testing
the classiļ¬er and the depth of the tree in this case was only ļ¬ve
nodes.
2) Training a Common Classiļ¬er for Both Generators: The
idea behind training a common classiļ¬er is that if this is suc-
cessful, identical classiļ¬ers can be used at all generators. The
results of this experiment are given in Table V.
The classiļ¬er trained for both generators gave 98.28% overall
accuracy on the training dataset. With the testing data for the
induction generator (DG1), it achieved an overall accuracy
of 99.22%, while achieving 100% accuracy in identifying is-
landing events. With testing data for the synchronous generator
(DG2), the classiļ¬er achieved 100% overall accuracy.
Fig. 7. DT classiļ¬er for detecting power system islands.
Thus, the classiļ¬er gives an overall accuracy of 99.61% when
both generators are considered. Based on the simulation exper-
iment that included 258 observations (considering both genera-
tors), it could be stated with 95% conļ¬dence [36] that:
1) relay dependability is greater than 95%;
2) relay security is greater than 96%;
3) relay overall accuracy is greater than 98%.
It should be noted that the data corresponding to normal oper-
ation (no transients) were excluded when calculating the accu-
racy values reported in Tables IIIāV. The trained classiļ¬ers were
found to be always accurate under normal operation. Thus, the
removal of normal operation cases results in more conservative
(lower) estimates for the accuracy.
Fig. 7 shows the DT structure of the classiļ¬er trained for both
generators. The depth of the tree is ļ¬ve nodes. This tree was
built in accordance to the CART algorithm (explained in the Ap-
pendix) by using the CARTĀ® Pro V6 commercial software [22].
The root (Node 1) has the total training data set. The percentage
values in each other node indicate how well the each splitter per-
forms in classifying the assigned class. For example, based on
the ļ¬rst splitter, that is, when 8483.74, a total of 535
cases were classiļ¬ed as Class-1 (non-islanding). Out of these,
only 533 actually belonged to Class-1; the other two belonged
to Class-2. With two misclassiļ¬ed cases, it gives 99.6% classi-
ļ¬cation accuracy at the particular splitter.
Features EVD1, EID1, EID2, and EID3 are not used in the
ļ¬nal DT, but they can be used as surrogate variables, that is, to
replace a particular variable from the ļ¬nal classiļ¬er if needed
(for example, to improve the noise immunity). Since the calcu-
lation of EID4 using the Mallet tree algorithm requires the cal-
culation of EID1, EID2, and EID3 as intermediate signals, the
feature extraction structure presented in Fig. 6 was retained.
The results presented before indicate that the common clas-
siļ¬er is able to give the same accuracy as separate classiļ¬ers in
identifying islanding, while keeping the depth of the tree smaller
than the separate classiļ¬er trained for DG1. Thus, the common
classiļ¬er was selected for further evaluation.
6. LIDULA AND RAJAPAKSE: PATTERN RECOGNITION APPROACH FOR DETECTING POWER ISLANDSāPART I 3075
Fig. 8. Process in the DT relay: (a) input signals, (b) DWT output, (c) Log
(ā3-phase wavelet energy contentsā), (d) transient signal detection (trigger), (e)
DT classiļ¬cation process, and (f) DT relay output.
D. Process of Islanding Detection
Fig. 8(a)ā(e) illustrates how the signals are processed through
the proposed method in the DT relay at DG1 for a sample is-
landing event (opening of breaker B3) that occurs at 11.5 s.
The feature extraction and classiļ¬cation process, which in-
volves the extraction of DWT coefļ¬cients, calculation of energy
content of wavelets, transient detection, and the processing in
the DT classiļ¬er is associated with a certain time delay.
Fig. 8(a) reveals that the transient appears in the input voltage
and current signals at the moment the disturbance occurred
( 11.5 s). However, as can be seen from Fig. 8(b)ā(d), the
DWT and energy content calculation introduces a delay of
about 0.0139 s for this particular islanding event.
The classiļ¬er is triggered by using a transient detector. Fig.
8(d) illustrates how the transient is detected by using the energy
content of the level four detail coefļ¬cient of the DG terminal
voltage (EVD4) in a sliding window of 0.0005 s. EVD4 was se-
lected as the trigger initiator considering its quality of showing
comparatively large variation in the event of a transient. If the
value of EDV4 exceeds a preset threshold value (2000), the clas-
siļ¬cation is carried out after a delay of 0.01 s. This delay is equal
to the window length for calculating wavelet energy values that
are fed to the classiļ¬er. The trigger threshold was set by studying
the data set. According to Fig. 8(d), the transient is detected at
11.5139 s and a trigger is generated after 0.01 s to acti-
vate the classiļ¬er. With already prepared inputs, the classiļ¬er
operation is almost instantaneous and, thus, the relay output is
generated at 11.5239 s. The response time of the proposed
relay for this particular islanding event is 0.0239 s (23.9 ms).
The relay shows a similar response, which was observed to be
always less than 24 ms at every islanding event tested.
VI. CONCLUSION
A fast and reliable islanding detection method based on
wavelet coefļ¬cients of transient signals was proposed. A
trained DT classiļ¬er was able to successfully categorize the
transient generating events as āislandingā or ānon-islandingā
using the energy associated with the wavelet coefļ¬cients. When
tested with a large number of test cases, the proposed technique
showed more than 95% dependability and over 96% security
at a 95% conļ¬dence level. This gave an overall classiļ¬cation
accuracy of more than 98%. The response time of the relay
remained below two cycles for all test cases.
Part II of this paper presents a performance evaluation of this
islanding detection method. It covers a comparison of the pro-
posed method with established passive methods of detecting
power islands under different scenarios, as well as the effects
of factors, such as measurement noise on the proposed power
islands detection method.
APPENDIX
The steps involved in learning a DT using the CART algo-
rithm are presented in the following sections.
A. Finding the Best Split of Each Predictor
In the CART algorithm, each split depends on the value of
only one predictor variable (input feature). It carries out a brute
force search through all possible splits to ļ¬nd the particular split.
Let
class
predictor variable
value of variable
learning data set
1) Tree Building Starts at the āRootā With the Variable
: If the predictor variable is an ordinal variable with
ā ā different values , there are different splits
on . The splits are found by sorting the values
from the smallest to the largest. For the purpose of illustra-
tion, let us take a sample case corresponding to Fig. 3. The
learning dataset , where is
given in Table VI. The size of the dataset is 10. Table VI
also shows the sample dataset when sorted by predictor
7. 3076 IEEE TRANSACTIONS ON POWER DELIVERY, VOL. 25, NO. 4, OCTOBER 2010
TABLE VI
SAMPLE DATASET TO EXPLAIN THE SELECTION OF SPLIT POINTS
Fig. 9. Example on goodness of split calculation.
TABLE VII
GOODNESS OF SPLIT VALUES AT EACH POSSIBLE SPLIT OF X
are possible āsplit
pointsā of . At each possible āsplit pointā of the variable,
the sample is split into two child nodes. Cases with a āyesā
response to the question posed are sent to the left node and
those with ānoā responses are sent to the right node.
2) Application of the Splitting Rule: There are different split-
ting rules: āGini rule,ā āTwoing rule,ā āOrdered ruleā etc.
Gini rule works well for noisy data and it is used in this study
to ļ¬nd the best split [21]. The basic idea behind the Gini rule is
to search the learning dataset for the largest class and to isolate
it from the rest of the data. The mathematical representation is
as follows. Let
node number;
class probability distribution of the dependent
variable at node t;
impurity measure at node ;
particular split;
proportion of cases at node that go into the left
child node ;
proportion of cases at node that go into the right
child node ;
impurity of the left child node;
TABLE VIII
MAXIMUM GOODNESS OF SPLIT VALUES OF EACH PREDICTOR X
impurity of the right child node;
goodness of split at node .
For a particular split at node , the Gini impurity measure
is deļ¬ned as
(A1)
If priors are proportional to data, then these probabilities are
the observed relative frequencies of each class at the node .
Therefore
(A2)
Once the impurity measure is calculated, then the goodness
of split is calculated
(A3)
The best split point is the one that maximizes the
when the node is split according to it.
As an example, the calculation for split point
7.9 at the Root node is presented in Fig. 9, and
of all possible split points of is given in Table VII. From the
table, 7.9 has the largest and, thus, the best
split of .
B. Find the Best Split of the Node
To ļ¬nd the best split of the node, the aforementioned two
steps are repeated for each of the remaining variables at the
Root, and the best splits on each variable are ranked according
to the . The algorithm then selects the variable and its
split point that minimized the impurity of the Root.
As an illustration, Table VIII presents the best splits of each
predictor with their values. It shows that it is possible
to select either 7.9 or 78 as the best split
of the Root. If 7.9 is selected, 78 would
be a surrogate splitter (a splitting rule that closely mimics the
primary split).
C. Class Assignment
There are two rules for assigning classes to nodes that can be
described as follows.
1) Assign terminal node to a class for which is the
highest. The rule assumes equal misclassiļ¬cation costs for
each class (refer to Fig. 3).
2) Assign terminal node to a class for which the expected
misclassiļ¬cation cost is at a minimum. The application of
this rule takes the severity of the costs of misclassifying
cases or observations in a certain class into account, and in-
corporates cost variability into a Gini splitting rule, which
needs to be modiļ¬ed accordingly.
The CART algorithm does not use a stopping rule. It con-
tinues growing the classiļ¬cation tree repeatedly applying the
8. LIDULA AND RAJAPAKSE: PATTERN RECOGNITION APPROACH FOR DETECTING POWER ISLANDSāPART I 3077
aforementioned three steps at each child node until further split-
ting is impossible. When the maximal tree is found, CART ex-
amines smaller trees by pruning away the possible branches.
The best tree is determined by testing for error rates or costs
[21], [22].
REFERENCES
[1] N. Jenkins, R. Allan, P. Crossley, D. Kirschen, and G. Strbac, Em-
bedded Generation. London, U.K.: Inst. Elect. Eng., 2000.
[2] H. B. PĆ¼ttgen, P. R. Macgregor, and F. C. Lambert, āDistributed gener-
ation: Semantic hype or the dawn of a new era?,ā IEEE Power Energy
Mag., vol. 1, no. 1, pp. 22ā29, Jan./Feb. 2003.
[3] A. M. Borbely and J. F. Kreider, Distributed GenerationāThe Power
Paradigm for the New Millennium. Boca Raton, FL: CRC, 2001.
[4] G. Hodgkinson, āSystem implications of embedded generation and
its protection and control-PES perspective,ā Inst. Elect. Eng. Colloq.
System Implications of Embedded Generation Protection Control,
1998, (Digest No. 1998/277).
[5] T. Y. Ismall, āThe implications of embedded generation on the ngc
transmission system,ā Inst. Elect. Eng. Colloq. System Implications of
Embedded Generation Protection Control, 1998, (Digest No. 1998/
277).
[6] G. Carpinelli, G. Celli, F. Pilo, and A. Russo, āDistributed generation
siting and sizing under uncertainty,ā in Proc. IEEE Power Tech., Porto,
Portugal, 2001, vol. 4, p. 7.
[7] M. E. H. Golshan and S. A. Areļ¬far, āDistributed generation, reactive
sources & network-conļ¬guration planning for power & energy-loss re-
duction,ā Proc. Inst. Eng., Gen., Transm. Distrib., vol. 153, no. 2, pp.
127ā136, Mar. 2006.
[8] Interconnecting Distributed Resources With Electric Power Systems,
IEEE Std. 1547-2003, 2003.
[9] R. A. Walling and N. W. Miller, āDistributed generation is-
landingāImplications on power system dynamic performance,ā
in Proc. IEEE Power Eng. Soc. Summer Meeting, 2002, vol. 1, pp.
92ā96.
[10] W. Freitas, W. Xu, C. M. Affonso, and Z. Haung, āComparative anal-
ysis between ROCOF and vector surge relays for distributed genera-
tion applications,ā IEEE Trans. Power Del,, vol. 20, no. 2, pt. 2, pp.
1315ā1324, Apr. 2005.
[11] J. E. Kim and J. S. Hwang, āIslanding detection method of distributed
generation units connected to power distribution system,ā in Proc. Pow-
erCon, Perth, Western Australia, 2000, vol. 2, pp. 643ā647.
[12] W. Freitas, Z. Huang, and W. Xu, āA practical method for assessing the
effectiveness of vector surge relays for distributed generation applica-
tions,ā IEEE Trans. Power Del., vol. 20, no. 1, pp. 57ā63, Jan. 2005.
[13] T. Funabashi, K. Koyanagi, and R. Yokoyama, āA review of islanding
detection methods for distributed resources,ā in Proc. IEEE Bologna
Power Tech Conf. , 2003, vol. 2, pp. 6ā11.
[14] H. H. Zeineldin, E. F. El-Saadany, and M. M. A. Salama, āDistributed
generation micro-grid operation: Control & protection,ā in Proc. Power
Systems Conf.: Advanced Metering, Protection, Control, Communica-
tion, and Distributed Resources, 2006, pp. 105ā111.
[15] Y.-H. Liy, T.-S. Luor, S.-J. Huang, and J.-M. Lin, āMethod and
System for Detecting Stand-Alone Operation of a Distributed Gener-
ating System,ā U.S. Patent 7 342 758, Mar. 2008.
[16] C.-T. Hsieh, J.-M. Lin, and S.-J. Huang, āEnhancement of is-
landing-detection of distributed generation systems via wavelet
transform-based approaches,ā Int. J. Elect. Power Energy Syst., vol.
30, no. 10, pp. 575ā580, Dec. 2008.
[17] A. Pigazo, V. M. Moreno, M. Liserre, and A. DellāAquila, āWavelet-
based islanding detection algorithm for single-phase PV distributed
generation systems,ā in Proc. IEEE Int. Symp. Industrial Electronics,
Vigo, Spain, pp. 2409ā2413.
[18] K. El-Arroudi, G. JoĆ³s, I. Kamwa, and D. T. McGillis, āIntelligent-
based approach to islanding detection in distributed generation,ā IEEE
Trans. Power Del., vol. 22, no. 2, pp. 828ā835, Apr. 2007.
[19] N. W. A. Lidula, N. Perera, and A. D. Rajapakse, āInvestigation of a
fast islanding detection methodology using transient signals,ā in Proc.
IEEE Power Energy Soc. General Meet., 2009, pp. 1ā6.
[20] Y. Sheng and S. M. Rovnyak, āDecision tree-based methodology for
high impedance fault detection,ā IEEE Trans. Power Del., vol. 19, no.
2, pp. 533ā536, Apr. 2004.
[21] B. Leo, J. Friedman, R. Olshen, and C. Stone, Classiļ¬cation and Re-
gression Trees. Belmont, CA: Wadsworth, 1984.
[22] D. Steinberg and P. Colla, CART: Tree-Structured Non-Parametric
Data Analysis. San Diego, CA: Salford Systems, 1995.
[23] Y. Yohannes and P. Webb, āClassiļ¬cation and regression trees,
cart TMāA user manual for identifying indicators of vulnerability
to famine and chronic food insecurity,ā Microcomputers in Policy
Research 3, Int. Food Policy Res. Inst., 1999.
[24] L. Bel, D. Allard, J. M. Laurent, R. Cheddadi, and A. Bar-Hend,
āCART algorithm for spatial data: Application to environmental
and ecological data,ā Comput. Stat. Data Anal., vol. 53, no. 8, pp.
3082ā3093, Jun. 2009.
[25] S. Chen, āFeature selection for identiļ¬cation and classiļ¬cation of
power quality disturbances,ā in Proc. IEEE Power Eng. Soc. General
Meet., 2005, vol. 3, pp. 2301ā2306.
[26] D. C. Robertson, O. I. Camps, J. S. Mayer, and W. B. Gish, āWavelets
and electromagnetic power system transients,ā IEEE Trans. Power
Del., vol. 11, no. 2, pp. 1050ā1058, Apr. 1996.
[27] I. Daubechies, Ten Lectures on Wavelets. Philadelphia, PA: SIAM,
1992.
[28] A. Graps, āAn introduction to wavelets,ā Comput. Sci. Eng., vol. 2, no.
2, pp. 50ā61, Jun. 1995.
[29] C. H. Kim and R. Agganrval, āWavelet transforms in power sys-
temsāPart 1: General introduction to the wavelet transforms,ā IEEE
Power Eng. J., vol. 14, no. 2, pp. 81ā87, Apr. 2000.
[30] C. H. Kim and R. Agganrval, āWavelet transforms in power sys-
temsāPart 2: Examples of application to actual power system
transients,ā IEEE Power Eng. J., vol. 15, no. 4, pp. 193ā202, Apr.
2000.
[31] H. A. Darwish, M. H. Farouk, A.-M. I. Taalab, and N. M. Mansour, āIn-
vestigation of real-time implementation of DSP-based dwt for power
system protection,ā in Proc. IEEE Power Eng. Soc. Transmission and
Distribution Conf. Exhibit., 2005/2006, pp. 1258ā1263.
[32] CIGRE C6.04.02 Task Force, Benchmark modeling and simulation for
analysis, design, and validation of distributed energy systems. Sep.
2006.
[33] N. Perera and A. D. Rajapakse, āRapid isolation of faults in power net-
works with distributed generators,ā M.Sc. dissertation, Univ. Manitoba,
Winnipeg, MB, Canada, May 2007.
[34] N. W. A. Lidula and A. D. Rajapakse, āFast and reliable detection of
power islands using transient signals,ā presented at the IEEE Int. Conf.
Industrial and Information Systems, Dec. 28ā31, 2009, paper 1050395.
[35] T. Frederick and N. Erdol, āArbitrary tilings of phase space,ā in Proc.
IEEE Int. Conf. Accoustics, Speech, and Signal Processing, 1994, vol.
3, pp. III/25āIII/28.
[36] D. C. Montgomery, G. C. Runger, and N. F. Hubel, Engineering Sta-
tistics. New York: Wiley, 1998.
N. W. A. Lidula (Sā09) received the B.Sc. (Eng.)
degree from the University of Moratuwa, Sri Lanka,
in 2002, the M.Eng. degree from the Asian Institute
of Technology, Bangkok, Thailand, in 2006, and the
Ph.D. degree in electrical and computer engineering
from the University of Manitoba, Winnipeg, MB,
Canada.
Her research interests are in distributed and renew-
able energy systems.
A. D. Rajapakse (Mā99āSMā08) received the B.Sc.
(Eng.) degree from the University of Moratuwa,
Katubedda, Sri Lanka, in 1990, the M.Eng. degree
from the Asian Institute of Technology, Bangkok,
Thailand, in 1993, and the Ph.D. degree from the
University of Tokyo, Tokyo, Japan, in 1998.
Currently, he is an Assistant Professor at the
University of Manitoba, Winnipeg, MB, Canada. His
research interests include power system protection,
transient simulation of power and power-electronic
systems, as well as distributed and renewable energy
systems.
Dr. Rajapakse is a Registered Professional Engineer in the Province of Man-
itoba, Canada.