International Journal of Power Electronics and Drive Systems (IJPEDS)

Vol. 14, No. 2, June 2023, pp. 1033~1043

ISSN: 2088-8694, DOI: 10.11591/ijpeds.v14.i2.pp1033-1043  1033

Detection of power transmission lines faults based on voltages

and currents values using K-nearest neighbors

Nisreen Khalil Abed, Faisal Theyab Abed, Hamdalla F. Al-Yasriy, Haider TH. Salim ALRikabi
Department of Electrical Engineering, College of Engineering, Wasit University, Al Kut, Iraq

Article Info ABSTRACT

Article history: The critical factors to consider when implementing a maintenance plan for
energy transmission lines are, accuracy, speed, and time, because of the
Received Dec 26, 2022 increased global demand for electricity power caused by rapid development,
Revised Feb 12, 2023 and overuse of electric power transmission lines (both underground cables and
Accepted Feb 29, 2023 overhead transmission lines), which in turn reduces the efficiency of the lines.
Consequently, the efficiency of the lines may be reduced as a result of overuse
or other activities like excavation that may have tampered with the cables.
Keywords: Thus, it becomes important to investigate the faults to which the lines are
exposed. To this end, this article focuses on the detection of fault in
Faults detection transmission lines through the use of k-nearest neighbor algorithm. Using this
Input features algorithm, the characteristics were obtained (voltage, current), and these
K-nearest neighbor algorithm characteristics enable the identification of faults in the transmission lines, and
Output features in the specific location (the entire system, phase B, and phase A). The benefits
Transmission line that can be derived from the use of this algorithm include time, accuracy,
speed, which are the requirements for the maintenance of transmission lines.
Euclidean distance used in the application of the k-nearest neighbor technique
for weights, and K = 3 for number of neighbors. The dataset was split into two
parts, 70% training set and 30% testing set.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Haider TH. Salim ALRikabi
Department of Electrical Engineering, College of Engineering, Wasit University
Al Kut, Iraq
Email: [email protected]

1. INTRODUCTION
Presently, the cost of developing electric power transmission lines is higher than ever before, because
of the higher demand for electricity. This high cost covers for power generation, transmission, and distribution
as contained in Figure 1 [1]. The performance of these transmission lines is affected by heavy and continuous
use, as well as other external factors [2]. Undetected faults can be a major obstacle in the functioning of any
power system, as they can stop the operation of the entire electrical system [3]–[5]. There are different kinds
of faults that can be found in transmission lines, and these different faults can be categorized as either
asymmetric or symmetrical. An example of such faults that can arise in transmission lines include phase fault
such as phase-to-ground fault, phase-to-phase fault, phase-to-earth fault, and three-phase fault. Nevertheless,
there presence does not affect the functionality of the power system. More so, other faults like overlapping
faults, circuit fault, and other faults are faults that are also regarded as unimportant faults compared to the
aforementioned faults. Traditionally, these lines are maintained through the use of megger device which
facilitates the detection of faults. Alternatively, the faults are also detected through physical inspection of lines
[6]–[12]. These two methods are time-consuming, and as such, countries around the world are exploring new
ways through which the faults can be detected and addressed within a short period of time. In this work the
ability of the k-nearest neighbor (KNN) algorithm to detect the faults is explored, and the specific kind of fault

Journal homepage: http://ijpeds.iaescore.com

1034  ISSN: 2088-8694

is identified through the use of MATLAB software, whether phase-ground fault or phase-to-phase fault. The
elements that should be considered when a fault is detected in any type of power system include voltage,
current, resistance, power factor, and frequency. Several techniques of fault detection show the presence of a
fault by comparing the post-fault values with the pre-fault values of the systems.

Figure 1. Power system structure [1]

2. A LITERATURE SURVEYS
A wide range of approaches and techniques have been used in the detection of faults in electric power
transmission lines. In the work done by Muir and Lopatto a new method was introduced; the method helps in
detecting fault in digital relays-based power system through the use of Petri nets [1]. The authors made use of
Petri nets for modelling and detection of location, and with the proposed technique, the power system is
monitored in a hierarchical manner. Their experimental results revealed that the use of Petri nets reduced the
time required to process information, and the precision of fault detection increased. As early as in 1994, the
use of microprocessors was employed by Barros and Drake to detect faults in real time [13] based on the
estimation of the three phase voltage phasors by mean of a set of Kalman filters, and on the calculation of the
fault probability. Subsequently, in 2004, wavelet transform was proposed by [3] for the detection of fault in a
transformer by measuring neural currents. The analysis of the wavelet transform was carried out based on the
Morlet wavelet (mother wavelet). It was concluded that significant improvement was achieved in terms of the
fault detection sensitivity by the use of wavelet analysis approaches for the assessment of impulse tests on
transformer. Similar efforts geared towards fault detection were made by Bracho and Martinez [14], who used
dynamic power supply current test in 1997. Subsequently, in 1998, Chowdhury and Aravena [15] introduced
a new technique through which faults can be detected by the use of a modular methodology. The method which
is relatively flexible also allows classification in power system. Upon detection of the fault, the fault indicator
is processed by a Kohonen network for the classification of faults. Abed and AlRikabi [8] who presented a
conference paper in 2021 focused on the detection of faults in underground cables as transmission lines, used
IoT applications to monitor and detect underground cable faults. In the work done by Majd et al. [16], the
protection and control of power systems were investigated. In their work, a technique for the detection of
transmission line faults was presented. In their proposed approach, the use of KNN based fault detection and
classification approaches was employed. Similar efforts made by Samet et al. [17] led to the production of a
technique for the detection and classification fault for transmission lines through; the authors used an improved
alienation coefficients method. In the research carried out by Gafoor and Rao, a wavelet-based fault detection
technique was proposed. The proposed technique is able to detect, classify faults as well as the location of the
fault in the transmission lines [18], [19].

3. THE PROPOSED METHOD

The dataset used in this work was used in modeling a power system in MATLAB was simulated for
fault analysis. As seen in Figure 2, the power system is made up of four power generators of 11×10^3 V, with
each pair sitting at the end of the transmission line. Transformers are present in between for the simulation and
investigation of different faults ta the midpoint of the transmission line.
The authors of the database carried out the simulation of the circuit under both normal conditions and
abnormal conditions (with faults). Afterwards, they collected and saved the measured line voltages and line
currents at the power system’s output side. Here, about 12000 data points were collected, and then the data was

Int J Pow Elec & Dri Syst, Vol. 14, No. 2, June 2023: 1033-1043
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1035

labeled. The dataset can be accessed through Kaggle [20]–[22]. The dataset is made up of input features
including voltages (Va, Vb, Vc) and currents (Ia, Ib, Ic) of the three phases, the description of statistics of the
input features as seen in Table 1, as well as their histogram distribution as presented in Figure 3 (see Appendix).

Figure 2. Power system diagram [20], [21]

Table 1. Statistics description of input features

Statistics Ia Ib Ic Va Vb Vc
Mean 25.476 -26.633 -0.607 0.002 -0.002 -0.001
Median 8.195 -0.118 -8.573 -0.002 -0.001 0.005
Mode -9.677 -93.940 85.800 0.000 -0.115 0.136
Minimum -883.542 -900.527 -900.527 -0.621 -0.608 -0.613
Maximum 885.739 889.869 901.274 0.606 0.628 0.600
Count 14395 14395 14395 14395 14395 14395

Also contained in the database are the values for the outputs (G, A, B, C), which possess just two
values; the value of 0 denotes no fault, while the value of 1 denotes the presence of faults. In this work,
additional output parameter (S) has been added to the entire system. Figure 4 (see Appendix) shows the
distribution of the output features. A summary of the dataset is presented using the correlation matrix in Table 2,
which presents the correlation between all features, whereby, the value-100% represents a perfectly negative
linear relationship between all feature, while the value 0% means there is no linear relationship between two
features, and the value 100% denotes a perfectly positive linear relationship between two features.

Table 2. Correlation matrix of features

Ia Ib Ic Va Vb Vc FG FC FB FA FS
Ia 100%
Ib -31.31% 100%
Ic -30.72% -33.58% 100%
Va 10.93% -1.39% 12.32% 100%
Vb -14.41% 2.84% 10.37% -53.31% 100%
Vc 1.93% -1.22% 3.48% 58.01% -37.99% 100%
FG -1.16% 2.56% -1.87% 2.11% -1.60% -0.78% 100%
FC -0.06% -3.07% 2.53% 1.26% -3.87% 2.34% 9.20% 100%
FB -0.06% -8.19% 7.71% 1.26% -4.23% 2.69% 9.20% 8.88% 100%
FA 6.05% -7.54% 0.88% 0.99% -3.23% 2.03% 9.20% 8.88% 8.88% 100%
FS 3.38% -6.19% 2.97% 2.99% -4.86% 1.42% 49.05% 47.11% 47.11% 47.11% 100%

Detection of power transmission lines faults based on voltages … (Nisreen Khalil Abed)
1036  ISSN: 2088-8694

4. METHOD
4.1. K-nearest neighbor
A KNN algorithm can be described as simple and efficient supervised machine learning method
employed in regression and classification operations [23]–[25]. Given that, the algorithm carries out
classification directly and based on the training examples, it is categorized as case-based classification or
example-based classification it classified as example-based classification, or case-based classification [26].
This algorithm performs the classification operation based on similarity criteria, giving consideration to the
distance measure. Here, "K" denotes the integer value that ranges from 3 to +10. Compared to even values, the
odd values are mostly preferred when seeking to get a good prediction. A given class is selected based on
majority votes given by neighboring points that correspond to the nearest class. The neighbors are assigned
weights so that the nearer neighbor adds more weight to the average that that of the farther one. Weights are
assigned to the assigned to the neighbors based on their Euclidean distance [27]. A flowchart for KNN
algorithm modeling is shown in Figure 5.

Figure 5. A simple flowchart for the k-nearest neighbor modeling [28]

The detection of faults in transmission lines is carried in five stages. In the first stage, the faults in
phase will be detected, followed by the second stage which involves the detection of faults in phase B. in the
third stage, the fault in phase C is detected, and followed by the detection of fault in the ground, and lastly, the
overall faults in the entire system are detected. The operations are performed according to the values of currents
and voltages. The application of these values is done in the following manner: phase A only features, phase B
only features, phase C only features, phase A and phase B features, phase A and phase C features, phase B and
phase C features, voltages only features, currents only features, and all features. The application of the KNN
technique involved the use of Euclidean distance for weights, while K = 3 for number of neighbors. The dataset
was divided into two for training and testing, with 70% of the dataset designated for training the algorithm,
and 30% for testing it. Table 3 shows the kind of features that were used in this paper.

Int J Pow Elec & Dri Syst, Vol. 14, No. 2, June 2023: 1033-1043
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1037

Table 3. Describtion of features

Types of features Features Number of features
Phase A only Ia, Va 2
Phase B only Ib, Vb 3
Phase C only Ic, Vc 3
Phase A and phase B Ia, Va, Ib, Vb 6
Phase A and phase C Ia, Va, Ic, Vc 6
Phase B and phase C Ib, Vb, Ic, Vc 6
Voltages only Va, Vb, Vc 3
Currents only Ia, Ib, Ic 3
All features Va, Vb, Vc, Ia, Ib, Ic 9

5. RESULTS AND DISCUSSION

Majority of the parameters used in measuring the performance of the algorithm are based on the
confusion matrix, are classified as ‘True’ prediction/reality matches (TP and TN) and ‘False’ non-matches or
errors (FP and FN) [29].
− True positive, means that the actual and predicted outcomes both fall under “faults” class.
− False positive, means that the predicted is in faults class whereas the actual is classified as “no fault” class.
− False negative, means the predicted fault is classified as “no fault”, while the actual is classified under
“fault class”.
− True negative, means that both the predicted and actual faults are classified as “no fault”. the values of true
positives, false positives, true negatives and false negatives is shown in the Tables 4 and 5.

Table 4. Confusion matrix of fault detection phases A, B, and C

Fault detection in phase A Fault detection in phase B Fault detection in phase C
Features
TN TP FP FN TN TP FP FN TN TP FP FN
Phase A only 2,197 2,053 36 33 1,198 958 1,086 1,077 1,188 945 1,121 1,065
Phase B only 1,539 1,342 694 744 2,183 1,983 101 52 1,681 1,408 628 602
Phase C only 1,349 1,182 884 904 1,332 1,194 952 841 2,165 1,955 144 55
Phase A and phase B 2,225 2,067 8 19 2,221 2,005 63 30 2,140 1,807 169 203
Phase A and phase C 2,223 2,066 10 20 2,150 1,831 134 204 2,240 1,983 69 27
Phase B and phase C 2,131 1,886 102 200 2,240 2,018 44 17 2,216 1,982 93 28
Voltages only 2,158 2,029 75 57 2,180 1,985 104 50 2,222 1,924 87 86
Currents only 2,233 2,078 0 8 2,242 2,027 42 8 2,260 2,007 49 3
All features 2,233 2,078 0 8 2,242 2,027 42 8 2,260 2,007 49 3

Table 5. It shows the faults detection of phases in the ground and system
Fault detection in ground Fault detection in system
Features
TN TP FP FN TN TP FP FN
Phase A only 2,089 1,416 291 523 3,440 475 152 252
Phase B only 1,928 1,444 452 495 3,442 536 150 191
Phase C only 2,131 1,415 249 524 3,442 558 150 169
Phase A and phase B 2,114 1,699 266 240 3,572 717 20 10
Phase A and phase C 2,078 1,687 302 252 3,576 716 16 11
Phase B and phase C 2,130 1,699 250 240 3,562 710 30 17
Voltages only 2,145 1,708 235 231 3,563 710 29 17
Currents only 2,235 1,789 145 150 3,582 727 10 0
All features 2,235 1,789 145 150 3,582 727 10 0

The proposed models were evaluated based on parameters in the confusion matrix including accuracy,
sensitivity, specificity, and precision. Accuracy refers to the ratio of total number of correct faults and no faults
predictions to sample size [29]. Sensitivity (recall) is the measure of faults points that correctly detected [30].
Specificity is the measure of no-fault points that are detected correctly [30]. Precision or confidence is the
measure of predicted faults that are actual faults [31]. These metrics were calculated for the results of the
methods that were used in this work. The results are presented in Tables 6 and 7.
For the detection of faults phase, A, only currents were used as input features, and optimal results
were obtained, which will be the same even if all features are used as inputs. Very good results were obtained
when the features of phase A were used (phase A only, phase A and phase B, phase A and phase C). Also, the
result obtained from the use of only voltages is better than the results of the features used in phase B and
phase C. For the detection of faults phase B, only currents were used as input features, and optimal results were
obtained, which will be the same even if all features are used as inputs. Very good results were obtained when

Detection of power transmission lines faults based on voltages … (Nisreen Khalil Abed)
1038  ISSN: 2088-8694

the features of phase B were used (phase B only, phase A and phase C, phase B and phase C). Also, the result
obtained from the use of only voltages is better than the results of the features used in phase B and phase C.

Table 6. Performance metrics of the accuracy, precision, and sensitivity of the phases
Fault detection in phase A Fault detection in phase B Fault detection in phase C
Features
Acc Pr Se Sp Acc Pr Se Sp Acc Pr Se Sp
Phase A only 0.984 0.983 0.984 0.984 0.499 0.469 0.471 0.525 0.494 0.457 0.470 0.515
Phase B only 0.667 0.659 0.643 0.689 0.965 0.952 0.974 0.956 0.715 0.692 0.700 0.728
Phase C only 0.586 0.572 0.567 0.604 0.585 0.556 0.587 0.583 0.954 0.931 0.973 0.938
Phase A and phase B 0.994 0.996 0.991 0.996 0.978 0.970 0.985 0.972 0.914 0.914 0.899 0.927
Phase A and phase C 0.993 0.995 0.990 0.996 0.922 0.932 0.900 0.941 0.978 0.966 0.987 0.970
Phase B and phase C 0.930 0.949 0.904 0.954 0.986 0.979 0.992 0.981 0.972 0.955 0.986 0.960
Voltages only 0.969 0.964 0.973 0.966 0.964 0.950 0.975 0.954 0.960 0.957 0.957 0.962
Currents only 0.998 1.000 0.996 1.000 0.988 0.980 0.996 0.982 0.988 0.976 0.999 0.979
All features 0.998 1.000 0.996 1.000 0.988 0.980 0.996 0.982 0.988 0.976 0.999 0.979

Table 7. It shows that the Performance metrics of accuracy, precision, and sensitivity of the phases with
ground and the system
Fault detection in ground Fault detection in system
Features
Acc Pr Se Sp Acc Pr Se Sp
Phase A only 0.812 0.830 0.730 0.878 0.906 0.758 0.653 0.958
Phase B only 0.781 0.762 0.745 0.810 0.921 0.781 0.737 0.958
Phase C only 0.821 0.850 0.730 0.895 0.926 0.788 0.768 0.958
Phase A and phase B 0.883 0.865 0.876 0.888 0.993 0.973 0.986 0.994
Phase A and phase C 0.872 0.848 0.870 0.873 0.994 0.978 0.985 0.996
Phase B and phase C 0.887 0.872 0.876 0.895 0.989 0.959 0.977 0.992
Voltages only 0.892 0.879 0.881 0.901 0.989 0.961 0.977 0.992
Currents only 0.932 0.925 0.923 0.939 0.998 0.986 1.000 0.997
All features 0.932 0.925 0.923 0.939 0.998 0.986 1.000 0.997

For the detection of faults phase C, only currents were used as input features, and optimal results were
obtained, which will be the same even if all features are used as inputs. Very good results were obtained when
the features of phase C were used (phase C only, phase A and phase C, Phase B and phase C). Also, the result
obtained from the use of only voltages is better than the results of the features used in phase A and phase B.
For ground fault detection, the best results were obtained by using only currents as inputs, which will be the
same if all features are used as inputs. Higher results were obtained for voltages only features as compared to
the results of features used in phase A and phase B and phase C. The use of the features in the two phases at
the same time yielded optimal results in comparison to when a single phase is used. For the detection of faults
in the entire system, optimal results were obtained using only current as input features, which will be the same
if all the features were used as inputs. Optimal results were obtained by using the features of two phases at the
same time as inputs. The results were better than using only single phase and voltages only. Generally, it was
found that better results were achieved in the detection of ground faults and those in the entire system. More
so, the least performance was recorded in the detection of ground faults. High values of sensitivity and
specificity were achieved in the case ground faults detection. This reveals that the algorithm is able to
accurately differentiate faults points from no fault points, indicating that the algorithm can be used reliably for
faults detection based on the values of voltages and currents of the transmission lines.

6. CONCLUSION
In this study, the process of faults detection in transmission lines was performed in five phases. The
algorithm proposed in this work successfully detected faults in phase A, phase B, phase C, ground, and whole
system. The detection of faults in the transmission lines was done through the use of K-nearest neighbor model
on a simulated power system that is made up of 11 KV generators. Also, the detection involved the use of
values of voltages and currents of the transmission lines and in different combinations. The algorithm’s
performance was evaluated using different parameters from the confusion matrix, including accuracy,
sensitivity, precision, and specificity. Analysis and discussion of the findings have been presented, showing
the best feature combinations for the detection of faults in electrical transmission lines, as well as the worst
combination.

Int J Pow Elec & Dri Syst, Vol. 14, No. 2, June 2023: 1033-1043
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1039

APPENDIX

Figure 3. Histogram distribution of input features

Detection of power transmission lines faults based on voltages … (Nisreen Khalil Abed)
1040  ISSN: 2088-8694

Figure 3. Histogram distribution of input features (continue)

Int J Pow Elec & Dri Syst, Vol. 14, No. 2, June 2023: 1033-1043
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1041

Figure 4. Output features distribution

REFERENCES
[1] A. Muir and J. Lopatto, “Final report on the August 14, 2003 blackout in the United States and Canada: causes and
recommendations,” 2004. [Online]. Available: https://www.energy.gov/oe/articles/blackout-2003-final-report-august-14-2003-
blackout-united-states-and-canada-causes-and.
[2] N. M. Zainuddin et al., “Review of thermal stress and condition monitoring technologies for overhead transmission lines: issues
and challenges,” IEEE Access, vol. 8, pp. 120053–120081, 2020, doi: 10.1109/ACCESS.2020.3004578.
[3] N. Yu, S. Shah, R. Johnson, R. Sherick, M. Hong, and K. Loparo, “Big data analytics in power distribution systems,” in 2015 IEEE
Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), Feb. 2015, pp. 1–5, doi:
10.1109/ISGT.2015.7131868.
[4] H. Akhavan-Hejazi and H. Mohsenian-Rad, “Power systems big data analytics: an assessment of paradigm shift barriers and
prospects,” Energy Reports, vol. 4, pp. 91–100, Nov. 2018, doi: 10.1016/j.egyr.2017.11.002.
[5] L. Abd Ali, F. Al-Rufaee, V. Kuvshinov, B. Krit, A. Al-Antaki, and N. Morozova, "Study of hybrid wind–solar systems for the Iraq
energy complex," Applied Solar Energy, vol. 56, pp. 284-290, 2020, https://doi.org/10.3103/S0003701X20040027.
[6] J. Antonino-Daviu, P. Jover Rodriguez, M. Riera-Guasp, M. Pineda-Sánchez, and A. Arkkio, “Detection of combined faults in
induction machines with stator parallel branches through the DWT of the startup current,” Mechanical Systems and Signal
Processing, vol. 23, no. 7, pp. 2336–2351, Oct. 2009, doi: 10.1016/j.ymssp.2009.02.007.
[7] N. A. Hussien, A. A. D. Al-Magsoosi, H. T. S. AlRikabi, and F. T. Abed, “Monitoring the consumption of electrical energy based
on the internet of things applications,” International Journal of Interactive Mobile Technologies (iJIM), vol. 15, no. 07, p. 17, Apr.
2021, doi: 10.3991/ijim.v15i07.20183.

Detection of power transmission lines faults based on voltages … (Nisreen Khalil Abed)
1042  ISSN: 2088-8694

[8] F. T. Abed and H. T. AlRikabi, “Using IoT applications for detection and monitoring of underground cable fault,” IOP Conference
Series: Materials Science and Engineering, vol. 1184, no. 1, p. 012003, Sep. 2021, doi: 10.1088/1757-899X/1184/1/012003.
[9] G. Dileep, "A survey on smart grid technologies and applications," Renewable energy, vol. 146, pp. 2589-2625, 2020,
doi.org/10.1016/j.renene.2.019.08.092
[10] Y. Du, S. Zhou, X. Jing, Y. Peng, H. Wu, and N. Kwok, “Damage detection techniques for wind turbine blades: a review,”
Mechanical Systems and Signal Processing, vol. 141, p. 106445, Jul. 2020, doi: 10.1016/j.ymssp.2019.106445.
[11] S. Al-Hamadani, "Solar energy as a potential contributor to help bridge the gap between electricity supply and growing demand in
Iraq: A review," Int J Adv Appl Sci ISSN, vol. 2252, no. 8814, p. 8814, 2020, doi: 10.11591/ijaas.v9.i4.pp302-312.
[12] H. D. S. Altai, F. T. Abed, M. H. Lazim, and H. T. S. ALRikabi, “Analysis of the problems of electricity in Iraq and
recommendations of methods of overcoming them,” Periodicals of Engineering and Natural Sciences (PEN), vol. 10, no. 1, pp.
607–614, Feb. 2022, doi: 10.21533/pen.v10i1.2722.
[13] J. Barros and J. M. Drake, “Realtime fault detection and classification in power systems using microprocessors,” IEE Proceedings:
Generation, Transmission and Distribution, vol. 141, no. 4, pp. 315–322, 1994, doi: 10.1049/ip-gtd:19949968.
[14] S. Bracho and M. Martinez, “Catastrophic and parametric fault detection by dynamic power supply current test,” in IEE Colloquium
on Testing Mixed Signal Circuits and Systems, 1997, vol. 1997, p. 10, doi: 10.1049/ic:19971201.
[15] F. N. Chowdhury and J. L. Aravena, “A modular methodology for fast fault detection and classification in power systems,” IEEE
Transactions on Control Systems Technology, vol. 6, no. 5, pp. 623–634, 1998, doi: 10.1109/87.709497.
[16] A. A. Majd, H. Samet, and T. Ghanbari, “K-NN based fault detection and classification methods for power transmission systems,”
Protection and Control of Modern Power Systems, vol. 2, no. 1, p. 32, Dec. 2017, doi: 10.1186/s41601-017-0063-z.
[17] H. Samet, A. Shabanpour-Haghighi, and T. Ghanbari, “A fault classification technique for transmission lines using an improved
alienation coefficients technique,” International Transactions on Electrical Energy Systems, vol. 27, no. 1, p. e2235, Jan. 2017, doi:
10.1002/etep.2235.
[18] S. A. Gafoor and P. V. R. Rao, “Wavelet based fault detection, classification and location in transmission lines,” in 2006 IEEE
International Power and Energy Conference, Nov. 2006, pp. 114–118, doi: 10.1109/PECON.2006.346630.
[19] H. T. S. AlRikabi and N. Ali Jasim, “Design and implementation of smart city applications based on the internet of things,”
International Journal of Interactive Mobile Technologies (iJIM), vol. 15, no. 13, pp. 4–15, Jul. 2021, doi:
10.3991/ijim.v15i13.22331.
[20] E. S. Prakash, “Electrical fault detection and classification dataset,” kaggle. https://www.kaggle.com/datasets/esathyaprakash/
electrical-fault-detection-and-classification?q=Electrical+Fault+in%3Adatasets.
[21] M. Jamil, S. K. Sharma, and R. Singh, “Fault detection and classification in electrical power transmission system using artificial
neural network,” SpringerPlus, vol. 4, no. 1, p. 334, Dec. 2015, doi: 10.1186/s40064-015-1080-x.
[22] C. S. Bojer and J. P. Meldgaard, “Kaggle forecasting competitions: an overlooked learning opportunity,” International Journal of
Forecasting, vol. 37, no. 2, pp. 587–603, Apr. 2021, doi: 10.1016/j.ijforecast.2020.07.007.
[23] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer, “KNN model-based approach in classification,” in On The Move to Meaningful
Internet Systems 2003: CoopIS, DOA, and ODBASE, Berlin, Germany: Springer, 2003, pp. 986–996.
[24] O. Adepoju, J. Wosowei, S. Lawte, and H. Jaiman, “Comparative evaluation of credit card Fraud detection using machine learning
techniques,” in 2019 Global Conference for Advancement in Technology (GCAT), Oct. 2019, pp. 1–6, doi:
10.1109/GCAT47503.2019.8978372.
[25] B. Charbuty and A. Abdulazeez, “Classification based on decision tree algorithm for machine learning,” Journal of Applied Science
and Technology Trends, vol. 2, no. 01, pp. 20–28, Mar. 2021, doi: 10.38094/jastt20165.
[26] P. Cunningham and S. J. Delany, “K-nearest neighbour classifiers - a tutorial,” ACM Computing Surveys, vol. 54, no. 6, pp. 1–25,
Jul. 2022, doi: 10.1145/3459665.
[27] S. K. Shukla and E. Koley, “Detection and classification of open conductor faults in six-phase transmission system using k-nearest
neighbour algorithm,” in 2017 7th International Conference on Power Systems (ICPS), Dec. 2017, pp. 157–161, doi:
10.1109/ICPES.2017.8387285.
[28] M. R. Mahdiani, E. Khamehchi, S. Hajirezaie, and A. Hemmati-Sarapardeh, “Modeling viscosity of crude oil using k-nearest
neighbor algorithm,” Advances in Geo-Energy Research, vol. 4, no. 4, pp. 435–447, Dec. 2020, doi: 10.46690/ager.2020.04.08.
[29] G. Canbek, S. Sagiroglu, T. T. Temizel, and N. Baykal, “Binary classification performance measures/metrics: a comprehensive
visualized roadmap to gain new insights,” in 2017 International Conference on Computer Science and Engineering (UBMK), Oct.
2017, pp. 821–826, doi: 10.1109/UBMK.2017.8093539.
[30] D. G. Altman and J. M. Bland, “Statistics notes: diagnostic tests 1: sensitivity and specificity,” British Medical Journal, vol. 308,
no. 6943, pp. 1552–1552, Jun. 1994, doi: 10.1136/bmj.308.6943.1552.
[31] D. M. W. Powers, “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,”
arXiv:2010.16061, 2020, doi: 10.48550/arXiv.2010.16061.

BIOGRAPHIES OF AUTHORS

Nisreen Khalil Abed is a lecturer in the Engineering College, at the Wasit

University, Iraq. His area of research focuses on power systems and their applications. Year
of Graduation 2006 University of Technology/Electromechanical Engineering Department –
Electrical branch Bachelor degree. M.Sb. Year of Graduation 2020 University of
Wasit/Electrical engineering department–general branch Master degree. She can be contacted
at email: [email protected].

Int J Pow Elec & Dri Syst, Vol. 14, No. 2, June 2023: 1033-1043
Int J Pow Elec & Dri Syst ISSN: 2088-8694  1043

Faisal Theyab Abed is a lecturer in the Engineering College, at the Wasit

University, Iraq. His area of research focuses on power systems and their applications. He
received his B.Sc. degree in Electrical Engineering in 2006 from the Al Mustansiriya
University in Baghdad, Iraq. His M.Sc. degree in Electrical Engineering focusing on power
systems from Russia in 2017. Al Kut city – Hay ALRabee, Wasit, Iraq. The number of articles
in national databases – 4, and the number of articles in international databases – 10. He can
be contacted at email: ftheyab@ uowasit.edu.iq.

Hamdalla F. Al-Yasriy is an Assistant Lecturer in the Engineering College, at

the Wasit University, Iraq. At 2016 receives his BSc degree in electrical engineering from
Wasit University, and at 2020, he receives his M.Sc. in the College of Engineering in Wasit
University. The number of articles in national databases – 2. He can be contacted at email:
[email protected].

Haider TH. Salim ALRikabi is presently Asst. Prof and one of the faculty
College of Engineering, Electrical Engineering Department, Wasit University in Al Kut,
Wasit, Iraq. He received his B.Sc. degree in Electrical Engineering in 2006 from the Al
Mustansiriya University in Baghdad, Iraq. His M.Sc. degree in Electrical Engineering
focusing on communications systems from California State University/Fullerton/USA in
2014. He is author, coauthor, and editor of some national and international journals and
conferences. His current research interests include communications systems with the mobile
generation, control systems, intelligent technologies, smart cities, renewable energies, and
the internet of things (IoT). Al Kut city – Hay ALRabee, Wasit, Iraq. The number of articles
in national databases – 10, and the number of articles in international databases – 70. He can
be contacted at email: hdhiyab@ uowasit.edu.iq.

Detection of power transmission lines faults based on voltages … (Nisreen Khalil Abed)