Documente Academic
Documente Profesional
Documente Cultură
Abstract - The state of an electric power system may be classified as either stable or unstable. The borderline of stability is at any
condition for which a slight change in an unfavourable direction of any pertinent quantity will cause instability. Voltage instability
in power distribution systems could lead to voltage collapse and thus power blackouts. The researchers will present an intelligent
system using back propagation algorithm which detects voltage instability and classifies voltage output of an assumed power
distribution system (PDS) as: stable or unstable.
The researcher’s work is the use of voltage output readings as the input patterns to the neural network for training and
generalizing purposes, thus providing a faster instability detection system that simulates a trained operator controlling and
monitoring the 3-phase voltage output of the assumed power distribution system.
Index Terms— Load Stability, Phase Synchronization, Voltage Collapse, Neural Network, Power Distribution System, 3-phase, Back-
Propagation Algorithm
pronounced, the system integrity is endangered mainly due
to protecting devices that trip generation, transmission, or
I. INTRODUCTION1 load equipment. This degradation process may eventually
lead to a blackout in the form of a voltage collapse. (Glavic,
T he study is focused primarily on researching viable
methods for applying real-time voltage instability
detection algorithms, which may be used to improve the
M. & Cutsem, T.V. 2011).
B. Research Design
III. FLOWCHART
Flow chart of WEKA program of a simulation of voltage
instability predictor:
FIGURE 1.1: Full Flow Chart For the testing phase, the researchers used command
prompt to type in the prediction testing script, then the
Based on the whole flow chart, on the Data part, the results are transferred to excel file, then performed
group separated the number of instances into 80% training accuracy. The result of this process will then be evaluated
and 20% testing and it is fed to the training phase. by the researchers in order to see the accuracy of the
prediction of the system before incorporating it to
distribution systems.
OKE-5116-103 3
The accuracy will depend on the number of data has a voltage value of 1.0 + j 0 P.U. The voltage-controlled
processed by the system and is then subject to improvement bus however, has voltage control capabilities. Instead of a
as stated in the recommendation of the paper. generator, it has tap-adjustable transformer and/or a static
VAR compensator.
IV. SIMULATION RESULTS
Designing a system requires training and sample points The load buses are the ones subjected to study in this
that will be made as a basis of the system. There are data paper since real power and reactive power are known
that needs to be properly checked and evaluated whether it variables. This is because the researchers intend to vary the
is correct or not. In order to check the efficiency of the load and locate and study what instance of load does it
system, with the help of the group’s chosen program, a cause a voltage instability.
legitimate sample of dataset was obtained from WEKA. The These load variables are obtained from IEEE Bus 14
data set that the researchers will use will come from the System, and since voltage magnitude and voltage angle are
result of the simulation of the IEEE 14 Bus Test System in unknown, this instance prove to be a good scenario for this
MATLAB. thesis so that voltage behavior can be observed.
The data set will then be used for the training of the
model from WEKA that will be used for the detection and The researchers have then varied the IEEE 14 Bus Test
prediction of the voltage instability. All the buses included
System 24-hour load profile with respect to a certain
in 24-hour load profile table are load buses. The following
percentage in its load and fed the data to MATLAB in order
buses included in the load profile will be subjected to the
to generate the data needed and to determine on what
testing process to be incorporated in the code in WEKA’s
interface (see Appendix A for 24 hour load profile). percentage of load variation the load instability occurred.
The extent of the detection system for voltage instability
covers the behavior of the load buses for 1 day (24 hours).
The initial data for the system was accumulated from a
reliable source which is IEEE 14 Bus System 24-hour load
profile. As observed, the load (P & Q) is varied every hour
for 24 hours. The values where used as the current load data
of respective buses in WEKA, subject to change per hour.
A neural network usually has 3 basic layers, namely the inaccurate. The accuracy of the prediction was only
input layer, hidden layers, and the output layer. From the 80.18%. This is because the code in WEKA doesn’t
neural network, the attributes declared on the data is indicate a right or wrong in a given set of inputs and thus, it
analyzed and processed by WEKA with declaration of is the system’s job to study and create computational pattern
values that result to a specific output, namely stable or from the input to provide a reliable and accurate detection
unstable. These attributes serve as the input layer and system. It has to study intensively the given values to
parameter of the artificial neural network. When predict a stable value. Because of this, the prediction
processed by WEKA, relationships and patterns are to be obtained a low percentage in accuracy.
generated in the form of weights, which is the lines
connecting the attributes to the neurons
V. CONCLUSION
These weights are usually multipliers that can be seen
Voltage instability was found to be a significant
from the model data generated by WEKA. These weights
impediment on the efficiency and safe operation of power
are then fed into the hidden layers and then
systems, causing fluctuations in the actual voltage readings
assessed/studied by the hidden layers with neurons to
in the power system, which may then lead to the so called
further identify relationships and perform back
“voltage collapse” or blackouts when left unchecked. The
propagation process to minimize the error and increase the
researchers had proposed an early voltage instability
integrity of the system.
detection system based from the PMU’s as input
D. Prediction Accuracy components which then utilize the artificial neural network
to predict the onset of a voltage collapse.
Designing an intelligent detection system for voltage
instability detection requires intensive study in order for the
research study to be effective and efficient. The researchers
gathered data from IEEE 14 Bus System and incorporated it
into the program WEKA. From there, programming
techniques were used in order to create a system that can
detect whether the voltages accumulated are unstable or not.
In totality, the researchers therefore concluded that
detecting voltage instability in the distribution grid is a
FIGURE 1.5. Accuracy Results possibility. WEKA is a favorable program to be used for
detecting voltage instability since it can easily adapt to new
From the figure above, different parameters/results can be inputs based from its learning and study derived from
seen. This is the prediction output of the system based from previous computations by taking into consideration real-
a given set of codes indicated from previous discussions. time basis. Methods such a Gauss-Seidel for variation of
These codes are derived from command prompt and copied load parameters and Artificial Neural Network for
to excel for more clarity of output. Instances, the first generating accurate outputs proved to be a viable option for
training and generating a model for the system. With this
column, represent the number of entries the test data has. In
paper, voltage instability will be detected and thus pave way
the 2nd column, the “actual” column shows the actual result
for distribution utilities to make their response the more
that the test data has. This indicates the ideal voltage
efficient and minimize further casualties such as brownouts
condition the detection system should predict based from its and blackouts from prolonging longer. Since the detection
measured value. The “predicted column” in the 3rd, shows system proved to be viable to detect bus location and time
the predicted results of the detection system using the model which violation occurs, repair response time will be
generated from WEKA or in any case, the output. The error shortened and maximize time efficiency. An increase or
column will determine whether there is an error or none in decrease of 5% in voltage can be further identified for the
the prediction stage. The (+) sign indicates that an error is system to be unstable.
detected, whereas no sign indicates that the predictions were
correct. The prediction column in the 4th however, VI. RECOMMENDATIONS
represents the prediction accuracy of the system. In Figure In applying this study, the researchers recommend that
A4, 1 from the 2nd row indicates that the system correctly the engineer check for the compatibility of the algorithm to
detected the first entry with a confidence level of 50.2%. In the distribution system for practicality purposes. The system
the first row with the error the system depicted the entry by had only been tested, at present, on the inputs from the data
1. This means that the system is 100% sure that the output gathered exclusively from IEEE 14 Bus System. The study
WEKA has predicted is wrong and inaccurate. As such, the was conducted primarily on the notion that voltage
next column shows the bus location and time (24 hour instability was a problem that the distribution utility faces.
setting) where and when the voltage violation had occurred. An advancement to this study is also to specify what kind of
The 1’s and 0’s in the last column indicates whether the load is the bus under observation, whether it is residential,
system is accurate or not, 1 being accurate and 0 being commercial, or industrial. Likewise, it is also better if the
system can determine what increase in load does the voltage REFERENCES
violation occurred. That way, the nature of the parameters Ainsworth, J. D., Gavrilovic, A., &Thanawala, H. L. (1980)
indicated in the bus as well as the instance of time where Static and Synchronous Compensators for HVDC
voltage instability occurs can be further comprehended and Transmission Convertors Connected to Weak AC Systems. In:
28th session CIGRE, pp 31–41
observational pattern can be acquired.
Andersson, G., Donalek, P., Farmer, R., Hatziargyriou, N.,
APPENDIX A. 24 HOUR LOAD PROFILE Kamwa, I., &Kundur, P. (2005) Causes of the 2003 major
grids blackouts in North America and Europe, and
Recommendation Means to Improve System Dynamic
Performance. IEEE Trans Power Syst 20(4): 1922–1928.