Scribd
Upload
50 views

Research Project Proposal

The document proposes using artificial neural networks and wide area measurement systems to predict power system transient stability and prevent blackouts. It discusses using phasor measurement unit data as inputs to train neural networks to classify stability status and detect instability early in order to trigger emergency controls. The framework aims to provide operators warning before voltage stability is degraded to allow timely corrective actions.

Uploaded by

Al-momaniMohammad
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
50 views

Research Project Proposal

The document proposes using artificial neural networks and wide area measurement systems to predict power system transient stability and prevent blackouts. It discusses using phasor measurement unit data as inputs to train neural networks to classify stability status and detect instability early in order to trigger emergency controls. The framework aims to provide operators warning before voltage stability is degraded to allow timely corrective actions.

Uploaded by

Al-momaniMohammad
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Research project

proposal
M. Almomani S. Algharaibah
Sensors, Measurement, and Smart
Metering
 To introduce the main monitoring techniques and devices of the power system
state, finalized to the control and diagnosis function of power system smart
grids.
 sensor subsystem: which senses the environment.
 processing subsystem: which performs computations on the sensed data.
 communication subsystem : message exchange.
Wide area monitoring system (WAMS)

 New term in power system use a collective technology (measurement


communication and information technology) for dynamic and real-time
monitoring wide are power system.
 Metering Devices : IEEE C37.118.1-2011
 Communication: IEEE C37.118.2-2011
 Information technology: application of EMS
SENSOR

WAMS

WSN
Blackout
security
AGC

EMS OPF
Blackouts

 after the 2003 US and Canada blackout, 61,800 MW of power was lost for up to two
days. The total impact on US workers, consumers, and taxpayers was a loss of
approximately $6.4 billion directly due to the effects of electric power.
 2003 Italy blackout: There was a serious power outage that affected all of Italy –
except the islands of Sardinia and Elba – for 12hours and part of Switzerland near
Geneva for 3hours on September 28, 2003. It was the largest
blackout in the series of blackouts in 2003, affecting a total of 56 million people
 2012 Indian blackout: On July 30 and 31, 2012, there was a major blackout in
India that affected over 600 million people. On July 30, nearly the entire
north region covering eight states was affected, with a loss of 38 000 MW
of load. On July 31, 48 000 MW of load was shed, affecting 21 states.
 2004 Jordan blackout: Total load shed was about 600 MW and blackout of Jordan
power system has taken place.
 Some of the past cascading blackouts share similarities. For example, the
two significant outages in the western North America in 1996, the U.S.-
Canadian blackout on August 14, 2003, and the outage in Italy on September
28, 2003, all had tree contact with transmission lines. Modeling and
understanding these common features will help prevent future cascading
blackouts that might be initiated by the same reason. At the same time, each
blackout has its own unique features due to the characteristics of the
particular system, which makes the modeling and understanding of cascading
failures challenging
Challenges in Modeling and Understanding
Cascading Failures

 Size of the system


 Limited computational power
 Mechanisms in cascading blackouts: thermal dynamics of the transmission line and
tree contact, human error, power flow redistribution, protection misoperation,
voltage collapse, transient instability, oscillation, and so on
 Complexities of the system
 Evolving system: The power system is evolving all the time. As the economy
and the population grow, the load is also constantly increasing.
 External factors: if the trees under some lines are not pruned or cleared properly,
it is possible that the lines can be tripped due to tree contact even
when the lines are not overloaded, especially in very hot days with low
wind
 A framework for developing a WAMS‐based protection and control scheme is
suggested here for mitigation of cascading failures:
 A comprehensive table of control strategies is designed based on adequate
offline studies for a wide range of contingency scenarios and operating
conditions.
 The strategy table is maintained online and updated in a timely manner,
for example, every 1–15 minutes, to cover any new appearing scenario or
operating condition not addressed by offline studies.
 Once the WAMS detects or reliably predicts any major instability, a control
strategy that matches best the current situation from the table with adaptive
refining should be performed in time.
Artificial Neural Network Based Algorithm for
transient instability detection problem
Using Wide Area Measurements
ANN
 Two sub-problems:
 Post fault rotor-angle trajectory prediction.
 Real time transient instability detection.
 There are three categories for the former sub-problem:
 Network reduction based rotor-angle trajectory super-real time simulation
 Curve-fitting based trajectory extrapolation
 Angle speed prediction and integration methods.
 There are three types of criteria for the transient instability detection.
 threshold-type criteria
 differentiation-type criteria
 integration-type criteria.
 J. Thorp et al. first investigated on the post-fault rotor angle trajectory
super-real-time simulation based on the network dynamic equivalence.[1]
 This method requires the data of network topology and parameters, which are hard
to be satisfied in real power systems.
 In [2] Haque proposed that rotor angle and the angular velocity of the
generator can be expressed through truncated Taylor series expansions.
 Later on, Sun proposed that the rotor speed can be expressed by a polynomial
function and the corresponding parameters can be estimated by using the least
square method in [3].
 Literature [4] first proposed that the generator angular velocity can be
obtained by Newton interpolation method and the generator angle in a future
time can be calculated by integration of the angular velocity.
Artificial Neural Network Based Algorithm for
Early Prediction of Transient Stability Using
Wide Area Measurements
 In this paper, an artificial neural networks
based methodology is proposed for predicting
the power system stability directly after
clearing the fault. A dataset is generated to
train a multilayer perceptron off-line, which
is then used for early online prediction of any
transient instability. The neural network is
fed by the inputs, which are the pre-fault,
during-fault, and post-fault voltage magnitude
measurements collected from the phasor
measurement units.
Artificial neural network based early detection
of real-time transient instability for initiation
of emergency control through wide-area
synchrophasor measurements

 The synchrophasor measurements are


used for real-time monitoring of the
system. The Artificial Neural Network
(ANN) is used as classifier for
predicting the transient instability
status of the system with rotor angles
and speeds (frequency) of generator as
inputs at different consecutive cycle
lengths after fault clearing.
On-line Voltage Instability Prediction using an
Artificial Neural Network

 In this paper, a predictive method to detect voltage instability using an


artificial neural network is presented. The proposed method allows
transmission system operators to predict long-term voltage instability far
before the system voltage stability has been degraded, allowing swift and
cost-effective control actions.
Blackout prediction in interconnected electric
energy systems considering generation re-
dispatch and energy curtailment
 In this paper, a two-stage scheme was proposed to predict blackouts. The
proposed scheme received the impedance measurements from the generator
terminals through PMUs and then sought to extract decision rules to distinguish
island conditions from other non-island conditions. While the conventional out-of
step relays detected the electrical separation of one synchronous machine from
the rest of the network, the proposed method acted as a wide-area out-of-step
predictor to detect the electrical separation of one region with respect to the rest
of the network. The boundaries of electric islands were determined using an MINLP
formulation. The output of the prediction was used to trigger the controlled-
splitting strategy before the occurrence of a blackout. The accuracy of the DT
classifier verified the performance of the proposed impedance-based scheme.

 Applied Energy 187 (2017) 50–61


REFERENCES

1- C. W. Liu, J. Thorp. “Application of synchronized phasor measurements to


real-time transient stability prediction.” IEE Proc. Gener. Transm. Distrib. 1995,
vol. 142, no.4, pp.355~360.
2-M. H. Haque, A. H. M. A. Rahim. “Determination of first swing stability limit of
multimachine power systems through Taylor series expansions.” IEE Proc. Gener.
Transm. Distrib. vol. 136, no.6, pp. 373~379, 1989.
3- J. Sun and K. L. Lo. “Transient stability real-time prediction for multi machine
power systems by using observation.” Proceedings of IEEE TECON 93. Beijing,
1993, pp. 217-221.
4- M. Takahashi, K. Matsuzawa, M. Sato, et al. “Fast generation shedding
equipment based on the observation of swings of generators.” IEEE Transactions
on Power Systems. vol.3, no.2,pp.439-446, May 1988.

You might also like