Stabilization Of Power System Using Artificial Intelligence Based System

Agnihotri Piyush; International Journal of Advance Research, Ideas and Innovations in Technology.
© 2017, IJARIIT All Rights Reserved Page | 966
ISSN: 2454-132X
Impact factor: 4.295
(Volume3, Issue1)
Available online at: www.ijariit.com
Stabilization Of Power System Using Artificial Intelligence
Based System
Piyush Agnihotri
Department of Electrical & Electronics
Engineering
Pranveer Singh Institute of Technology,
Kanpur, INDIA
piyushagnihotri034@gmail.com
Jitendra Kumar Dwivedi
Department of Electrical Engineering
Harcourt Butler Technical University
Kanpur, INDIA
jkdwivedi.hbti@gmail.com
Vishnu Mohan Mishra
Department of Electrical Engineering
GB Pant Engineering College,
Pauri-Garhwal
vmm66@rediffmail.com
Abstract— This paper reviews limitations of traditional control system and modern control system controllers, which are
overcome to some extent using artificial intelligent techniques, such as ANN, Fuzzy Logic, Expert System, Particle Swarm
Optimization, Genetic Algorithm, etc. The review shows that efforts are made towards Power System Stabilizer based on
Artificial Intelligent Techniques, which will give positive impact on the system stabilities and improve system performances.
Keywords—ANN; PSO; Fuzzy Logic; Genetic Algorithm.
I. INTRODUCTION
Power system engineering forms a vast and major portion of electrical engineering studies. It is mainly concerned with the
production of electrical power and its transmission from the sending end to the receiving end as per consumer requirements,
incurring minimum amount of losses. The power at the consumer end is often subjected to changes due to the variation of load or
due to disturbances induced within the length of transmission line. For this reason the term power system stability is of utmost
importance in this field, and is used to define the ability of the of the system to bring back its operation to steady state condition
within minimum possible time after having undergone some sort of transience or disturbance in the line. Ever since the 20th
century, till the recent times all major power generating stations over the globe has mainly relied on AC distribution system as the
most effective and economical option for the transmission of electrical power.
The Automatic Voltage Regulator (AVR) and exciter are the main components of the generator excitation system. The
terminal generator voltage sensed and compared with the reference voltage to control the exciter output. Subsequent to any
disturbance the damper and the field winding attempt to damp rotor swing. The damping process repels by the negative damping
torques introduced by AVR.
As a result, the power system may expose undesirable oscillations or lose synchronism. For this concern, the Power
System Stabilizer (PSS) become technologically advanced and expanded to serve for an effective functioning. The main function
of the PSS in the excitation system is introducing an additional signal to provide a damping component that is in the phase with
the rotor speed deviation. Therefore, the System Stability will be enhanced by adding PSS device.
Stabilizers that developed according to classical and modern control theories are based on liberalized machine model.
Power system is a nonlinear, complex system and is subjected to different kinds of disturbances that yield unresolved issues and
uncertain consequences in different power system problems. With such limitations, it is difficult
to stabilize power system efficiency by these kinds of PSSs. Therefore, other types of modern control techniques like adaptive
controller and H∞ control system were used to achieve better operating performance as distinguished from conventional
stabilizers.
Artificial Intelligence (AI) techniques proved to be effective tools to resolve many power system problems and those they
could be more effective when properly joined together with conventional mathematical approaches were proposed based on these
AI techniques. In this work, a serious attempt is made to present a comprehensive analysis of artificial intelligent techniques for
designing PSS, which are proposed by researchers recently. The performance of a variety of controllers is demonstrated and
compared with other types of controllers.

Vt-ref
w
II. POWER SYSTEM STABILIZER
A. Application Support
Excitation systems with high gain and fast response times greatly aid transient stability (synchronizing torque), but can also
reduce small signal stability (damping torque). Power system stabilizer (PSS) control provides a positive contribution by damping
generator rotor angle swings, which are in a broad range of frequencies in the power system. These range from low frequency
intertie modes (typically 0.1 - 1.0 Hz), to local modes (typically 1 - 2Hz), to intra-plant modes (about 2 -3 Hz).
B. Tuning Modes
The PSS provides modulation of field voltage that damps out power and speed oscillations through normal AVR control. The
tuning study determines the optimum PSS settings, based on the particular generator, AVR settings, and system characteristics.
Special purpose detailed models are used for this analysis. Our studies determine the key adjustment of PSS phase compensation.
To complement this offering, we also perform PSS/Torsional Interaction screening for steam turbines with low modal
frequencies. These studies are performed to determine if a torsional filter is required.
C. Testing’s of the AVR/PSS Control
Testing of the PSS is normally performed during plant commissioning. The test condition for PSS is at or near base load output of
the plant. The testing of modern excitation systems is facilitated by the use of internal data recording and test signals.
The basic types of tests usually performed are given in the following list.
1. Step test in AVR reference (base load – without PSS).
2. Gain margin test to determine the PSS gain to be used.
3. Step test in AVR reference (base load – with PSS).
D. Conventional PSS Schematic Diagram
A schematic block diagram of a generator, excitation system and power system stabilizer (based on a speed error signal) is shown
in Figure 1. A phase compensation approach is usually employed for design of the PSS. At the natural mechanical frequency of
oscillation, or local mode frequency, the phase lead of the PSS is chosen to compensate for the combined lag of the excitation
system and the generator relating A Vt-ref t APe. The PSS then provides a component of electrical power in phase with speed and
therefore directly contributes to the system damping at that frequency. The magnitude of this damping component is determined
by the chosen compensator gain.
III. INTELLIGENT TECHNIQUES BASED CONTROLLERS
In the recent year of developments, the classified and reviewed techniques include fuzzy logic system, ANN, optimization based
AI, and hybrid AI.
A. Fuzzy Logic Controller
Sir Zadeh has introduced the concept of fuzzy logic in 1963. The fuzzy logic is derived from fuzzy set theory. In fuzzy set, infinite
number of membership are allowed. The degree of each membership for each element is indicated by a number between 0 and 1.
To design traditional controllers, it is necessary to liberalize nonlinear systems. Then, control laws are derived based on the
new model. These controllers are used to control the system. Fuzzy logic controllers are nonlinear. Moreover, fuzzy logic
controllers do not need a controlled plant model, and not sensitive to plant parameter variations. By using fuzzy logic, the human
experience can be used in designing the controller.
Fuzzy logic controllers are rule-based. The rules of the system are written in natural language and translated in fuzzy logic. First,
Figure 1: Schematic Diagram of PSS
Pe
Vt
Efd
UPSS
Excitation
System
Generator
and Load
Power System
Stabilizer
+
+
-

the crisp inputs values are converted through fuzzification process to corresponded linguistic fuzzy sets with appropriate
membership values using normalized member functions.. There are different ways to define the result of a rule e.g. max-min
inference method, etc. Finally, defuzzifire converts the linguistic variables to crisp values using normalized membership functions
and output gains.
El-Sherbiny et al. presented a simple controller based on state feedback control system. The excitation control signal comprises
both of the fuzzy controller and the conventional PI controller output signals.
A stabilizer which covers both heavy and light conditions can provide better performance than conventional PSS. This is
investigated in study. In this study, two linear PSSs were developed based on the conventional frequency domain method to
accommodate above conditions. Fuzzy reasoning was formed to find a single stabilize signal in such away that the signal matches
the operating condition optimally.
Hossein-Zadeh and Kalam introduced an indirect adaptive fuzzy power system stabilizer. The power system was represented by
two unknown nonlinear differential equations. Two fuzzy logic systems built based on these equations and then the stabilizer
designed according to that. Lyapunov’s synthesis method applied to adapt the fuzzy logic systems.
A direct adaptive fuzzy logic stabilizer proposed by with a small rule base as to compared to a standard fuzzy logic stabilizer. In
order to adapt the stabilizer to different operating conditions, the rule-base was tuned on-line for Single Machine Infinite Bus
(SMIB) and multi-machine power systems. Here, the controller parameters are estimated using the variable-structure algorithm.
Mitra et al. proposed a fuzzy power system stabilizer with a new input signals. These signals are tie line connecting two areas
and the speed deviation. The approach gave better dynamic performance compared to a conventional PSS and fuzzy PSS with a
usual speed deviation and acceleration input signals. The cost and scanning time of the approach were reduced because the same
signal can fed to each of the fuzzy logic PSSs.
A new global tuning technique proposed by for fuzzy power-system stabilizers in a multi-machine power system in order to damp
the power system oscillations. This technique is based on an iterative adaptive efficient partition algorithm. Numerical results
show that this algorithm can find the optimal global solution faster than a conventional Genetic Algorithm (GA).
Soliman et al. proposed a linear matrix inequalities (LMI) design of a model-based fuzzy static output-feedback PSS. Here, a
power system design model is represented by a Takagi–Sugeno (T–S) fuzzy model. This model is used to develop a stabilizer
working with different operating conditions and disturbances. A static fuzzy PSS that guarantees robust pole-placement in an
LMI region has been designed. Simulations results show capability of the proposed approach in damping of inter area oscillations
for 4-machine 2-area power system.
Wide-area measurement systems (WAMS) can be used to improve the large scale power system performance. Delay time during
sending and receiving signal may be corrupt system performance. To overcome this drawback, Dou et al. proposed the delay-
independent robust control problem based on WAMS using H∞ fuzzy control method. Here, the nonlinear large interconnected
power systems represented by a set of equivalent T–S fuzzy model. The model stabilized by
using feedback decentralized control scheme.
B. Artificial Neural Network Controller
An artificial neural network is a mathematical model or computational model based on Biological neural networks. It consists of a
number of simple nodes (neurons) connected together to form either a single layer or multiple layers. The connections between
neurons are weights that should be trained. Connections from one layer back to a previous layer, and connections between neurons
in the same layer are called feedback connections.
There are different types of Neural Networks (NNs); a NN is said to be feed-forwarded network if the input and intermediate
signals (connections) are always propagated forwards i.e. the information moves from input to output through hidden layers in
forward direction without any loops, while a recurrent NN is a network that has more than one cycle.
ANN as an effective tools used for many years for identification and control of complex systems due to the non-linear mapping
properties of the neural networks. Neural network when sufficiently trained may be used as controller instead of conventional
PSS. To achieve good performance, the NN must be trained for different operating conditions to tune the parameters of the
conventional PSS. The process of learning using the conventional back propagation network under different conditions makes
interference. To overcome this drawback, Pillutla and Keyhani suggested a modular NN instead of back propagation network.
This model consists of three local expert networks and a single gate network with
three layers for each one. The ANN was trained directly from the input and output of the conventional PSS. The simulation
results demonstrated that the modular PSS is more effective in damping system oscillations and providing good performances.
A feed forward neural network with single hidden layer was used, to develop a neural adaptive power system stabilizer. These

approaches used different techniques. Each stabilizer is comprises of two sub networks; Adaptive Neuro-Identifier (ANI) and
adaptive neuro-controller (ANC). Both sub-networks were trained by using the back propagation algorithm. While the first one
approach based on the direct adaptive control scheme, the second one based on the indirect adaptive control scheme and adapted
on-line.
Radial basis function network (RBFN) has three layers which are: input, hidden, and output layers. Here, RBF is usually a
gaussian function. The hidden layer is trained at first using an unsupervised learning algorithm to find centers and widths of the
radial basis functions for individual pattern units. To find the weights between the pattern units and the output units, the output
layer is trained using supervised learning algorithm.
Abido and Abdel-Magid developed an RBFN to re-tuned PSS parameters on-line based on real-time measurement of
the machine loading conditions.The proposed stabilizer was trained for different operating conditions and system
parameter variations. A set of significant radial basis
orthogonal least squares learning algorithm functions and the
network parameters were obtained using
A very large number of training is required in the neural network as is used in the approach presented by. To avoid this
problem a self-tuning PSS based on ANN proposed by [21]. In this approach the ANN was introduced for tuning the
conventional PSS parameters in real-time. A new method applied for selecting the number of neurons in the hidden layer.
To improve the transient stability of power systems under different operating conditions and parametric uncertainties, Senjyu et
al. proposed a Recurrent Neural Network (RNN) stabilization controller. The proposed supplementary RNN controller was
applied for both AVR and the governor. The weight of the controller adjusted on-line. The signal output of first RNN was added
to the PSS signal output for excitation control. The signal output of second RNN was used as a stabilizing signal for the governor
system. The proposed approach applied to single-machine infinite bus.
Due to complexity of large-scale power systems, design of intelligent controllers based ANN, requires large training time and
large number of neurons. These motivate Chaturevdi and Malik to use Generalized Neurons (GN) to develop a generalized
neuron-based adaptive PSS. The stabilizer was trained off-line for a wide range of operating conditions and different disturbances.
It was then trained on-line on the power system. The simulation achieved on SMIB system and the results reveals that the
proposed stabilizer performs well under severe disturbances.
In order to enhance the system performance, Gain-Scheduling technique was applied to design a PSS. This type of stabilizer
functions better than the conventional PSS. Barreiros et al. proposed a neural power system stabilizer which is trained using a set
of gain scheduling PSS parameters. These parameters were obtained by applying pole-placement technique for different
operating conditions. They conclude that the stabilizers would be more beneficial at the case when the reactive power absorbed
by the generators.
The single neuron model was employed by to the probabilistic eigen value analysis for improving the optimization of robust
PSS parameters. The PSS performance was self-adjusted to follow the system operating condition by forming an aiding PSS gain
from the single neuron model. The approach applied successfully to an eight-machine system equipped with six PSSs.
Adaptive critics and neural networks were used by to design and real time implementation of an Optimal Wide Area Control
Systems (WACS). The WACS was implemented on digital signal processor (DSP) which is interfaced to the real time digital
simulator (RTDS). In this approach, neural network system developed to estimate the power system dynamics and to build
nonlinear optimal control. Simulation results show that the damping of inter-area oscillation was enhanced by adding PSS to the
WACS under different operating conditions and contingencies.
C. Optimization Based Intelligent Techniques
Different types of intelligent optimization techniques are used to search for optimal or near optimal solution for many power
system problems. These techniques are GA, Particle Swarm Optimization (PSO), Tabu Search (TS) algorithm etc.
i) Genetic Algorithm (GA) technique
A GA is a type of evolutionary algorithms used as a search technique to find an optimal or near optimal solution for many
problems. It is categorized as global search heuristics. A GA is implemented as an iterative procedure in which a population of
function inputs (strings) is randomly selected. Then the population is used to create a new population in the string and the process
is repeated in the next iterations. The process of creating a new population passes through selection, mating, and mutation
operations.
GA has been applied by many authors for tuning PSS parameters. Simulation results show activity of GA in tuning PSS
parameters with fixed location. However, these PSSs cannot guarantee good damping performance when the location of the
stabilizer is changed. Therefore, Sebaa, and Boudour applied a simple method to find the optimal locations and the best PSSs
parameters simultaneously in multi-machine power systems using GA. Nonlinear simulation and eigen values analysis

demonstrate the effectiveness of the technique in damping of oscillations under different scenarios.
It is difficult to use binary for representation when dealing with continuous search space with large dimensions. Therefore, the
real-coded genetic algorithm was employed by to search for optimal PSS and SVC-based stabilizer parameters. The eigen value
analysis and non-linear simulation were carried out for a weak connected power system. The results demonstrate the ability of the
proposed stabilizers to improve stability of the system.
.
ii) Particle Swarm Optimization (PSO) technique
PSO is one of the modern heuristic algorithms. It is also a population based evolutionary algorithm. PSO is motivated by the
simulation of the social behavior of birds. Individual particles in the swarm with a position and velocity fly in a multidimensional
search space. The velocity is continually adapted according to the corresponding particle’s own experience and other
accompanying particles’ experiences. It is expected that the particles will be flying in the course of finding better areas. El-
Zonkoly et al. proposed PSO technique for tuning parameters of brushless exciter and lead-lag power system stabilizer.
Simulation results demonstrate the activities of the stabilizer in damping of oscillations of multi-machine power system.
D. Hybrid Artificial Intelligent Controller
Two or more artificial intelligent techniques are used to produce a hybrid intelligent system. Through cooperative interactions
such techniques are applied in series or in integration to gain successful results. In last two decades, hybrid systems applied in
engineering applications.
Gain-scheduling PID stabilizer is proposed by and to enhance the stability of the power systems. A hybrid conventional PSS, a
fuzzy logic based PSS and simple switching criteria was used in Lie and Sharaf 1996. This approach applied to a SMIB under
various transient disturbances including faults. In, the parameters of the proposed stabilizer were tuned on-line based on the speed
error signal and its derivative. This controller applied to SMIB and multi-machine power systems.
Djukanovic et al. presented adaptive fuzzy control based on unsupervised learning neural nets for improving the generating unit
transient of a hydro power system. By using appropriate means, a linguistic control strategy of optimal state-feedback regulator
design was converted to a variable control strategy. The proposed controller contains a set of fuzzy logic based controller modules
and a neural net classifier. The relationship between controller inputs and controller output generated by using unsupervised
learning of NN and stored in a matrix called fuzzy associative matrix.
The test inputs used to generate the input–output pairs in training neural network may not be rich enough to excite all modes of
the system and the design of the traditional fuzzy logic controller requires a lot of trial and error. To avoid these drawbacks,
Abido and Abdel-Magid proposed a fuzzy basis function network (FBFN) to develop PSS.
GA is applied by to select and tune the optimal parameters of a neurofuzzy PSS. Suitable fitness function was employed to
determine the optimal parameters of the If and Then parts membership functions during the learning procedure. The proposed
stabilize tested on SMIB system and the results show improving dynamic performances under different operating conditions.
In many cases the initial fuzzy rules which are estimated according to the human experiences tuned using feedback, but with
insufficient information about the control system the trial and error may be necessary. Recently different techniques employed to
avoid this drawback such as TS algorithm, PSO, and Evolutionary Algorithms (EA). These techniques used by many researchers
to design fuzzy PSS. To find the optimal parameters of member functions and desired PSS gains, Cheng and Elangovan applied
TS algorithm. The approach applied to SMIB and multi-machine power systems and the results reveal that the proposed fuzzy
PSSs has robust and adaptive performance under different operating conditions including three phase fault.
Malik presented a comprehensive study to illustrate the possibility of implementing an adapting controller using different
approaches. Adaptive PSS designed based on purely analytic techniques, purely AI techniques, and combination of the analytical
and AI techniques. These stabilizers used to enhance the stability and damping oscillation of an electrical generating unit. These
systems were implemented and tested in real-time on physical models in the Laboratory.
To find the optimal parameters of member functions and desired PSS gains, Hwang et al. applied Adaptive Evolutionary
Algorithm (AEA) comprising GA and Evolution Strategy (ES) for designing fuzzy PSS. ES technique is based on the ideas of
adaptation and evolution. The approach provides good results when applied to SMIB and multi-machine power systems.
Tuning of the PID controller parameters is very important to get best results. Craziness based Particle Swarm Optimization
(CRPSO) and binary coded GA methods were used by to determine the optimal PID gains. These techniques applied to determine
off line, nominal, optimal gains of the PID controller for an AVR. For on line off-nominal system parameters Sugeno fuzzy logic
has been used. The authors concluded that CRPSO is more robust than GA in performing optimal transient under different
operating conditions. Moreover, CRPSO requires less computational time than GA.

Number of variables is based on the complexity of the power system. In a standard fuzzy system, the number of the rules and the
complexity of the problem increase exponentially with the number of variables involved. To introduce linear relation between the
number of variables and number of rules, the hierarchical fuzzy system can be used. This property motivated Caner et al. to
propose the hierarchical fuzzy PSS. The stability enhanced by using this controller for SMIB system with more number of
variables and with appropriate number of rules.
The Bacteria Foraging Optimization (BFO) technique was used by to tune the parameters of both single-input and dual-input
PSSs. The conventional stabilizer and the three dual-input IEEE PSSs were optimally tuned to obtain the optimal transient
performances. Sugeno fuzzy logic was used for on-line, off-nominal operating conditions. Simulation results revealed that the
transient performance of dual-input PSS is better than single-input PSS. In addition, the proposed BFO technique provides better
transient performance compared to GA.
A robust adaptive fuzzy controller proposed by to design a PSS. Fuzzy logic was used to implement system with both nominal
values and adaptive system. A feedback linearization-based control law is implemented using the identified model. The gains of
the feedback linearization controller were tuned using a particle swarm optimization technique. The proposed controller tested on
a 4-machine 2-area power system. The results show the ability of the proposed stabilizer in damping inter-area oscillation
compared to conventional PSS.
El-Zonkoly et al. proposed particle swarm optimization technique for tuning of a fuzzy logic power system stabilizer. The
approach applied to multi-machine power system and simulation carried out. The results show that the stabilizer is successfully
working under different loading and fault conditions.
CONCLUSION
This paper attempts to present new major studies of AI techniques, such as ANN, fuzzy logic, hybrid artificial intelligent, expert
systems, and optimization techniques, applied to develop power system stabilizer (PSS). The controllers that designed based on
conventional control theory, modern control theory, and adaptive control theory are found to have certain restrictions. By contrast,
the advantages of AI techniques convinced and encouraged many researchers to apply these techniques to solve the problems of
Power system control. This review is undertaken to explore and report that fast and accurate acting controllers developed based
on AI techniques are required to maintain system stability and damping of oscillation and provide high-quality performance.
Different types of AI stabilizers are assessed and compared with other types of stabilizers.
REFERENCES
[1]J. Machowiski, J. W. Bialek, and J. R. Bumby, Power System Dynamics and Stability, John Wiley & sons, 2015.
[2]N. He, R. Liu , and D. Xu, “The study of upfc fuzzy control with self-adjustable factor,” IEEE/PES Transmission and
Distribution Conference & Exhibition: Asia and Pacific Dalian, China, pp. 1-5, 2012.
[3] G.K. Venayagamoorthy, “Optimal control parameters for a UPFC in a multimachine using pso,” Intelligent Systems
Application to Power Systems, 2012. Proceedings of the 13th International Conference on pp. 488-493, 2012.
[4] A.T. Al-Awami, Y.L. Abdel-Magid, and M.A. Abido, “A particle-swarm-based approach of power system stability
enhancement with unified power flow controller,” Electric Power and Energy Systems, vol. 29, pp. 251-259, 2007.
[5]E.M. Gouveia, and M.A. Matos, “Symmetric ac fuzzy power flow model,” European journal of Operation Research, vol. 197,
pp. 1012-1019, 2009.
[6] L.H. Tsoukalas, and R.E. Uhric, Fuzzy and neural approaches in engineering, John Wiley & Sons, Inc, pp. 15, 2014.
[7]M.E. El-Hawary, Electric Power Applications of Fuzzy Systems, IEEE PRESS, 2015.
[8]M.K. El-Sherbiny, A.M. Sharaf , G. El-Saady, and E.A. Ibrahim, “A novel fuzzy state feedback controller for power system
stabilization,”
Electric Power Systems Research, vol. 39, pp. 61-65, 1996.
[9]J. Lu, M.H. Nahrir, and D.A. Pierre, “A fuzzy logic-based adaptive power system stabilizer for multi-machine systems,”
Electric Power Systems Research, vol. 60, pp. 115- 121, 2016.
[10]N. Hossein-Zadeh, and A. Kalam, “An indirect adaptive fuzzy-logic power system stabilizer,” Electrical Power and Energy
Systems, vol. 24, pp. 837-842, 2016.
[11]A. L. Elshafei, K.A. El-Metwally, and A.A. Shaltout, “A variable-structure adaptive fuzzy- logic stabilizer for single and
multi-machine power systems,” Control Engineering Practice, vol. 13, pp. 413-423, 2012.
[12]P. Mitra, S. Chowdhury, S.P. Chowdhury, S.K. Pal, R.N. Lahiri, and Y.H. Song, “Performance of a fuzzy power system
stabilizer with tie line active power deviation feedback,” Power Systems Conference and Exposition, PSCE 2006 IEEE PES,
vol. 29, no. 1, pp. 884- 889, 2006.
[13]D.E. Kvasov , D. Menniti, A. Pinnarelli, Y.D. Sergeyev, and N. Sorrentino, “Tuning fuzzy power-system stabilizers in multi-
machine systems by global optimization algorithms based on efficient domain partitions,” Electric Power Systems Research,
vol. 78, pp. 1217–1229, 2008.

[14]M. Soliman, A.L. Elshafei, F. Bendary, and W. Mansour, “LMI static output-feedback design of fuzzy power system
stabilizers”, Expert Systems with Applications, vol. 36, pp. 6817–6825, 2009.
[15]C. Dou, Q. Jia, S. Jin, and Z. Bo, “Delay-independent decentralized stabilizer design for large interconnected power systems
based on WAMS,” Electrical Power and Energy Systems, vol. 29, pp. 775–782, 2007.
[16]D.W. Patterson, Artificial Neural Networks Theory and Applications, Prentice Hall, 1996.
[17]S. Pillutla and A. Keyhani, “Power system stabilization based on modular neural architecture”, Electrical Power & Energy
Systems, Vol. 19, No. 6, pp. 411-418, 2014.
[18]N. Hosseinzadeh, and A. Kalam, “A hierarchical neuralnetwork adaptive power system stabilizer”, International Journal of
Power and Energy Systems, vol. 19, no. 1, 2015.
[19]P. Shamsollahi, and O.P. Malik, “Design of a neural adaptive power system stabilizer using dynamic backpropagation
method,” Electrical Power and Energy Systems, vol. 22, pp.29- 34, 2000.
[20]M.A. Abido, and Y.L. Abdel-Magid, “Adaptive tuning of power system stabilizers using radial basis function networks,”
Electric power System Research, vol. 49, pp. 21-29, 2015.
[21]R. Segal, A. Sharma, and M.L. Kothari, "A self-tuning power system stabilizer based on artificial neural network”, Electrical
Power and Energy Systems, vol. 26, pp. 423- 430, 2004.
[22]T. Senjyu, Y. Morishima, T. Yamashita, and K. Uezato, “Recurrent neural network supplementary stabilization controller for
automatic voltage regulator and governor,” Electric Power Components and Systems, vol. 31, pp. 693-707, 2003.
[23]D.K. Chaturevdi, and O.P. Malik, “Generalized neuron-based PSS and adaptive PSS”, Control Engineering Practice, vol. 13,
no. 12, pp. 507-1514, December 2012.
[24]J.A.L. Barreiros, A.M.D. Ferreira, C. Tavares-da-Costa, W. Barra, and J.A.P. Lopes, “A neural power system stabilizer
trained using local linear controllers in a gain-scheduling scheme,” Electrical Power and Energy Systems, vol. 27, pp. 473–
479, 2012.
[25]H. Ping, W. Kewen, T. Chitong, and B. Xiaoyan, “Studies of the improvement of probabilistic pass by using the single
neuronmodel,” Electrical Power and Energy Systems, vol. 29, pp.217–221, 2007.
[26]S. Ray, and G.K. Venayagamoorthy “A wide area measurement based neurocontrol for generation excitation systems,”
Engineering Applications of Artificial Intelligence, vol. 22, pp. 473–481, 2009.
[27]S.K. Aditya, and D. Das, “Design of load frequency controller using genetic algorithm for two area interconnected hydro
power system,” Electrical Power Components And Systems, 31, pp. 81-94, 2003.
[28]A. Hasanovic, and A. Feliachi, “Genetic Algorithm based inter-area oscillation damping controller design using MATLAB,”
Power Eng. Soc. Summer Meeting, vol. 3, pp. 1136–1141, 2016.
[29]K. Sebaa, and M. Boudour, “Optimal locations and tuning of robust power system stabilizer using genetic
[30]algorithms,” Electric Power Systems Research, vol. 79, pp. 406–416, 2009.
[31]M.A. Abido, and Y.L. Abdel-Magid, “Coordinated design
of a PSS and an SVC-based controller to enhance power system stability,” Electrical Power and Energy Systems, vol. 25, pp.
695–704, 2003.
[32] A.M. El-Zonkoly , A.A. Khalil, and N.M. Ahmied, “Optimal tunning of lead-lag and fuzzy logic power system stabilizers
using particle swarm optimization,” Expert Systems with Applications, vol. 36, pp. 2097–2106, 2009.
[33] F. Glover, and M. Laguna, Tabu Search, Springer, 2014.
[34] M.A. Abido, “A novel approach to conventional power system stabilizer design using tabu search”, Electrical Power and
Energy Systems, vol. 21, pp. 443–454, 2015.
[35] S. Kirkpatrick, C.D. Gelatt and M. P. Vecchi, “Optimization by simulated annealing”, Science, vol. 220, Number 4598, pp.
671-680, 2015.
[36] A. Das, and B.K. Chakrabarti, Quantum Annealing and Related Optimization Methods, Lecture Note in Physics, Vol. 679,
Springer, Heidelberg, 2012.
[37] M.A. Abido, “An efficient heuristic optimization technique for robust power system stabilizer design,” vol. 58, no. 2, pp. 53-
62, June 2016.
K.M. Passino, ,“Biomimicry of Ba cterial Foraging for Distributed Optimization and Control, ” IEEE Control Systems Magazine,
vol. 22, no. 3, pp. 52-67, June 2016.
[38]Mishra, M. Tripathy, and J. Nanda “Multi-machine power system stabilizer design by rule based bacteria foraging,” Electric
Power Systems Research, vol. 77, pp. 1595–1607, 2007.
[39]T.T. Lie, and A.M. Sharaf, “An adaptive fuzzy logic power system stabilizer,” Electric Power Systems Research, vol.38,
pp.75-81, 1996.
[40] P.K. Dash, A.C. Liew, and B.R. Mishra, “An adaptive PID stabilizer for power systems using fuzzy logic,”
[41] Electric Power Systems Research, vol. 44, pp.213–222, 2015.
[42]M.B. Djukanovic, D.M Dobrijevic, M.S Calovic, M. Novicevic, and D.J. Sobajic “Coordinated stabilizing control for the
exciter and governor loops using fuzzy set theory and neural nets,” Electrical Power & Energy Systems, vol. 19, No. 8, pp.
489-499, 2014.
[43] M.A. Abido, and Y.L. Abdel-Magid, “A fuzzy basis function network based power system stabilizer for generator excitation
control,” Electrical Power Systems Research, vol. 49, pp. 11-19, 2015..
[44]A. Afzalian, and D.A. Linkens, “Training of neuro fuzzy of power system stabilisers using genetic algorithms,” Electrical
power and Energy Systems, vol. 22, pp. 93-102, 2000.

[47] V. Mukherjee, and S.P. Ghoshal, “Intelligent particle swarm optimized fuzzy pid controller for AVR system,” Electrical
Power Systems Research, vol. 77, no. 12, pp. 689-1698, October 2007.
[45] stabilizer via integrated tabu-fuzzy knowledge based controller,” Electrical Power and Energy Systems, vol. 25, pp. 543- 550,
2003.
[46]O.P. Malik, “Amalgamation of adaptive control and ai techniques: applications to generator excitation control,” Annual
Reviews in Control, vol. 28, pp. 97- 106, 2004.
[47] G. Hwang, D. Kim, J. Lee, and Y. An, “Design of fuzzy power system stabilizer using adaptive evolutionary algorithm,”
Engineering Applications of Artificial Intelligence, vol. 21, pp. 86-96, 2008.

Stabilization Of Power System Using Artificial Intelligence Based System

More Related Content

What's hot (19)

Similar to Stabilization Of Power System Using Artificial Intelligence Based System (20)

Recently uploaded (20)

Stabilization Of Power System Using Artificial Intelligence Based System