MINISTRY OF EDUCATION AND TRAINING

UNIVERSITY OF TRANSPORT AND COMMUNICATIONS

NGUYỄN DUY TRUNG

RESEARCH ON CONSTRUCTING
THE HYDROELECTRIC TURBINE SPEED CONTROL
SYSTEM FOR INTERCONNECTED AREA
BASED ON FUZZY LOGIC
AND ARTIFICIAL NEURAL NETWORKS

Course: Control Engineering and Automation

Code: 9520216

SUMMARY OF
ENGINEERING DOCTORAL THESIS

HÀ NỘI – 2020
The Thesis was completed at:
UNIVERSITY OF TRANSPORT AND COMMUNICATIONS

Scientific Instructors::
1. Prof., Dr. Lê Hùng Lân
2. Associate Prof., Dr. Nguyễn Văn Tiềm

Reviewer 1:

Reviewer 2:

Reviewer 3:

The thesis will be defended to the University - Level Doctoral

Dissertation Reviewer Council at Room Conference room on 4th
floor, Building A8 In University of Transport and Communications
(No. 3 Cau Giay, Hanoi) at .......................... date........../............./2020.

The thesis can be found at:

- Vietnam National Library
- Library of University of Transport and Communications
 1
PREAMBLE
1. The reason for choosing the topic
For the current Vietnamese electricity system, raising the capacity
and stabilizing the system to meet the electricity demand is very urgent
and necessary. In order to meet the electricity demand for power loads
and improve the quality of electricity, the Government, ministries,
branches and localities have introduced many preferential policies to
encourage corporations and private enterprises. and foreign enterprises
invest in building power generation plants to supply the Vietnamese
electricity system, with special priority given to renewable energy in
order to improve the quality of electricity and ensure national energy
safety and security. .
In our country today, the construction of smart grid system requires
integrating many diverse energy sources to ensure national energy
security, so the connection of power sources and hydropower plants is
important and necessary. This problem will be focused on solving by the
PhD student in the thesis with the topic: "Research on building regional-
linked hydroelectric turbine speed control systems on the basis of fuzzy
logic and artificial neural networks".
2. The purpose of the topic
Researching and building models of regional-linked hydropower
turbine speed control system.
Research on building regional-linked hydroelectric turbine speed
control system on the basis of fuzzy logic and artificial neural networks
to improve control quality.
3. Research method
Study the actual technological process of the operating mode of the
hydroelectric automation system.
Research, construct and survey a simulation model of a hydraulic
generator turbine based on Matlab / Simulink simulation tool with actual
parameters of the unit, using new intelligent control algorithms.
4. Object and scope of the study
- Researching equipment and technology for turbines for
hydroelectric plants in single and two regions.
- Study the process of operating the plant and power system, study the
fault types of the unit and the influence of parameters such as: Unit
failure, generator capacity, frequency when load changes. , linking with
factories in the power supply area.
Designing PI type fuzzy logic controller is based on optimization
algorithms such as instrumentation optimization (PSO), genetic
algorithm (GA), differential evolution (DE).
 2
Synthesis of the neuron controller combined with predictive control
algorithms (ANN - MPC), nonlinear regression (NARMA), adaptive
control with reference model (MRAC) applied in frequency control load
numbers of hydropower systems linking the two regions.
5. Scientific and practical significance
* Scientific significance:
Develop the intelligent control algorithms based on the application of
fuzzy control and neural networks for synthesis of hydroelectric turbine
speed controller of two – area interconnected system when the load
changes.
* Practical significance:
The results of this study is the basis for experimentation towards
manufacturing smart controllers to improve the control quality of
hydroelectric turbine controller for current hydroelectric plants in
Vietnam.
6. New results achieved
- Synthesize the optimal PI, PD fuzzy controller for two-area
connected hydropower turbine speed (frequency) controller with 03
algorithms using Particle swarm optimization (PSO), Genetic algorithm
(GA) and Differential evolution (DE) algorithm.
- Synthesize the optimal neural controller for two-area connected
hydropower turbine speed (frequency) controller with 03 algorithms
using Predictive control (MPC), Nonlinear regression control (NARMA
) and Model reference adaptive control (MRAC). The correction
parameters were determined through the PSO algorithm.
7. Research content
The thesis is structured with: Introduction and 5 chapters, conclusions
and recommendations, list and research works, annexes of drawings and
references.
CHAPTER 1
OVERVIEW OF INTERCONNECTED AREA
HYDROELECTRIC TUABIN SPEED CONTROL FOR GRID
FREQUENCY STABILIZATION
1.1. Introduction to Vietnam hydroelectricity
In our country, hydroelectricity accounts for a high proportion in the
structure of electricity production. Currently, although the power sector
has diversified its power sources, hydroelectricity still accounts for a
significant proportion. In 2014, hydroelectricity accounted for about
32% of total electricity production. According to forecasts of Power
 3
Planning VII (PDP VII), by 2020 and 2030, the proportion of
hydropower is still quite high, corresponding to 23%.

Figure 1.1. Hydroelectric plant model

1.2. Automation systems in hydroelectric plants
In the hydroelectric plant, the automation system in the plant is very
important, because all operations and troubleshooting are done
automatically.
1.3. The problem of controlling frequency and active power in the
electrical system
1.4. The problem of frequency control of generation with regional
linkage
1.5. Review of studies
- Overseas research:
In the world, the research on integrated control systems for single-
area has been studied for a long time, now basically solved the small load
and independent power generation. Currently getting more attention in
applying intelligent control theory such as fuzzy system and artificial
neural network system.
The problem of automatic generator control (AGC) or LFC load
frequency control in electrical systems has a long history and is one of
the most important topics of interconnected electrical systems. In an
electrical system, the LFC controller as an auxiliary generator plays an
important and fundamental role in maintaining the electrical system
reliability at an adequate level. In LFC practice, components rapidly
change system signals that are virtually invisible due to the filters
involved in the process. That is why further reduction in LFC response
time is neither possible nor desirable. In practice, the quality of an LFC
 4
system depends on the quality of the control signals. This compensation
generation is related to the short-term balance of power, the frequency of
the power system has a key role to enable power exchange and better
power supply to electrical loads [60], [61] , [66], [71], [73].
Additional controls have been applied to effectively adjust the ACE
to zero. Research work also contributes to LFC's designs based on
various control techniques.
Discrete modeling of the LFC in two-zone power systems is shown in [21].
LFC

One area PS – For Classic control GRC and GDB

Research gap
(1 area) HVDC method nonlinear

Two area PS for DG and The optimal Objective Trend research

(2 regions) RERs control method functions direction

Three area Smart gird Adaptive Computer –

(3 regions) controls based control

Four area Sustainable

Small gird Compression
(4 regions) controls

Figure 1.6. LFC system

Table 1.2. Comparison between recent studies on the topics
LFC / AGC in the document
Area Skill
Document Source type Controller Type
number optimization
[101] 2 Thủy điện - Nhiệt điện FLC Fuzzy
[96 2 Thủy điện - Nhiệt điện, Ga I IPSO
[102] 2 Hydropower- Thermal power, Gas OOPC -
[97] 2 Hydropower - Wind - Diesel PIDD TLBO
[98] 2 Thermal power, Gas I,PI,ID,PID DE
[103] 2 Thermal power Fuzzy - PID FA
[99] 2 Thermal power I -
[78] 3 Hydropower- Thermal power, Gas I IPSO
[79] 2 Hydropower- Thermal power PID ICA
[80] 2 Hydropower- Thermal power DMPC DMPC
[81] 3 Hydropower- Thermal power, Gas PID QOHC
[82] 2 Hydropower- Thermal power, Gas FOPID IPSO
[83] 2 Thermal power DMPC DMPC
[84] 2 Hydropower- Thermal power, Gas FOFPID BFOA
[85] 2 Hydropower- Thermal power ANFISC ANFIN -PS
[86] 2 Thermal power PID PSA
[87] 2 Thermal power CHB _I -
[88] 2 Thermal power I CSA
 5
Area Skill
Document Source type Controller Type
number optimization
[89] 2 Thermal power I+ FLC BFO
[90] 2 Hydropower- Thermal power, Gas I OHS
[91] 2 Hydropower- Thermal power, Gas FOFPID ICA
Hydropower- Thermal power -
[92] 2 I CRPSO
Diesels
[93] 2 Hydropower- Thermal power I CRPSO
[94] 2 Hydropower- Thermal power I ICA
[95] 2 Hydropower- Thermal power, Gas PI PSO -SCA
- Research in the country
In which [9] studied PID controller with fuzzy correction applied to
the problem of hydroelectric turbine operating load in independent mode.
In [8] "Application study of neural fuzzy network to build control
algorithm for hydroelectric turbine velocity control" applied fuzzy neural
network algorithm to adjust PID controller parameters. In [10], research
and application of modern measurement and control solutions to improve
the quality of frequency stability in small and medium hydropower
plants. The method of backstepping, optimal control and Kalman
filtration has been introduced to build adaptive controller to improve the
quality and stability of turbine rotation frequency in small and medium
hydro power plants.
1.6. Select a topic name and research direction
Through analysis, the author chooses the title of the topic: "Research
on building regional-linked hydroelectric turbine speed control system
on the basis of fuzzy logic and artificial neural networks"
1.7. Thesis objectives
- Researching and building models
of interconnected area hydropower
turbine speed control system.
- Research on building
interconnected area hydroelectric
turbine speed control system on
the basis of fuzzy logic and
artificial neural network, using
optimization algorithms to
improve control quality.
- Compare the proposed control
strategies to find the most suitable Figure 1.7. Thesis implementation
control solution for the given process
problem.
 6
1.8. Conclusion chapter 1
- The thesis has analyzed the problem of hydropower turbine speed
control, an overview of domestic and foreign studies on design of
hydroelectric turbine speed control system.
On the basis of these analyzes, the thesis sets out the design of a
hydroelectric turbine speed control system linking two regions to
stabilize the load frequency based on the application of intelligent control
techniques of fuzzy logic and neural network, applying optimization
algorithm PSO, GA, DE ...
The published results [CT5] belong to the list of published scientific
works of the thesis.
CHAPTER 2
DYNAMIC MODEL OF THE INTERCONNECTED AREA
HYDROELECTRIC GENERATOR TURBINE SYSTEM
2.1. Structure diagram of single-area hydropower system

Figure 2.2. Model of single-area hydropower system

2.1.1. Pressure piping model
 ht ( s )
 TW ( s) (2.1)
ut ( s)
where TW  Lur is constant water start time at rated load, (s),
ag hr
2.1.2. Model of electric - hydraulic servo system,
 g e ( s) 1
Wg ( s)   (2.3)
 xe ( s) 1  s.Tg
2.1.3. Model of hydraulic turbine
 P m ( s) 1  Tw s
w t ( s)   (2.4)
 g ( s) 1  0.5Tw s
2.1.4. Model generator
 7

 ( s) 1
w p ( s) 
 (2.5)
 P m ( s)   P e ( s) Ms  D
2.1.5. Investigation of system dynamics
2.2. Hydropower system model linking two regions

Figure10 (a)

Figure 10 (b)
Figure 2.10. Hydropower system links the two regions
2.3. Hydroelectric generator turbine speed control system model
linking two regions
1
B1 R1
Pref1 Xe1 g1(s) PL1
P1HV(s) Pm1

1 Tw1.s  1 1
Remote 1
controll 1 Tg1.s  1 . 1
0.5Tws M 1s  D1
Tp1.s1
ACE1
Speed ​1 Wing direction 1 Tua bin 1 Generator 1

1
s
2T12

-1
-1

Pref 2 Xe2 g2(s) P2HV(s) Pm2

1 Tw2.s  1 1
Remote 1
controll 2
`
Tg 2.s  1 . 1
0.5Tws M 2 s  D2
Tp2.s1

Speed ​2 Wing direction 2 Tua bin 2 Generator 2

PL 2
1
B2
ACE2 R2

Figure 2.15. Control system mathematical model diagram

Hydropower links the two regions
 8
In the thesis, the simulation examples are performed with values
of system parameters as follows [11,16,18]:
Tg1  Tg 2  48.7(s) ; Tw1  Tw 2  1(s)
Tr1  Tr 2  0.513 (s); M1  M 2  0.6 (s);
D1  D2  1 (pu); R1  R2  2.4 (Hz/p.u)
T12  0.0707 (pu)
2.4. Conclusion chapter 2
In this chapter, the thesis has built the mathematical model of the
basic functional blocks of the single-zone hydropower turbine control
system and the regional connection.
Surveying the working characteristics of functional blocks of 2-zone
linked hydropower system, giving a schematic diagram of the speed
control system of hydropower turbines linking two regions.
The results are published [CT4] in the list of published scientific
works of the thesis.
CHAPTER 3
DESIGNING A INTERCONNECTED AREA HYDROELECTRIC
TUABINE SPEED CONTROLLER ON THE BASIS OF FUZZY LOGIC
TO STABILIZE THE LOAD FREQUENCY
3.1. PID law fuzzy controller
* Fuzzy controller according to PID law
* Fuzzy controller according to PD law
* Fuzzy controller according to PI law
3.2 Controller parameter optimization algorithms
3.2.1 The algorithm of PSO swapping
3.2.2 GA genetic algorithm
3.2.3 DE differential evolution algorithm
3.3. Hydropower turbine speed controller design linking 2 zones to stabilize
the frequency when the load changes
FLC 1 CONTROL-AREA 1 ∆PL1
ACE 1(t) ∆f1
Governor Turbine Generator

Compute
∆Ptie12

ACE 2(t)
Governor Turbine Generator
∆f2
∆PL2
FLC 2 CONTROL-AREA 2
Figure 3.7. Hydropower network diagram linking two regions
 9
3.2.1. Design FLC1 and FLC 2 type PI controller
PI-type Fuzzy
Knowledge
logic controller
base
Fuzzification Defuzzification
e(t ) E(t) interface interface
Ge Decision- un(t)
u(t)
d making Gu 
dt Gce logic U(t)
ce(t) CE(t)

r(t) e(t) Fuzzy logic u(t) Control y(t)

_
controller plant
Setpoint
ym(t)

Sensor &
transmitter
Figure 3.8. Typical PI type fuzzy logic controller architecture for the controller
Table 3.1. Suggested fuzzy rule table for PI / PD type fuzzy controller
DE(t)
E(t)
NB NM NS ZE PS PM PB
NB PB PB PB PM PM PS ZE
NM PB PM PM PM PS ZE NS
NS PB PM PS PS ZE NS NM
ZE PM PM PS ZE NS NM NM
PS PM PS ZE NS NS NM NB
PM PS ZE NS NM NM NM NB
PB ZE NS NM NM NB NB NB
3.2.2. Design FLC1 and FLC 2 type PD controller

Figure 3.9. PD-type fuzzy logic controller structure incorporates

optimal PSO algorithm
 10
3.2.3. Optimization of fuzzy controller parameters

Figure 3.10. PI-type fuzzy logic controller structure incorporates

optimal PSO algorithm
3.2.4. Simulation of hydroelectric turbine speed control system linking
2 regions

Figure 3.11. PID controller parameters

3.2.4.1. Simulate a PI-type FLC controller with PSO combination
3.2.4.2. Some simulation results
Single area hydroelectric plant
The objective function is to minimize the criteria of the integral error
[1], [11].
 11
T T
J   | e(t ) | dt   | r (t )  y (t ) | dt  min (3.14)
0 0

Figure 3.17. Simulation results for a single-area hydropower plant

(a) Load change; (b) Frequency deviation (speed) response

Figure 3.18. Compare the three FLC controllers for the case
single area hydroelectric plant
Hydropower system links the two regionsThe target function used in
optimization is given by the formula (3.15) below:
T
J   | f1 (t ) |  | f 2 (t ) |  | Ptie,12 (t ) | dt  min (3.15)
0
 12

Figure 3.20. Convergence of PSO algorithm

Figure 3.21. Update correction coefficients using PSO algorithm

Figure 3.22. Compare three fuzzy controllers applying different bio-

optimization algorithms (PSO, GA and DE)
 13

Figure 3.23. Target functions in two-zone linked hydroelectric systems

applying fuzzy logic controllers applying three optimization algorithms
3.4. Conclusion chapter 3
In this chapter, the thesis proposes design options for FLC fuzzy controller
to control hydroelectric turbine speed connecting two regions. FLC fuzzy
controllers have a PI or PD structure with three parameters that need to be
adjusted. These parameters can be optimized by applying biological
optimization algorithms such as PSO herd optimization, GA evolution algorithm
and DE differential evolution algorithm. The numerical simulation results
deployed in MATLAB / Simulink software contributed to confirm the efficiency
of the proposed FLC controllers. The proposed fuzzy controllers offer better
control quality when compared to conventional PID controllers and exhibit an
effective control strategy for handling a class of complex engineering objects.
The results were published at the International Conference (ICACR 2019) in
the work No. [CT1]. Under the SCOPUS category, in the published list of the
thesis's scientific works.
CHAPTER 4
DESIGNING A INTERCONNECTED AREA HYDROELECTRIC
TUABINE SPEED CONTROLLER ON THE BASIS OF ARTIFICIAL
NEURAL NETWORK TO STABILIZE THE LOAD FREQUENCY
4.1. Question
4.2. Applying artificial neural network to synthesize zone-linked
hydroelectric turbine speed controller
4.2.1. Basic concepts of neural networks
4.2.2. Methods of training artificial neural networks
4.2.2.1. Supervised Learning
4.2.2.2. Reinforcement learning
4.2.2.3. Unsupervised Learning (Unsupervised Learning)
Table 4.1 Comparing three learning methods of neural networks
Human brain Artificial neural network
Learn with the guidance of a teacher Supervised Learning
Learning with teacher evaluation reinforcement learning
Self-study Unattended study
 14
4.2.2.4. Single layer transmission network
4.3. Strategies for controlling turbine speed in the problem of
hydropower system frequency control using artificial neural networks
4.3.1. The frequency-load control strategy uses a NARMA-L2 controller

Figure 4.9. Model of 2-zone linked hydroelectricity using

NARMA - L2 controller based on ANN
4.3.2. The LFC controller is based on MRAC
4.3.3. MPC ANN application for LFC
4.3.3.1. Structure of MPC is based on ANN

Figure 4.11. ANN model of MPC applied for the ith control area
4.3.3.2. LFC strategy Apply MPC ANN application
(i) Scenario 1: The ANN application MPC is applied to the single-
area electricity system as shown in Figure 4.20 (a).
(ii) Scenario 2: ANN based MPC type LFC controller applied for
hydropower system linking two regions as shown in Figure 4.20 (b).
T
 
J     fi (t )   Ptie,ij dt. (4.16)
0 i i, j 
 15

(b)
Figure 4.12. Control structure of hydroelectric systems Adopt LFC controller
(a) Single-area hydropower plant (b) Hydropower system linking two regions
4.4. The simulation results
4.4.1. Single-zone hydroelectric controller using a neuron controller

Figure 4.13. Single-region hydroelectricity model

4.4.2 Hydropower control connects two regions using a neuron
controller
4.4.2.1. Simulation results for NARMA and MRAC controller
(i) In the first scenario, the variable load occurs in each area at
different times and intensity (see Figure 4.16-4.18).

Figure 4.16. Simulation results for the first simulation scenario

(a) Load changes; (b) Dynamic response of frequency deviation in the first
region; (c) Dynamic response of frequency deviation in the second region
 16

Figure 4.17. Deviation of exchanged power on the line

in the first simulation case

Figure 4.18. The target function for the first simulation scenario
Table 4.3. Comparison results are based on several control criteria
in the first simulation case
PID NARMA MRAC
Standard
ACE1 ACE2 ACE1 ACE2 ACE1 ACE2
IAE 8.6040 9.0902 2.4292 2.9809 3.0097 3.4023
ISE 0.4119 0.5678 0.0792 0.1844 0.0942 0.2010
ITAE 1233.0 1317.0 215.6 325.8 293.0 374.8
ITSE*10-3 6243.2 9055.6 850.4 2575.7 1059.8 2836.0

Figure 4.19. Simulation results for the second scenario

(a) Change the load in the first sector
(b) Variation of frequency deviation in the first region
 17

Figure 4.20. Objective functions for the second simulation

Table 4.4. Quality comparison of controllers based on two control
standards IAE and ISE for the second simulation case
Standard PID NARMA MRAC
IAE 39.1473 24.9040 24.6673
ISE 6.7665 2.8997 2.8608
The simulation results show superior efficiency of NARMA and MRAC
neuron controllers compared to PID controllers.
4.4.2.2. Simulation results for MPC controller

Figure 4.21. Training of two LFC controllers

based on ANN - typical results
 18

Figure 4.22. Hydroelectric plant simulation results linking two regions

(a) Load changes; (b) the frequency deviation of the first control zone;
(c) Frequency deviation of the second control area

Figure 4.23. Power exchanged on the line and the target function
(a) Associated current; (b) The objective function
Table 4.5: Comparison results based on some control criteria
Standard PID MPC
IAE (*10-3) 0.0378 0.0266
ISE (*10-3) 0.0047 0.0034
ITAE (*10-3) 7.4247 5.1596
ITSE (*10-3) 0.8990 0.6432
4.5. Conclusion chapter 4
The simulation results using MATLAB / Simulink software have
demonstrated the superiority of the above three controllers over the
classic controller like PID.
When evaluating and comparing each LFC controller using artificial
neural network, some comments can be made as follows:
 19
- NARMA-L2 controller has faster network training time because
there is no need to identify the control object, when the control object is
linearized.
- The MRAC controller requires two processes: controller object
identification and neural network training for the controller.
- The MPC controller only needs the process of identifying the control
object, but because MPC is the predictive controller, it takes a lot of time
to run the simulation.
The results are published in the work number [CT2], [CT3] in the
published list of scientific works of the thesis.
CHAPTER 5
ANALYZING AND EVALUATING THE EFFICIENCY OF
SOLUTIONS FOR INTELLIGENT CONTROL OF TURBINE SPEED
IN HYDROELECTRIC PLANTS
5.1. Question
5.2. Synthesize and analyze control solutions for single-area and
interconnected area hydropower plants
5.2.1. Schematic diagram of a single-area hydroelectric plant using
fuzzy controller and neural network

Figure 5.1. Model of application controllers for single zone

Figure 5.3. Comparing the response of the generator speed difference

when using controllers applying fuzzy logic and neural networks
and PID - single area
 20
5.2.2. Hydroelectric turbine speed control system model linking 2 zones
to stabilize load frequency

Figure 5.4. Model of application controllers for linking 2 zones

Figure 5.5. Load changes for each region

Figure 5.6. Speed deviation Figure 5.7. Speed deviation

response for zone 1 using different response for zone 2 using different
turbine speed controllers turbine speed controllers

Figure 5.8. Valve position control Figure 5.9. Zone valve position
signal in zone 1 control signal 2
 21

Figure 5.10. Mechanical power Figure 5.11. Mechanical power

deviation for zone 1 deviation for zone 2

Figure 5.12. Speed deviation for zone 1

(a) Speed deviation (b) Speed deviation

Figure 5.13. Speed deviation for zone 2

(a) Power deviation (b) Power deviation

Figure 5.14. Power deviation on line by area 1.2
- In area 1 (zone 1).
 22

(a) (b)
Figure 5.15. Area control area deviation 1

(a) ACE region signal deviatio (b) ACE region signal deviation
Figure 5.16. ACE region signal deviation - absolute value

Figure 5.17. ITAE indicator for zone control error 1 signal

In Figure 5.17 we plot to compare the quality of the considered units, we
see good quality MPC controller then NARMA controller and MRAC
controller, next is FLC controller and finally PID controller.
In area 2 (zone 2)

Figure 5.18. Zone control area deviation 2

 23

Figure 5.20. ITAE indicator for zone control bias signal 2

In Figure 5.20, we plot to compare the quality of the considered units,
we see the best quality MPC controller then MRAC controller,
NARMA next is FLC controller and finally PID controller.
Table 5.1. Comparison of the controllers based on the ITAE quality
index for generator speed error response
Comparison Remote control
criteria MRAC NARMA PID FLC MPC
Area 1 0.40091 0.26399 0.43384 0.41620 0.342361
Area 2 0.40094 0.26401 0.51285 0.41622 0.34238
Table 5.2. Comparison of the controllers based on ITAE quality
criteria for line interchange power deviation between two zones
Comparison Remote controll
criteria P12_ MRAC P12_ NARMA P12_ PID P12_ FLC P12 _ MPC
ITAE 0.314738 0.32221 4.154547 0.32321 0.270638
5.3. Conclusion chapter 5
In this chapter, the thesis has synthesized, simulated, and compared
different solutions applying fuzzy logic controller and neural network
designed in the previous chapters for single-zone hydropower and 2-zone
linkage.
- Intelligent control solutions using fuzzy controller and neuron are
all higher quality than using PID controller.
- In principle, the system uses a higher speed neuron controller, but
needs time to train the network.
- With single area: Neural network controller using MPC gave the
best results in adjustment quality, static deviation, transient process
compared with PI and MRAC, NARMA-L2 fuzzy controllers.
 24
- For regional linkage: Depending on the location, there are appropriate
optimal solutions, with the control areas being NARMA-L2 neuron
controllers, and the link line capacity is the controller. MPC neuron.
For example, if the hydropower system is single-area, does not
require fast action time, you can choose an MPC controller. However, if
fast action time is required, the NARMA-L2 controller selection solution
can be considered. The fuzzy controller has the advantage when the
subject is uncertain.
CONCLUSIONS AND RECOMMENDATIONS
A. Results achieved
- Construction of hydraulic turbine control system for interconnected area.
- Design of PI and PD-type optimized fuzzy logic controllers based on
applying PSO flocking optimization algorithms, GA evolution algorithm
and DE differential evolution for interconnected area hydraulic turbine
control system.
- Synthesize 03 artificial neural network controllers based on the principles of
predictive control MPC, adaptive control with reference model MRAC, linear
regression NARMA - L2 for interconnected area hydraulic turbine control
system. Applying the bio-optimization algorithm of PSO herds to find the
optimal correction coefficients for the proposed controllers.
- Building a computer simulation program to compare and evaluate control
solutions set out in the thesis
B. The new results of the thesis:
- Synthesize the optimal PI, PD fuzzy controller for two-area connected
hydropower turbine speed (frequency) controller with 03 algorithms
using Particle swarm optimization (PSO), Genetic algorithm (GA) and
Differential evolution (DE) algorithm.
- Synthesize the optimal neural controller for two-area connected
hydropower turbine speed (frequency) controller with 03 algorithms
using Predictive control (MPC), Nonlinear regression control (NARMA)
and Model reference adaptive control (MRAC). The correction
parameters were determined through the PSO algorithm.
C. Recommendation:
The research results achieved in the dissertation can be used for the
purpose of training, testing research, and manufacturing to replace the
current PID controllers used for hydroelectric plants in Vietnam.
Continue to research, perfect and develop smart controllers and use
optimal algorithms to manufacture controller applications for
hydroelectric plants in Vietnam.
 PUBLICATION
[CT1]. DuyTrung-Nguyen,NgocKhoat-Nguyen,HungLan-Le,
VanTiem-Nguyen (2019), Publication: ICACR 2019:
Proceedings of the 2019 3rd International Conference on
Automation, Control and Robots, October 2019 Pages 61-66
Designing PSO-Based PI-type Fuzzy Logic Controllers: A
Typical Application to Load-Frequency Control Strategy of an
Interconnected Hydropower System. https://doi.org/10.1145/
3365265.3365278. (Ei Compendex and Scopus).
[CT2]. DuyTrung-Nguyen,NgocKhoat-Nguyen,HungLan-Le,
VanTiem-Nguyen (2020), Intellgent ann - Based load
frequency control strategies for an interconnected
hydropower system Journal of military science and
technology research. Page (43-54).No 65.
[CT3]. DuyTrung-Nguyen,NgocKhoat-Nguyen,HungLan-Le,
VanTiem-Nguyen (2020); Study on application of ann - based
MPC controller for load - frequency control of an
interconnested hydropower Plant, Journal of military science
and technology research. Page (86 -97).No 65.
[CT4].DuyTrung-Nguyen,NgocKhoat-Nguyen,HungLan-
Le,VanTiem-Nguyen, Thi Thu Huong- Hoang, Thi Mai
Phuong- Dao (2020), Research to build mathematical
models for regional-linked hydropower systems in the
problem of stable turbine speed. Journal of Science and
Technology: Volume 56, No. 3 jun /2020. Page (29-34) P
-ISSN;1859; E-ISSN 2615 - 9619.
[CT5] DuyTrung-Nguyen,NgocKhoat-Nguyen,HungLanLe,
VanTiem-Nguyen,ThiThu Huong- Hoang, Thi Mai Phuong-
Dao (2020), Overview of turbine speed control in regional
linked hydropower systems for grid frequency stabilization,
Journal of Science and Technology: Volume 56, No 2 Apr
2020. Page (38-43) P -ISSN;1859; E-ISSN 2615 - 9619.
[CT6]. Nguyen Duy Trung Hoang Thi Thu Huong, Le Hung Lan,
Nguyen Van Tiem, Comparison analysis of intelligent
controllers for hydropower turbine speed control, Journal
of Science and Technology: Vol. 56, No. 5 ( October 2020).
P -ISSN; 1859; E-ISSN 2615 - 9619. (accept post)