63 anfis based neuro-fuzzy controller in lfc of windmicro hydro-diesel hybrid power system (1).docx

ANFIS BASED NEURO-FUZZY CONTROLLER IN LFC OF WINDMICRO HYDRO-DIESEL HYBRID POWER SYSTEM

CHAPTER 1

1.1 INTRODUCTION

Nowadays, electricity generation is very important because of its increasing

necessity and enhanced environmental awareness such as reducing pollutant emissions.

The dynamic behavior of the system depends on disturbances and on changes in the

operating point. The quality of generated electricity in power system is dependent on the

system output, which has to be of constant frequency and must maintain the scheduled

power and voltage. Therefore, load frequency control, LFC, is very important in order to

supply reliable electric power with good quality for power systems. The wind- micro

hydro –diesel system is one of the hybrid systems utilizing more than one energy source.

For the increasing demand of electricity due to developments at a faster rate, it is

becoming difficult to meet the increasing demand of electricity only with conventional

sources.

In most remote and isolated areas, electric power is often supplied to the

local community by diesel generators. However, diesel generators cause significant

impacts on the environment. [2]. Due to the environmental and economic impacts of a

diesel generator, interest in alternative cost-efficient and pollution free energy generation

has grown enormously. Currently, wind is the fastest growing and most widely utilized

renewable energy technology in power systems. Wind power is economically attractive

when the wind speed of the proposed site is considerable for electrical generation and

electric energy is not easily available from the grid [1]. Wind power is intermittent due to

worst case weather conditions, so wind power generation is variable and unpredictable.

Wind power is not fully controllable and their availability depends on daily and seasonal

patterns [3]. As a result, conventional energy sources such as diesel generators are used in

conjunction with renewable energy for reliable operation. The hybrid wind power with

diesel generation has been suggested by [2] and [3] to handle the problem above. To meet

the increasing load demand for an isolated community, expansion of these hybrid power

systems is required. One possible option available is to add a micro hydro generating unit

in parallel, where water streams are abundantly available.

Dr. KVSRIT Department of EEE


The resulting wind-micro hydro-diesel hybrid power system must provide

good quality service to the consumer load, which depends mostly on the type and action

of the generation controller. The unsteady nature of wind and frequent change in load

demands may cause large and severe oscillation of power. The fluctuation of output

power of such renewable sources may cause a serious problem of frequency and voltage

fluctuation of the grid [2]. An effective controller for stabilizing frequency oscillations

and maintaining the system frequency within acceptable range is significantly required.

Therefore, a control system is required to detect the load changes and its mechanical

power production and stabilize the system frequency [4].

The supplementary controller of the diesel generating unit, called the Load

Frequency Controller, may satisfy these requirements. The load frequency control (LFC)

maintains the frequency deviation from its nominal value to within specified bounds and

dynamic performance of the system [7],[8],[9] . The function of the load frequency

controller is to eliminate a mismatch created either by the small real power load change or

due to a change in input wind power. The Load Frequency control (LFC) or Automatic

Generation Control (AGC) has been one of the most important subjects concerning power

system engineers in the last decades. Research studies were conducted for Load

Frequency control of Thermal and Hydro power system with conventional and intelligent

controllers [6],[11]-[14]. Load Frequency controller was designed with conventional PI

controller for wind- diesel hybrid system [5] and for wind-diesel- hydro hybrid power

system [1 6].[17]. LFC using Fuzzy logic controller with optimization techniques for

wind –diesel hybrid system was presented in [1 5].

LFC using ANFIS based controllers for thermal and Hydro thermal

systems are presented in [20] and [21] respectively. In the proposed paper, adaptive

Neuro-Fuzzy Inference System based Neuro-Fuzzy controller is designed for Load

Frequency Control of wind micro hydro-diesel hybrid power system. The ANFIS based

Neuro-Fuzzy controller for a governor in diesel side and for a blade pitch control in wind

side are designed individually for performance improvement of the Wind-micro hydro-

diesel hybrid system.



Simulations are performed for load frequency control in an isolated

wind micro hydro- diesel hybrid power system with different load disturbances by the

proposed ANFIS based Neuro-Fuzzy controller and also with conventional PI and fuzzy

logic controller for comparison. The proposed adative Neuro Fuzzy Inference System

trains the parameters of the Fuzzy logic controller and improves the system performance.

Simulation results show the superior performance of the proposed Neuro- fuzzy controller

in comparison with the conventional PI controller and fuzzy logic controller in terms of

the settling time, overshoot against various load changes.



CHAPTER 2

2.1 INTRODUCTION TO FUZZY LOGIC:

In recent years, the number and variety of applications of fuzzy logic have

increased significantly. The applications range from consumer products such as cameras,

camcorders, washing machines, and microwave ovens to industrial process control,

medical instrumentation, decision-support systems, and portfolio selection.

To understand why use of fuzzy logic has grown, you must first understand what

is meant by fuzzy logic.

Fuzzy logic has two different meanings. In a narrow sense, fuzzy logic is a logical

system, which is an extension of multivalve logic. However, in a wider sense fuzzy logic

(FL) is almost synonymous with the theory of fuzzy sets, a theory which relates to classes

of objects with unsharp boundaries in which membership is a matter of degree. In this

perspective, fuzzy logic in its narrow sense is a branch of fl. Even in its more narrow

definition, fuzzy logic differs both in concept and substance from traditional multivalve

logical systems.

In fuzzy Logic Toolbox software, fuzzy logic should be interpreted as FL, that is,

fuzzy logic in its wide sense. The basic ideas underlying FL are explained very clearly

and insightfully in Foundations of Fuzzy Logic. What might be added is that the basic

concept underlying FL is that of a linguistic variable, that is, a variable whose values are

words rather than numbers. In effect, much of FL may be viewed as a methodology for

computing with words rather than numbers. Although words are inherently less precise

than numbers, their use is closer to human intuition. Furthermore, computing with words

exploits the tolerance for imprecision and thereby lowers the cost of solution.

Another basic concept in FL, which plays a central role in most of its

applications, is that of a fuzzy if-then rule or, simply, fuzzy rule. Although rule-based

systems have a long history of use in Artificial Intelligence (AI), what is missing in such

systems is a mechanism for dealing with fuzzy consequents and fuzzy antecedents. In

fuzzy logic, this mechanism is provided by the calculus of fuzzy rules. The calculus of



fuzzy rules serves as a basis for what might be called the Fuzzy Dependency and

Command Language (FDCL). Although FDCL is not used explicitly in the toolbox, it is

effectively one of its principal constituents. In most of the applications of fuzzy logic, a

fuzzy logic solution is, in reality, a translation of a human solution into FDCL.

A trend that is growing in visibility relates to the use of fuzzy logic in

combination with neuro computing and genetic algorithms. More generally, fuzzy logic,

neuro computing, and genetic algorithms may be viewed as the principal constituents of

what might be called soft computing. Unlike the traditional, hard computing, soft

computing accommodates the imprecision of the real world.

The guiding principle of soft computing is: Exploit the tolerance for imprecision,

uncertainty, and partial truth to achieve tractability, robustness, and low solution cost. In

the future, soft computing could play an increasingly important role in the conception and

design of systems who’s MIQ (Machine IQ) is much higher than that of systems designed

by conventional methods.

Among various combinations of methodologies in soft computing, the one that

has highest visibility at this juncture is that of fuzzy logic and neuro computing, leading

to neuro-fuzzy systems. Within fuzzy logic, such systems play a particularly important

role in the induction of rules from observations. An effective method developed by Dr.

Roger Jang for this purpose is called ANFIS (Adaptive Neuro-Fuzzy Inference System).

This method is an important component of the toolbox.

The fuzzy logic toolbox is highly impressive in all respects. It makes fuzzy logic

an effective tool for the conception and design of intelligent systems. The fuzzy logic

toolbox is easy to master and convenient to use. And last, but not least important, it

provides a reader friendly and up-to-date introduction to methodology of fuzzy logic and

its wide ranging applications.

2.2 What is fuzzy logic:

Fuzzy logic is all about the relative importance of precision: How important is it

to be exactly right when a rough answer will do?



You can use Fuzzy Logic Toolbox software with MATLAB technical computing

software as a tool for solving problems with fuzzy logic. Fuzzy logic is a fascinating area

of research because it does a good job of trading off between significance and precision—

something that humans have been managing for a very long time.

In this sense, fuzzy logic is both old and new because, although the modern and

methodical science of fuzzy logic is still young, the concept of fuzzy logic relies on age-

old skills of human reasoning.

fig 5.1 fuzzy description

2.3 Why use fuzzy logic:

Fuzzy logic is a convenient way to map an input space to an output space. Mapping

input to output is the starting point for everything. Consider the following examples:

With information about how good your service was at a restaurant, a fuzzy logic

system can tell you what the tip should be.



With your specification of how hot you want the water, a fuzzy logic system can

adjust the faucet valve to the right setting.

With information about how far away the subject of your photograph is, a fuzzy

logic system can focus the lens for you.

With information about how fast the car is going and how hard the motor is

working, a fuzzy logic system can shift gears for you.

To determine the appropriate amount of tip requires mapping inputs to the

appropriate outputs. Between the input and the output, the preceding figure shows a black

box that can contain any number of things: fuzzy systems, linear systems, expert systems,

neural networks, differential equations, interpolated multidimensional lookup tables, or

even a spiritual advisor, just to name a few of the possible options. Clearly the list could

go on and on.

Of the dozens of ways to make the black box work, it turns out that fuzzy is often

the very best way. Why should that be? As Lotfi Zadeh, who is considered to be the

father of fuzzy logic, once remarked: "In almost every case you can build the same

product without fuzzy logic, but fuzzy is faster and cheaper.".

2.4 When not to use fuzzy logic:

Fuzzy logic is not a cure-all. When should you not use fuzzy logic? The safest

statement is the first one made in this introduction: fuzzy logic is a convenient way to

map an input space to an output space. If you find it's not convenient, try something else.

If a simpler solution already exists, use it. Fuzzy logic is the codification of common

sense — use common sense when you implement it and you will probably make the right

decision. Many controllers, for example, do a fine job without using fuzzy logic.

However, if you take the time to become familiar with fuzzy logic, you'll see it can be a

very powerful tool for dealing quickly and efficiently with imprecision and nonlinearity.

2.5 What can fuzzy logic toolbox software do:

You can create and edit fuzzy inference systems with Fuzzy Logic Toolbox

software. You can create these systems using graphical tools or command-line functions,



or you can generate them automatically using either clustering or adaptive neuro-fuzzy

techniques.

If you have access to Simulink software, you can easily test your fuzzy system in

a block diagram simulation environment.

The toolbox also lets you run your own stand-alone C programs directly. This is made

possible by a stand-alone Fuzzy Inference Engine that reads the fuzzy systems saved from

a mat lab session. You can customize the stand-alone engine to build fuzzy inference into

your own code. All provided code is ansi compliant.

Because of the integrated nature of the mat lab environment, you can create your own

tools to customize the toolbox or harness it with another toolbox, such as the Control

System Toolbox, Neural Network Toolbox, or Optimization Toolbox software.

2.6 Fuzzy logic tool box:

The Fuzzy Logic Toolbox extends the MATLAB technical computing

environment with tools for designing systems based on fuzzy logic. Graphical user

interfaces (GUIs) guide you through the steps of fuzzy inference system design.

Functions are provided for many common fuzzy logic methods, including fuzzy

clustering and adaptive neuro fuzzy learning.

The toolbox lets you model complex system behaviors using simple logic rules and then

implements these rules in a fuzzy inference system. You can use the toolbox as a

standalone fuzzy inference engine. Alternatively, you can use fuzzy inference blocks in

simulink and simulate the fuzzy systems within a comprehensive model of the entire

dynamic system

2.6.1 Working with the fuzzy logic toolbox:

The Fuzzy Logic Toolbox provides GUIs to let you perform classical fuzzy

system development and pattern recognition. Using the toolbox, you can develop and

analyze fuzzy inference systems, develop adaptive neuro fuzzy inference systems, and

perform fuzzy clustering. In addition, the toolbox provides a fuzzy controller block that

you can use in Simulink to model and simulate a fuzzy logic control system. From



Simulink, you can generate C code for use in embedded applications that include fuzzy

logic.

2.6.2 Building a fuzzy inference system:

Fuzzy inference is a method that interprets the values in the input vector and, based on

user defined rules, assigns values to the output vector. Using the GUI editors and viewers

in the Fuzzy Logic Toolbox, you can build the rules set, define the membership functions,

and analyze the behavior of a fuzzy inference system (FIS). The following editors and

viewers are provided.

fig 2.2 fuzzy interference system

2.7 Key features:

■ Specialized GUIs for building fuzzy inference systems and viewing and analyzing

results

■ Membership functions for creating fuzzy inference systems

■ Support for AND, OR, and NOT logic in user-defined rules



■ Standard Mamdani and Sugeno-type fuzzy inference systems

■ Automated membership function shaping through neuroadaptive and fuzzy clustering

learning techniques

■ Ability to embed a fuzzy inference system in a Simulink model

■Ability to generate embeddable C code or stand-alone executable fuzzy inference

engines.



CHAPTER 3

3.1primary Gui Tools Of The Fuzzy Logic Toolbox:

In this section we'll be building a simple tipping example using the graphical

user interface (GUI) tools provided by the Fuzzy Logic Toolbox. Although it's possible to

use the Fuzzy Logic Toolbox by working strictly from the command line, in general it's

much easier to build a system graphically. There are five primary GUI tools for building,

editing, and observing fuzzy inference systems in the Fuzzy Logic Toolbox. The Fuzzy

Inference System or FIS Editor, the Membership Function Editor, the Rule Editor, the

Rule Viewer, and the Surface Viewer. These GUIs are dynamically linked, in that

changes you make to the FIS using one of them, can affect what you see on any of the

other open GUIs. You can have any or all of them open for any given system. These are

shown in Fig.1

Fig. 3.1 Primary GUI Tools of the Fuzzy Logic Toolbox



The FIS Editor handles the high level issues for the system: How many input and output

variables? What are their names? The Fuzzy Logic Toolbox doesn't limit the number of

inputs. However, the number of inputs may be limited by the available memory of your

machine. If the number of inputs is too large, or the number of membership functions is

too big, then it may also be difficult to analyze the FIS using the other GUI tools.

The Membership Function Editor is used to define the shapes of all the

membership functions associated with each variable. The Rule Editor is for editing the list

of rules that defines the behavior of the system.

The Rule Viewer and the Surface Viewer are used for looking at, as opposed to

editing, the FIS. They are strictly read-only tools. The Rule Viewer is a matlab-based

display of the fuzzy inference diagram shown at the end of the last section. Used as a

diagnostic, it can show (for example) which rules are active, or how individual

membership function shapes are influencing the results. The Surface Viewer is used to

display the dependency of one of the outputs on any one or two of the inputs that is, it

generates and plots an output surface map for the system.

The five primary GUIs can all interact and exchange information. Any one of

them can read and write both to the workspace and to the disk (the read-only viewers can

still exchange plots with the workspace and/or the disk). For any fuzzy inference system,

any or all of these five GUIs may be open. If more than one of these editors is open for a

single system, the various GUI windows are aware of the existence of the others, and will,

if necessary, update related windows. Thus if the names of the membership functions are

changed using the Membership Function Editor, those changes are reflected in the rules

shown in the Rule Editor. The editors for any number of different FIS systems may be

open simultaneously. The FIS Editor, the Membership Function Editor, and the Rule

Editor can all read and modify the FIS data, but the Rule Viewer and the Surface Viewer

do not modify the FIS data in any way.

We'll start with a basic description of a two-input, one-output tipping problem.

The Basic Tipping Problem. Given a number between 0 and 10 that represents the quality

of service at a restaurant (where 10 is excellent), and another number between 0 and 10



that represents the quality of the food at that restaurant (again, 10 is excellent), what

should the tip be?

3.2 Tripping Function:

The starting point is to write down the three golden rules of tipping, based on years of

personal experience in restaurants.

1. If the service is poor or the food is rancid, then tip is cheap.

2. If the service is good, then tip is average.

3. If the service is excellent or the food is delicious, then tip is generous.

We'll assume that an average tip is 15%, a generous tip is 25%, and a cheap tip is

5%. It's also useful to have a vague idea of what the tipping function should look like. A

simple tipping function is shown as in Fig.2. Obviously the numbers and the shape of the

curve are subject to local traditions, cultural bias, and so on, but the three rules are pretty

universal. Now we know the rules, and we have an idea of what the output should look

like. Let's begin working with the GUI tools to construct a fuzzy inference system for this

decision process.

Fig 3.2 the tipping Function



The following discussion walks you through building a new fuzzy inference

system from scratch. If you want to save time and follow along quickly, you can load the

already built system by typing fuzzy tipper This will load the FIS associated with the file

tipper.fis (the .fis is implied) and launch the FIS Editor. However, if you load the pre-

built system, you will not be building rules and constructing membership functions.

The FIS Editor displays general information about a fuzzy inference system.

There's a simple diagram as shown in Fig.3 that shows the names of each input variable

on the left, and those of each output variable on the right. The sample membership

functions shown in the boxes are just icons and do not depict the actual shapes of the

membership functions.

Below the diagram is the name of the system and the type of inference used. The

default, Madman-type inference, is what we'll continue to use for this example. Another

slightly different type of inference, called Surgeon-type inference, is also available.

Below the name of the fuzzy inference system, on the left side of the figure, are

the pop-up menus that allow you to modify the various pieces of the inference process.

On the right side at the bottom of the figure is the area that displays the name of an input

or output variable, its associated membership function type, and its range. The latter two

fields are specified only after the membership functions have been. Below that region are

the Help and Close buttons that call up online help and close the window, respectively. At

the bottom is a status line that relays information about the system.

To start this system from scratch, type fuzzy at the mat lab prompt. The

generic untitled FIS Editor opens, with one input, labeled input1, and one output, labeled

output1. For this example, we will construct a two-input, one output system, so go to the

Edit menu and select Add input. A second yellow box labeled input2 will appear. The two

inputs we will have in our example are service and food. Our one output is tip.



Fig 3.3 FIS Editor

We'd like to change the variable names to reflect that, though:

Click once on the left-hand (yellow) box marked input1 (the box will be

highlighted in red).

In the white edit field on the right, change input1 to service and press Return.

Click once on the left-hand (yellow) box marked input2 (the box will be

highlighted in red).

In the white edit field on the right, change input2 to food and press Return.

Click once on the right-hand (blue) box marked output1.

In the white edit field on the right, change output1 to tip.

From the File menu select Save to workspace as.. and a window appears as

shown in fig.4.

Enter the variable name tipper and click on ok.



You will see the diagram updated to reflect the new names of the input and output

variables. There is now a new variable in the workspace called tipper that contains all the

information about this system.

Fig. 3.4 ‘Save to workspace as...’ Window

By saving to the workspace with a new name, you also rename the entire system. Your

window will look like as shown in Fig.5.

Fig 3.5 the updated FIS Editor

Leave the inference options in the lower left in their default positions for now. You've

entered all the information you need for this particular GUI. Next define the membership



functions associated with each of the variables. To do this, open the Membership

Function Editor. You can open the Membership Function Editor in one of three ways:

Pull down the View menu item and select Edit Membership Functions....

Double-click on the icon for the output variable, tip.

Type mfedit at the command line.

The membership function editor:

The Membership Function Editor shares some features with the FIS Editor. In fact, all

of the five basic GUI tools have similar menu options, status lines, and Help and Close

buttons. The Membership Function Editor is the tool that lets you display and edit all of

the membership functions associated with all of the input and output variables for the

entire fuzzy inference system. Fig.6 shows the Membership Function Editor.

When you open the Membership Function Editor to work on a fuzzy inference system

that does not already exist in the workspace, there is not yet any membership functions

associated with the variables that you have just defined with the FIS Editor



Fig. 3.6 The Membership Function Editor

On the upper left side of the graph area in the Membership Function Editor is a "Variable

Palette" that lets you set the membership functions for a given variable. To set up your

membership functions associated with an input or an output variable for the FIS, select an

FIS variable in this region by clicking on it.

Next select the Edit pull-down menu, and choose Add MFs.... A new window will appear,

which allows you to select both the membership function type and the number of

membership functions associated with the selected variable. In the lower right corner of

the window are the controls that let you change the name, type, and parameters (shape),

of the membership function, once it has been selected.

The membership functions from the current variable are displayed in the main graph.

These membership functions can be manipulated in two ways. You can first use the

mouse to select a particular membership function associated with a given variable quality,

(such as poor, for the variable, service), and then drag the membership function from side

to side. This will affect the mathematical description of the quality associated with that

membership function for a given variable. The selected membership function can also be



tagged for dilation or contraction by clicking on the small square drag points on the

membership function, and then dragging the function with the mouse toward the outside,

for dilation, or toward the inside, for contraction. This will change the parameters

associated with that membership function.

Below the Variable Palette is some information about the type and name of the current

variable. There is a text field in this region that lets you change the limits of the current

variable's range (universe of discourse) and another that lets you set the limits of the

current plot (which has no real effect on the system).

The process of specifying the input membership functions for this two input tipper

problem is as follows:

Select the input variable, service, by double-clicking on it. Set both the Range

and the Display Range to the vector [0 10].

Select Add MFs... from the Edit menu. A window pops open as shown in Fig.7.

Fig 6.7. Add MFs… Window

Use the pull-down tab to choose gaussmf for MF Type and 3 for Number of

MFs. This adds three Gaussian curves to the input variable service.

Click once on the curve with the leftmost hump. Change the name of the curve

to poor. To adjust the shape of the membership function, either use the mouse, as



described above, or type in a desired parameter change, and then click on the

membership function. The default parameter listing for this curve is [1.5 0].

Name the curve with the middle hump, good, and the curve with the rightmost

hump, excellent. Reset the associated parameters if desired.

Select the input variable, food, by clicking on it. Set both the Range and the

Display Range to the vector [0 10].

Select Add MFs... from the Edit menu and add two trapmf curves to the input

variable food.

Click once directly on the curve with the leftmost trapezoid. Change the name of

the curve to rancid. To adjust the shape of the membership function, either use

the mouse, as described above, or type in a desired parameter change, and then

click on the membership function. The default parameter listing for this curve is

[0 0 1 3].

Name the curve with the rightmost trapezoid, delicious, and reset the associated

parameters if desired.

Next you need to create the membership functions for the output variable, tip. To create

the output variable membership functions, use the Variable Palette on the left, selecting

the output variable, tip. The inputs ranged from 0 to 10, but the output scale is going to be

a tip between 5 and 25 percent.

Use triangular membership function types for the output. First, set the Range (and the

Display Range) to [0 30], to cover the output range. Initially, the cheap membership

function will have the parameters [0 5 10], the average membership function will be [10

15 20],and the generous membership function will be [20 25 30].Your system should look

something like shown in Fig.8.



fig. 3.8 The updated Membership Function Editor

Now that the variables have been named, and the membership functions have appropriate

shapes and names, you're ready to write down the rules. To call up the Rule Editor, go to

the View menu and select Edit rules..., or type rule edit at the command line. The Rule

Editor Window pops open as shown in Fig 6.9

3.4 The rule editor:

Constructing rules using the graphical Rule Editor interface is fairly self-evident.

Based on the descriptions of the input and output variables defined with the FIS Editor,

the Rule Editor allows you to construct the rule statements automatically, by clicking on

and selecting one item in each input variable box, one item in each output box, and one

connection item. Choosing none as one of the variable qualities will exclude that variable



from a given rule. Choosing not under any variable name will negate the associated

quality. Rules may be changed, deleted, or added, by clicking on the appropriate button.

The Rule Editor also has some familiar landmarks, similar to those in the FIS

Editor and the Membership Function Editor, including the menu bar and the status line.

The Format pop-up menu is available from the Options pull-down menu from the top

menu bar -- this is used to set the format for the display. Similarly, Language can be set

from under Options as well. The Help button will bring up a MATLAB Help window.

Fig 3.9. The Rule Editor

To insert the first rule in the Rule Editor, select the following:

Poor under the variable service

Rancid under the variable food

The radio button, or, in the Connection block

Cheap, under the output variable, tip.



The resulting rule is

1. If (service is poor) or (food is rancid) then (tip is cheap) (1)

The numbers in the parentheses represent weights that can be applied to each rule if

desired. You can specify the weights by typing in a desired number between zero and one

under the Weight setting. If you do not specify them, the weights are assumed to be unity

(1).

Follow a similar procedure to insert the second and third rules in the Rule Editor to get

1. If (service is poor) or (food is rancid) then (tip is cheap) (1)

2. If (service is good) then (tip is average) (1)

3. If (service is excellent) or (food is delicious) then (tip is generous) (1)

To change a rule, first click on the rule to be changed. Next make the desired changes to

that rule, and then click on Change rule. For example, to change the first rule to

1. If (service not poor) or (food not rancid) then (tip is not cheap) (1)

click not under each variable, and then click Change rule.

The Format pop-up menu from the Options menu indicates that you're looking

at the verbose form of the rules. Try changing it to symbolic. You will see

1. (service==poor) => (tip=cheap) (1)

2. (service==good) => (tip=average) (1)

3. (service==excellent) => (tip=generous) (1)

There is not much difference in the display really, but it's slightly more language

neutral, since it doesn't depend on terms like "if" and "then." If you change the format to

indexed, you'll see an extremely compressed version of the rules that has squeezed all the

language out.



1, 1 (1): 1

2, 2 (1): 1

3, 3 (1): 1

This is the version that the machine deals with. The first column in this structure

corresponds to the input variable, the second column corresponds to the output variable,

the third column displays the weight applied to each rule, and the fourth column is

shorthand that indicates whether this is an OR (2) rule or an AND (1) rule. The numbers

in the first two columns refer to the index number of the membership function. A literal

interpretation of rule 1 is: "if input 1 is MF1 (the first membership function associated

with input 1) then output 1 should be MF1 (the first membership function associated with

output 1) with the weight 1." Since there is only one input for this system, the AND

connective implied by the 1 in the last column is of no consequence.

The symbolic format doesn't bother with the terms, if, then, and so on. The

indexed format doesn't even bother with the names of your variables. Obviously the

functionality of your system doesn't depend on how well you have named your variables

and membership functions. The whole point of naming variables descriptively is, as

always, making the system easier for you to interpret. Thus, unless you have some special

purpose in mind, it will probably be easier for you to stick with the verbose format.

At this point, the fuzzy inference system has been completely defined, in that the

variables, membership functions, and the rules necessary to calculate tips are in place. It

would be nice, at this point, to look at a fuzzy inference diagram like the one presented at

the end of the previous section and verify that everything is behaving the way we think it

should. This is exactly the purpose of the Rule Viewer, the next of the GUI tools we'll

look at. From the View menu, select View rules....



3.5 The rule viewer:

Fig 3.10. The Rule Viewer

The Rule Viewer displays a roadmap of the whole fuzzy inference process. It's

based on the fuzzy inference diagram described in the previous section. You see a single

figure window as shown in fig.10 with 10 small plots nested in it. The three small plots

across the top of the figure represent the antecedent and consequent of the first rule. Each

rule is a row of plots, and each column is a variable. The first two columns of plots (the

six yellow plots) show the membership functions referenced by the antecedent, or the if-

part of each rule. The third column of plots (the three blue plots) shows the membership

functions referenced by the consequent, or the then-part of each rule. If you click once on

a rule number, the corresponding rule will be displayed at the bottom of the figure. Notice

that under food, there is a plot which is blank. This corresponds to the characterization of



none for the variable food in the second rule. The fourth plot in the third column of plots

represents the aggregate weighted decision for the given inference system. This decision

will depend on the input values for the system.

There are also the now familiar items like the status line and the menu bar. In the

lower right there is a text field into which you can enter specific input values. For the

two-input system, you will enter an input vector, [9 8], for example, and then click on

input. You can also adjust these input values by clicking anywhere on any of the three

plots for each input. This will move the red index line horizontally, to the point where you

have clicked. You can also just click and drag this line in order to change the input

values. When you release the line, (or after manually specifying the input), a new

calculation is performed, and you can see the whole fuzzy inference process take place.

Where the index line representing service crosses the membership function line "service

is poor" in the upper left plot will determine the degree to which rule one is activated. A

yellow patch of color under the actual membership function curve is used to make the

fuzzy membership value visually apparent. Each of the characterizations of each of the

variables is specified with respect to the input index line in this manner. If we follow rule

1 across the top of the diagram, we can see the consequent "tip is cheap" has been

truncated to exactly the same degree as the (composite) antecedent--this is the implication

process in action. The aggregation occurs down the third column, and the resultant

aggregate plot is shown in the single plot to be found in the lower right corner of the plot

field. The de-fuzzy fied output value is shown by the thick line passing through the

aggregate fuzzy set.

The Rule Viewer allows you to interpret the entire fuzzy inference process at

once. The Rule Viewer also shows how the shape of certain membership functions

influences the overall result. Since it plots every part of every rule, it can become

unwieldy for particularly large systems, but, for a relatively small number of inputs and

outputs, it performs well (depending on how much screen space you devote to it) with up

to 30 rules and as many as 6 or 7 variables.

The Rule Viewer shows one calculation at a time and in great detail. In this sense,

it presents a sort of micro view of the fuzzy inference system. If you want to see the entire



output surface of your system, that is, the entire span of the output set based on the entire

span of the input set, you need to open up the Surface Viewer. This is the last of our five

basic GUI tools in the Fuzzy Logic Toolbox, and you open it by selecting View surface...

from the View menu. The Surface Viewer window pops open as shown in fig.10

The surface viewer:

Upon opening the Surface Viewer, we are presented with a two-dimensional curve

that represents the mapping from service quality to tip amount. Since this is a one-input

one-output case, we can see the entire mapping in one plot. Two-input one-output

systems also work well, as they generate three-dimensional plots that mat lab can adeptly

manage. When we move beyond three dimensions overall, we start to encounter trouble

displaying the results. Accordingly, the Surface Viewer is equipped with pop-up menus

that let you select any two inputs and any one output for plotting. Just below the pop-up

menus are two text input fields that let you determine how many x-axis and y-axis grid

lines you want to include. This allows you to keep the calculation time reasonable for

complex problems. Pushing the Evaluate button initiates the calculation, and the plot

comes up soon after the calculation is complete. To change the x-axis or y-axis grid after

the surface is in view, simply change the appropriate text field, and click on either X-

grids or Y-grids, according to which text field you changed, to redraw the plot.

The Surface Viewer has a special capability that is very helpful in cases with two

(or more) inputs and one output: you can actually grab the axes and reposition them to get

a different three-dimensional view on the data. The Ref. Input field is used in situations

when there are more inputs required by the system than the surface is mapping. Suppose

you have a four-input one-output system and would like to see the output surface. The

Surface Viewer can generate a three-dimensional output surface where any two of the

inputs vary, but two of the inputs must be held constant since computer monitors cannot

display a five-dimensional shape. In such a case the input would be a four-dimensional

vector with Na Ns holding the place of the varying inputs while numerical values would

indicate those values that remain fixed. An Na N is the IEEE symbol for "not a number."



Fig 3.11 The Surface Viewer

This concludes the quick walk-through of each of the main GUI tools. Notice that for the

tipping problem, the output of the fuzzy system matches our original idea of the shape of

the fuzzy mapping from service to tip fairly well. In hindsight, you might say, "Why

bother? I could have just drawn a quick lookup table and been done an hour ago!"

However, if you are interested in solving an entire class of similar decision-making

problems, fuzzy logic may provide an appropriate tool for the solution, given its ease with

which a system can be quickly modified.

Importing and exporting from the Gui tools:

When you save a fuzzy system to disk, you're saving an ascii text FIS file

representation of that system with the file suffix .fis. This text file can be edited and

modified and is simple to understand. When you save your fuzzy system to the mat lab

workspace, you're creating a variable (whose name you choose) that will act as a mat lab

structure for the FIS system. FIS files and FIS structures represent the same system.



CHAPTER 4

4.1 PI controller

The general block diagram of the PI speed controller is shown in Figure 2 [14].

The output

Of the speed controller (torque command) at n-th instant is expressed as follows:

Te (n)=Te(n−1)+Kp_ωre(n)+Kiωre(n) (10)

Where Te (n) is the torque output of the controller at the n-th instant, and Kp and Ki the

proportional and integral gain constants, respectively.

A limit of the torque command is imposed as

The gains of PI controller shown in (10) can be selected by many methods such as trial

and error method, Ziegler–Nichols method and evolutionary techniques-based searching.

The numerical values of these controller gains depend on the ratings of the motor.

4.2 Advantages and disadvantages

The integral term in a PI controller causes the steady-state error to reduce to zero,

which is not the case for proportional-only control in general.

The lack of derivative action may make the system more steady in the steady state

in the case of noisy data. This is because derivative action is more sensitive to

higher-frequency terms in the inputs.



Without derivative action, a PI-controlled system is less responsive to real (non-

noise) and relatively fast alterations in state and so the system will be slower to

reach setpoint and slower to respond to perturbations than a well-tuned PID

system may be.

4.3 Integral Action and PI Control

Like the P-Only controller, the Proportional-Integral (PI) algorithm computes and transmits a

controller output (CO) signal every sample time, T, to the final control element (e.g., valve, variable

speed pump). The computed CO from the PI algorithm is influenced by the controller tuning parameters

and the controller error, e(t).

PI controllers have two tuning parameters to adjust. While this makes them more challenging to

tune than a P-Only controller, they are not as complex as the three parameter PID controller.

Integral action enables PI controllers to eliminate offset, a major weakness of a P-only

controller. Thus, PI controllers provide a balance of complexity and capability that makes them by far

the most widely used algorithm in process control applications.

The PI Algorithm While different vendors cast what is essentially the same algorithm in

different forms, here we explore what is variously described as the dependent, ideal, continuous, position

form:

Where:

CO = controller output signal (the wire out)

CObias = controller bias or null value; set by bump less transfer as explained below

e(t) = current controller error, defined as SP – PV

SP = set point

PV = measured process variable (the wire in)

Kc = controller gain, a tuning parameter

Ti = reset time, a tuning parameter



The first two terms to the right of the equal sign are identical to the P-Only controller

referenced at the top of this article.

The integral mode of the controller is the last term of the equation. Its function is to

integrate or continually sum the controller error, e(t), over time.

Some things we should know about the reset time tuning parameter, Ti:

▪

It provides a separate weight to the integral term so the influence of integral action can

be independently adjusted.

▪

It is in the denominator so smaller values provide a larger weight to (i.e. increase the

influence of) the integral term.

▪It has units of time so it is always positive.

4.4 Function of the Proportional Term

As with the P-Only controller, the proportional term of the PI controller, Kc·e(t),

adds or subtracts from CObias based on the size of controller error e(t) at each time t.

As e(t) grows or shrinks, the amount added to CObias grows or shrinks immediately and

proportionately. The past history and current trajectory of the controller error have no

influence on the proportional term computation.

The plot below (click for a large view) illustrates this idea for a set point response. The

error used in the proportional calculation is shown on the plot:

▪ At time t = 25 min, e(25) = 60–56 = 4

▪ At time t = 40 min, e(40) = 60–62 = –2



Recalling that controller error e(t) = SP – PV, rather than viewing PV and SP as separate

traces as we do above, we can compute and plot e(t) at each point in time t.

Below (click for a large view) is the identical data to that above only it is recast as a plot

of e(t) itself. Notice that in the plot above, PV = SP = 50 for the first 10 min, while in the

error plot below, e(t) = 0 for the same time period.

This plot is useful as it helps us visualize how controller error continually changes size

and sign as time passes.


http://www.controlguru.com/postpics/pierror2big.jpg

http://www.controlguru.com/postpics/pierrorbig.jpg

http://www.controlguru.com/postpics/pierror2big.jpg


4.5 Function of the Integral Term

While the proportional term considers the current size of e(t) only at the time of the

controller calculation, the integral term considers the history of the error, or how long and

how far the measured process variable has been from the set point over time.

Integration is a continual summing. Integration of error over time means that we sum up

the complete controller error history up to the present time, starting from when the

controller was first switched to automatic.

Controller error is e(t) = SP – PV. In the plot below (click for a large view), the integral

sum of error is computed as the shaded areas between the SP and PV traces.

Each box in the plot has an integral sum of 20 (2 high by 10 wide). If we count the

number of boxes (including fractions of boxes) contained in the shaded areas, we can

compute the integral sum of error.

So when the PV first crosses the set point at around t = 32, the integral sum has grown to

about 135. We write the integral term of the PI controller as:


http://www.controlguru.com/postpics/piintbig.jpg

http://www.controlguru.com/postpics/piintbig.jpg


Since it is controller error that drives the calculation, we get a direct view the situation

from a controller error plot as shown below (click for a large view):

Note that the integral of each shaded portion has the same sign as the error. Since the

integral sum starts accumulating when the controller is first put in automatic, the total

integral sum grows as long as e(t) is positive and shrinks when it is negative.

At time t = 60 min on the plots, the integral sum is 135 – 34 = 101. The response is

largely settled out at t = 90 min, and the integral sum is then 135 – 34 + 7 = 108.

4.6 Integral Action Eliminates Offset

The previous sentence makes a subtle yet very important observation. The response is

largely complete at time t = 90 min, yet the integral sum of all error is not zero.

In this example, the integral sum has a final or residual value of 108. It is this residual

value that enables integral action of the PI controller to eliminate offset.

As discussed in a previous article, most processes under P-only control experience offset

during normal operation. Offset is a sustained value for controller error (i.e., PV does not

equal SP at steady state).

We recognize from the P-Only controller:


http://www.controlguru.com/wp/p64.html

http://www.controlguru.com/postpics/piint2big.jpg

http://www.controlguru.com/postpics/piint2big.jpg


that CO will always equal CObias unless we add or subtract something from it.

The only way we have something to add or subtract from CObias in the P-Only equation

above is if e(t) is not zero. It e(t) is not steady at zero, then PV does not equal SP and we

have offset.

However, with the PI controller:

we now know that the integral sum of error can have a final or residual value after a

response is complete. This is important because it means that e(t) can be zero, yet we can

still have something to add or subtract from CObias to form the final controller output, CO.

So as long as there is any error (as long as e(t) is not zero), the integral term will grow or

shrink in size to impact CO. The changes in CO will only cease when PV equals SP

(when e(t) = 0) for a sustained period of time.

At that point, the integral term can have a residual value as just discussed. This residual

value from integration, when added to CObias, essentially creates a new overall bias value

that corresponds to the new level of operation.

In effect, integral action continually resets the bias value to eliminate offset as operating

level changes. PI-controllers have been applied to control almost any process one could

think of, from aerospace to motion control, from slow to fast systems. With changes in

system dynamics and variation in operating points PI-controllers should be retuned on a

regular basis. Adaptive PI-controllers avoid time-consuming manual tuning by providing

optimal PI-controllers settings automatically as the system dynamics or operating points

change[2]. There are various conventional methods used for tuning of PI-controller such

as :



1. Trial and error

2. Continuous cycling method (Ziegler Nichols method)

3. Process Reaction Curve Methods (Ziegler-Nichols and Cohen-Coon methods)

4. Ziegler-Nichols method (both types of responses)

5. Cohen-Coon method (self regulating response only

Trial and error [3]

PI-Controller equation is:

It is quite time consuming if a large number of trial are required or if the process

dynamics are slow. Testing can be expensive because of lost productivity or poor product

quality

Continuous cycling may be objectionable because the process is pushed to the stability

limit. Consequently, if external disturbances or a change in the process occurs during

controller tuning an unstable operation or a hazardous situation could result. The tuning

process is not applicable to processes that are open loop because such processes typically

are unstable at high and low values of Kc but are stable at intermediate range values.

This information is an analogy of knowledge of how the other agents around them have

performed. Namely, each agent tries to modify its position as shown in Fig. (1).



CHAPTER 5

MODELING OF PROPOSED THEORY

5.1 SYSTEM MODEL DESCRIPTION

The schematic block diagram of the isolated wind-micro hydro-diesel hybrid power

system is shown in Fig-1. In the hybrid system considered, synchronous generator is connected

on diesel-generator (DG) and induction generators connected on wind turbine and hydro

turbine[10]. Moreover, the Blade pitch controller is installed in the wind side while the governor

is equipped with the diesel side. In the wind-turbine generating unit, the ANFIS based Neuro-

Fuzzy controller is designed as a supplement controller for the pitch control, which constantly

maintains the wind power generation . For the diesel generating unit, the ANFIS based Neuro-

Fuzzy controller is designed to improve the performance of governor. The proposed Neuro-

Fuzzy controller uses the system frequency deviation of the power system as a feedback input on

diesel side, so that it can offset the mismatch between generation and load demand by adjusting

the speed changer position.

Nomenclature:

ΔFs - deviations in system frequency

ΔFT - speed of the wind-turbine induction generator.

ΔPGD – deviation in diesel power generation

ΔPGW - deviation in wind power generation

ΔPGH - deviation in hydro power generation

ΔP

IW - deviation in input power

ΔPIH - deviation in micro hydro power



Figure-1: Configuration of isolated wind - micro hydro diesel hybrid system

Table 1: System parameters

The transfer function block diagram of a wind- micro hydrodiesel hybrid power system with

Neuro-Fuzzy controller used in this study is shown in Fig-2. The input power to the windpower



generating unit is not controllable in the sense of generation control, but a supplementary

controller known as LFC can control the generation of the diesel unit and thereby of the system.

The transfer function block diagram of this hybrid system includes the LFC and also the blade-

pitch controller with ANFIS based Neuro-Fuzzy controller. The dynamics of the wind power

generating unit is described by a first order system. The continuous time dynamic behavior of the

load frequency control system is modeled by a set of state vector differential equations.

(1)

Where X, U and p are the state, control and disturbance vectors, respectively. A, B and Γ are real

constant matrices, of the appropriate dimensions, associated with the above vectors.

Figure-2: Simulink model of wind -micro hydro- diesel hybrid system with ANFIS based Neuro-

Fuzzy controller



5.2 CONVENTIONAL PI CONTROLLER

Among the various types of load-frequency control, the PI controller is most widely applied to

speed-governor systems for LFC schemes [1 7]. One advantage of the PI controller is that it

reduces the steady-state error to zero. Fig-3 shows the block diagram of conventional PI

controller.

Figure-3: Block diagram of conventional PI controller

Mathematically it is represented as

(2)

However, since the conventional PI controller with fixed gains has been designed at nominal

operating conditions, it fails to provide the best control performance over a wide range of

operating conditions and exhibits poor dynamic performance. To solve this problem, Fuzzy

Logic techniques have been proposed in [6],[11]-[1 4]. System operating conditions are

monitored and used as inputs to a fuzzy system whose output signal controls the inputs to

governor for increasing or decreasing the generation for maintaining the system frequency.



CHAPTER 6

6.1. FUZZY LOGIC CONTROLLER

Recently, the fuzzy logic based control has extensively received attentions in various

power systems applications [18]. FLCs are knowledge-based controllers usually derived

from a knowledge acquisition process or automatically synthesized from self-organizing control

architectures. A fuzzy system knowledge base consists of fuzzy IF-THEN

rules and membership functions characterizing the fuzzy sets. The Fuzzy Logic Controller

considered here for comparison is based on Mamdani inference model. The LFC problem

considered here is composed of the sudden small load perturbations or a change in input wind

power which continuously disturb the normal operation of a power system. Hence, the deviations

of frequency must be controlled.

6.2 Fuzzification

Fuzzification is the process of transforming real-valued variable into a fuzzy set variable.

Fuzzy variables depend on nature of the system where it is implemented.

6.2 Knowledge Base

The heart of the fuzzy system is a knowledge base consisting of fuzzy IF-THEN rules.

The rule base consists of a set of fuzzy rules. The data base contains the membership function of

fuzzy subsets. A fuzzy rule may contain fuzzy variables and fuzzy subsets characterized by

membership function.

6.3 De-Fuzzification

The purpose of De-fuzzification is to convert the output fuzzy variable to a crisp value,

So that it can be used for control purpose. It is employed because crisp control action is

required in practical applications. Fig-4 shows the block diagram of Fuzzy logic controller

designed for comparison.



Figure-4: Block diagram of Fuzzy logic controller

The heuristic rules of the knowledge base are used to determine the fuzzy controller action. The

membership functions, knowledge base and method of de-fuzzification essentially determine the

controller performance. The input variable (ΔFs) in diesel side for governor is used as error

signal for fuzzy logic controller. The membership functions with 7 linguistic variables

(NL,NM,NS,Z,PS,PM,PL) for two input and one output variable and rule base are shown in Fig-

5 and Table-2 for the designed fuzzy logic controller for comparison with the proposed controller

Table-2

Rule base (with 7 membership functions)



Figure-5 Membership functions of input and output variable



CHAPTER 7

7.1 ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM (ANFIS)

ANFIS is a multi-layer adaptive neural network-based fuzzy inference system[19].

ANFIS algorithm is composed of fuzzy logic and neural networks with 5 layers to implement

different node functions to learn and tune parameters in a fuzzy inference system (FIS) structure

using a hybrid learning mode. In the forward pass of learning, with fixed premise

parameters, the least squared error estimate approach is employed to update the consequent

parameters and to pass the errors to the backward pass. In the backward pass of learning, the

consequent parameters are fixed and the gradient descent method is applied to update the

premise parameters. Premise and consequent parameters will be identified for membership

function (MF) and FIS by repeating the forward and backward passes. Adaptive Neuro-Fuzzy

Inference Systems are fuzzy Sugeno models put in the framework of adaptive systems to

facilitate learning and adaptation [19]. Such framework makes FLC more systematic and less

relying on expert knowledge. To present the ANFIS architecture, let us consider two-fuzzy

rules based on a first order Sugeno model:

Rule 1: if (x is A1) and (y is B1) then (f1 = p1x + q1y + r1)

Rule 2: if (x is A2) and (y is B2) then (f2 = p2x + q2y + r2)

where x and y are the inputs, Ai and Bi are the fuzzy sets, fi are the outputs within the fuzzy

region specified by the fuzzy rule, pi, qi and ri are the design parameters that are

determined during the training process. Out of the five layers, the first and the fourth layers

consist of adaptive nodes while the second, third and fifth layers consist of fixed nodes. The

adaptive nodes are associated with their respective parameters, get duly updated with each

subsequent iteration while the fixed nodes are devoid of any parameters. The ANFIS architecture

to implement these two rules is shown in Fig. 6.



Layer 1: fuzzification layer Every node I in the layer 1 is an adaptive node. The outputs of layer

1 are the fuzzy membership grade of the inputs, which are given

where x and y is the inputs to node i, where A is a linguistic label (small, large) and where μAi

(x), μBi-2 (y) can adopt any fuzzy membership function.

Layer 2: rule layer a fixed node labeled M whose output is the product of all the incoming

signals, The outputs of this layer can be represented as:

(5)



Figure-6. ANFIS architecture

Layer 3: normalization layer are also fixed node is a circle node labeled N

(6)

Layer 4: defuzzification layer an adaptive node with a node .The output of each node in this

layer is simply the product of the normalized firing strength and a first order polynomial.

(7)

Layer5: summation neuron a fixed node which computes the overall output as the summation of

all incoming signals.

(8)



CHAPTER 8

8.1 NEURO-FUZZY CONTROLLER

The development of the control strategy to control the frequency deviation of the wind-

micro hydro-diesel hybrid power system using the concepts of ANFIS control scheme is

presented here.. The neuro-fuzzy method combines the advantages of neural networks and fuzzy

theory to design a model that uses a fuzzy theory to represent knowledge in an interpretable

manner and the learning ability of a neural network to optimize its parameters . The proposed

controller

integrates fuzzy logic algorithm with a structure of artificial neural network (ANN) five-layer in

order to reap the benefits of both methods .ANFIS is a specific approach in neuro-fuzzy

development which was first introduced by Jang [1 9]. To start with, we design the controller

using the ANFIS scheme. The model considered here is based on Takagi-Sugeno Fuzzy

inference model. The block diagram of the proposed ANFIS based Neuro-Fuzzy controller for

wind-micro hydro-diesel hybrid power system consists of 4 parts, viz., fuzzification, knowledge

base, neural network and the de-fuzzification blocks, shown in Fig-7.

Figure-7 Block diagram of ANFIS based Neuro-Fuzzy Controller

ANFIS uses a hybrid learning algorithm to identify consequent parameters of Sugeno type fuzzy

inference systems. It applies a combination of the least squares method and back propagation



gradient descent method for training fuzzy inference system membership function parameters to

emulate a given training data set. The fuzzy inference system under consideration has two inputs.

In the proposed paper, inputs to the ANFIS considered are error(ΔFs) and change in error(ΔFs)‟

whereas the output is the corresponding signal to the governor. Steps to design the Neuro-Fuzzy

Controller are as given below:

1. Draw the Simulink model with FLC (Takagi-Sugeno inference model) and simulate it with 7

membership functions for the two inputs(error(ΔFs) and change in error(ΔFs)‟) and with the

given rule base.

2. Collect the training data while simulating with FLC to design the Neuro-Fuzzy controller.

3. The two inputs, i.e., error(ΔFs) and change in error(ΔFs)‟ and the output signal gives the

training data.

4. Use „anfisedit‟ to create the Neuro-Fuzzy FIS file.

5. Load the training data collected in Step.1 and load the Neuro-Fuzzy FIS file.

6.Choose the hybrid learning algorithm.

7. Train the collected data with generated FIS up to a particular no. of Epochs.

Fig-8 shows the ANFIS structure for the designed Neuro Fuzzy controller.



Figure 8. ANFIS model structure for LFC of wind-micro hydro-diesel hybrid power system

CHAPTER 9

9.1 SIMULATION AND ANALYSIS

Simulations were performed using the proposed ANFIS based Neuro-Fuzzy controller ,

Fuzzy Logic controller (FLC Mamdani model) and the conventional PI controller to the wind-

micro hydro-diesel hybrid power system. All the performance criteria‟s such as settling time,

overshoot and zero steady state are considered to get minimized for all the cases such as change

in frequency, change in wind power, change in diesel power and change in hydro power during

various load disturbances to get the optimum performance of the wind- micro hydro-diesel

hybrid power system. The same system parameters given in Tables 1 were used for the above

three controllers for comparison. Simulation is carried out for 1 % ,2%, 3%,4% and 5%

step increase in the power load ( ∆PL=0.01 p.u. ,0.02 p.u.,0.03 p.u.,0.04 p.u. and 0.05 p.u.) at t =

0s . The overshoot and setting time of proposed ANFIS based Neuro-Fuzzy controller are lower

than those of Fuzzy logic controller and conventional PI controller. The change in frequency of



the system, change in wind power generation, change in diesel power generation and change in

hydro power generation for 0.02 p.u. step load change is shown in Fig-9(a),9(b),9(c) and 9(d)

respectively. And the change in frequency of the system, change in wind power generation,

change in diesel power generation and change in hydro power generation for 0.04 p.u. step load

change is shown in Fig-10(a),10(b),10(c) and 10(d).

9.2 MAT LAB CIRCUIT



9.3 SIMULATION RESULTS

WITH PI CONTROLLER:



Fig-9(a) : Frequency deviation of the hybrid system for the step load change.

Fig-9(b) Change in wind power generation for the step load change.



Fig-9(c) Change in diesel power generation for the step load change.

Fig-9(d) Change in hydro power generation for the step load change .

WITH FUZZY CONTROLLER



Fig-10(e) Change in frequency for the step load change .

Fig-10(f) Change in wind power generation for the step load change.



Fig-10(g) Change in diesel power generation for the step load change.

Fig-10(h) Change in hydro power generation for the step load change.



WITH ANN CONTROLLER

Fig-10(i) Change in frequency for the step load change .

Fig-10(j) Change in wind power generation for the step load change.



Fig-10(k) Change in diesel power generation for the step load change.

Fig-10(l) Change in hydro power generation for the step load change.



CHAPTER 10

10.1CONCLUSION

The Neuro-Fuzzy controller is designed for Load frequency control of an isolated wind-

micro hydro-diesel hybrid power system, to regulate the frequency deviation and power

deviations, based on Adaptive Neuro-Fuzzy Inference System (ANFIS) architecture.

Performance comparison of the proposed paper indicates that the system response of the Load

Frequency Control with the application of ANFIS based Neuro-Fuzzy controller has a quite

shorter settling time. The results obtained by using ANFIS based NeuroFuzzy controller

proposed in this paper outperform than those of conventional PI controller and the fuzzy logic

controller by its hybrid learning algorithm. The main advantage of designing the ANFIS based

Neuro-Fuzzy controller is to control the frequency deviation and power deviation of the wind-

micro hydro-diesel hybrid power system and to increase the dynamic Performance. It has been

shown that the proposed controller is effective and provides significant improvement in system

performance by combing the benefits of Fuzzy logic and neural networks. The proposed

controller maintains the system reliable for sudden load changes and proves its superiority.



CHAPTER 11

11.1 REFERENCES

[1] Ackermann, T., “Wind power in power systems”, John Wiley & Sons Ltd, 2005

[2] Ray Hunter, George Elliot, “Wind-Diesel Systems; A guide to the technology and its

implementation”, Cambridge university Press, 1994.

[3] Lipman, N.H., “Wind-diesel and autonomous energy systems”, Elservier Science Publishers

Ltd, 1989

[4] O.I. Elgerd and C. Fosha, “Optimum megawatt frequency control of multi-area electric

energy systems”, IEEE Trans Power Appl Syst 89 (4) (1970), pp. 556–563.

[5]T.S Bhatti, A.A.F. Al–Ademi and N.K. Bansal, “Load Frequency Control of Isolated Wind

Diesel Hybrid Power System,” Energy Conver.Mgnt Vol. 38. No. 9. pp. 829-837,1997

[6] Soundarrajan. A et al, “Intelligent controllers for Automatic Generation Control”,

Proceedings of The International conference on Robotics, Vision, Information and signal

processing, Malaysia, 2003, 307-311.

[7] P. Kundur, “Power System Stability & Control”. Tata McGraw Hill, New Delhi, Fifth reprint

2008,pp 581 -626

[8] Saadat, Hadi; ―”Power System Analysis” McGraw Hill,1999

[9] C.E. Fosha and O.I. Elgerd, “The megawatt frequency control problem: a new approach via

optimal control theory”, IEEE Trans Power Appl Syst 89 (4) (1970), pp. 563–577.

[10] R.C. Bansal, T.S. Bhatti, D. P. Kothari, “A bibliographical survey on induction generators

for application of non-conventional energy systems”, IEEE Transactions on Energy Conversion.

18, (2003) 433-439.

[11] B. Anand and A. Ebenezer Jeyakumar “Load Frequency Control with Fuzzy Logic

Controller Considering Non Linearities and Boiler Dynamics” ICGST-ACSE Journal, ISSN

1687-4811, Volume 8, Issue III, January 2009

[1 2] Ertug˘rul Cam, “Application of fuzzy logic for load frequency control of hydroelectrical

power plants”, Energy Conversion and Management 48 (2007) 1281 – 1288

[1 3]Ertugrul Cam ,Ilhan Kocaarslan, “Load frequency control in two area power systems using

fuzzy logic controller”, Energy Conversion and Management 46 (2005) 233–243



[1 4]A. Soundarrajan, S. Sumathi, “Effect of Non-linearities in Fuzzy Based Load Frequency

Control”, International Journal of Electronic Engineering Research Volume 1 Number 1 (2009)

pp. 37–51.

[15]C. Chokpanyasuwan, S. Pothiya, S. Anantasate, W. Pattaraprakorn, and P.

Bhasaputra ,”Robust Fuzzy logic PID Controller for Wind-Diesel Power System using Particle

Swarm Optimization”,GMSARN International Conference on Sustainable Development, Nov.

2008

[16]R. Dhanalakshmi, S. Palaniswami, “Load Frequency Control of Wind Diesel Hydro Hybrid

Power System Using Conventional PI Controller”, European Journal of Scientific

Research ,ISSN 1450-216X Vol.60 No.4 (2011), pp. 630-641

[17] Bhatti T S, Al–Ademi A A F et al,”Load Frequency control of isolated wind-diesel-micro

hydro hybrid power systems. Elsevier-Energy, . (1997) , 22(5): 461 - 470.

[18] Ross T J , “Fuzzy logic with Engineering Applications”, second edition, John wiley&sons

Ltd. (2004)

[1 9] J.R. Jang, “ANFIS: Adaptive-network-Based Fuzzy Inference System”,IEEE Trans. On

Systems, Man and Cybernetics, Vol. 23, No.3, May.1993, pp.665-685.

[20]Gayadhar Panda, Sidhartha Panda and C. Ardil, “Hybrid Neuro Fuzzy Approach for

Automatic Generation Control of Two–Area Interconnected Power System”,

International Journal of Computational Intelligence, Vol. 5, No. 1, pp. 80-84, 2009.

[21] C.Srinivasa Rao , “Adaptive Neuro-Fuzzy Based Inference System for Load Frequency

Control ofHydrothermal System under Deregulated Environment”I nternational Journal of

Engineering Science and TechnologyVol. 2(12), 2010, 6954-6962
