Visvesvaraya Technological University

Belagavi, Karnataka-590 018

A Seminar Report on

“ARTIFICIAL INTELLIGENCE IN POWER

SYSTEM”
A seminar report submitted in partial fulfillment of the requirement
for the VIII semester degree of
Bachelor of Engineering
In
Electrical & Electronics Engineering

Submitted by
Name: S PAVITHRA
USN: 1CR16EE062

Under the Guidance of

Ms. PARVATHY THAMPI M.S
Assistant Professor, Department of Electrical & Electronics Engineering
CMR Institute of Technology

CMR Institute of Technology, Bengaluru-560 037

Department of Electrical & Electronics Engineering

2019-2020

i
 CMR INSTITUTE OF TECHNOLOGY
DEPARTMENT OF ELECTRICAL & ELECTRONICS ENGINEERING
AECS Layout, Bengaluru-560 037

Certificate
Certified that the Seminar work entitled “ARTIFICIAL INTELLIGENCE IN POWER
SYSTEM” has been successfully presented by Ms. S PAVITHRA(1CR16EE062) at CMR
Institute of Technology, Bengaluru, in partial fulfillment of the requirements for the VIII
Semester degree of Bachelor of Engineering in Electrical & Electronics Engineering of
Visvesvaraya Technological University, Belagavi during the academic year 2019-2020. It is
certified that all corrections/suggestions indicated for Internal Assessment have been
incorporated in the report deposited in the departmental library.
The Seminar report has been approved as it satisfies the academic requirements in
respect of Seminar work as prescribed for the said Degree.

Signature of the Guide Signature of the HOD Signature of the

Principal

----------------------------- --------------------------------
Ms. Paravathy Thampi M.S, Dr. K. Chitra -----------------------------
Assistant Professor Professor & HOD Dr. Sanjay Jain
EEE Department EEE Department Principal,
CMRIT, Bengaluru CMRIT, Bengaluru

ii
 CMR INSTITUTE OF TECHNOLOY
DEPARTMENT OF ELECTRICAL & ELECTRONICS ENGINEERING
AECS Layout, Bengaluru-560 037

DECLARATIO
N

I, Ms. S PAVITHRA (1CR16EE062), hereby declare that the Seminar report entitled
“ARTIFICIAL INTELLIGENCE IN POWER SYSTEM” has been carried out by
me under the guidance of Ms. PARVATHY THAMPI M.S, Assistant Professor,
Department of Electrical & Electronics Engineering, CMR Institute of Technology,
Bengaluru, in partial fulfillment of the requirements for the VIII Semester degree of
Bachelor of Engineering in Electrical & Electronics Engineering of Visvesvaraya
Technological University, Belagavi during the academic year 2019-2020.

Place: Bengaluru Ms. S PAVITHRA

Date:
1CR16EE062
05.05.2020

iii
 Acknowledgement

The satisfaction and euphoria that accompany the successful completion of any
task would be incomplete without the mention of people, who are responsible for the
completion of the Seminar work and who made it possible, because success is the
outcome of hard work and perseverance, but steadfast of all is encouraging guidance. So
with gratitude, I acknowledge all those whose guidance and encouragement served me to
motivate towards the success of the Seminar work.

I take great pleasure in expressing my sincere thanks to Dr. Sanjay Jain,

Principal, CMR Institute of Technology, Bengaluru for providing an excellent
academic environment in the college and for his continuous motivation towards a
dynamic career. I would like to profoundly thank Dr. B Narasimha Murthy, Vice-
principal of CMR Institute of Technology and the whole Management for providing such
a healthy environment for the successful completion of the Seminar work.

I would like to convey my sincere gratitude to Dr. K Chitra, Head of Electrical

and Electronics Engineering Department, CMR Institute of Technology, Bengaluru for
her invaluable guidance and encouragement and for providing good facilities to carry
out this Seminar work.

I would like to express my deep sense of gratitude to Ms. Parvathy Thampi M.S,
Assistant Professor, Electrical and Electronics Engineering, CMR Institute of
Technology, Bengaluru for his/her exemplary guidance, valuable suggestions, expert
advice and encouragement to pursue this Seminar work.

I am thankful to all the faculties and laboratory staffs of Electrical and

Electronics Engineering Department, CMR Institute of Technology, Bengaluru for
helping me in all possible manners during the entire period.

Finally, I acknowledge the people who mean a lot to me, my parents, for their
inspiration, unconditional love, support, and faith for carrying out this work to the
finishing line. I want to give special thanks to all my friends who went through hard times
together, cheered me on, helped me a lot, and celebrated each accomplishment.

Lastly, to the Almighty, for showering His Blessings and to many more, whom I didn’t
mention here.

iv
 ABSTRACT

A continuous and reliable supply of electricity is necessary for the

functioning of today’s modern and advanced society. Since the early
to mid-1980s, most of the effort in power systems analysis has turned
away from the methodology of formal mathematical modeling which
came from the areas of operations research, control theory and
numerical analysis to the less rigorous and less tedious techniques of
artificial intelligence (AI). Power systems keep on increasing on the
basis of geographical regions, assets additions, and introduction of
new technologies in generation, transmission and distribution of
electricity.
ARTIFICIAL INTELLIGENCE techniques have become popular for
solving different problems in power systems. Artificial intelligence is
the science of automating intelligent behaviors currently achievable
by humans. These techniques can deal with difficult tasks faced by
applications in modern large power systems with even more
interconnections installed to meet increasing load demand. The
application of these techniques has been successful in many areas of
power system engineering.

v
 CONTENTS

Title Page i
Certificate ii
Declaration iii
Acknowledgement iv
Abstract v
Contents vi-vii
List of Figures viii
List of Tables ix
List of Abbreviations and Symbols x

Chapter 1: INTRODUCTION 1– 8
1.1 Power System 1-1
1.2 Structure of Power System 2-4
1.3 Artificial Intelligence (AI) 4-7
1.4 Need of Artificial Intelligence in Power System 8-8

Chapter 2: LITERATURE REVIEW

9-16
2.1 History of Power System 9-10
2.2 History of Artificial Intelligence 11-15
2.3 Artificial Intelligence and Electric Power Systems 15-16

Chapter 3: ARTIFICIAL INTELLIGENCE TECHNIQUES USED 17-28

IN POWER SYSTEM

3.1 Expert System 17-21

3.2 Artificial Neural Network 21-24
3.3 Fuzzy Logic 24-28
3.4 Comparison between different AI techniques in power system 28

Chapter 4: APPLICATION OF AI TECHNIQUE IN POWER

SYSTEM 29-31
4.1 Application of AI technique in power system 29

vi
4.2 Application of AI in Transmission Lines
30-31

32
Chapter 5: CONCLUSIONS
References 33-34

vii

vii
 LIST OF FIGURES

Figure 1: Structure of Power System 1

Figure 2: A sample unsupervised and supervised learning methods: 7

(a) clustering; (b) regression;(c) classification
Figure 3: A sketch of Pearl Steel Station 10
Figure 4: The Adam Beck station 10
Figure 5: Structure of an Expert System 18
Figure 6: Architecture of a feedforward ANN 22
Figure 7: Typical structure of an ANN 23
Figure 8: Fuzzy Logic System 25
Figure 9: Benefits of using Fuzzy Logic 26
Figure 10: Fuzzification 26
Figure 11: Defuzzification 27
Figure 12: Fuzzy Logic Control 28
Figure 13: Block diagram of application of AI in power system 30
Figure 14: Using Artificial Intelligence and Machine Learning to manage
the electricity grids of the future 31

viii
 LIST OF TABLES

Table 1: Comparison methods of machine learning 7

Table 2: comparison between different AI techniques 28

ix

LIST OF ABBREVIATIONS AND SYMBOLS

 AI - ARTIFICIAL IN TELLIGENCE

 XPSs – EXPERT SYSTEM

 ANNs- ARTIFICIAL NEURAL NETWORK

 FL- FUZZY LOGIC

 INTRODUCTION Chapter 1

CHAPTER 1

INTRODUCTION

1.1 POWER SYSTEM

An electrical Power system is a network of electrical components deployed to

supply, transfer, and use electric power. It uses the form of energy (like
coal and diesel) and converts it into electrical energy. An example of an
electric power system is the grid that provides power to an extended area.
An electrical grid power system can be broadly divided into
the GENERATORS that supply the power, the TRANSMISSION
SYSTEM that carries the power from the generating centers to the load
centers, and the DISTRIBUTION SYSTEM that feeds the power to nearby
homes and industries.

The power plant, transformer, transmission line, substations, distribution line, and distribution
transformer are the six main components of the power system. The power plant generates the power
which is step-up or step-down through the transformer for transmission. The transmission
line transfers the power to the various substations. Through substation, the power is transferred to
the distribution transformer which step-down the power to the appropriate value which is suitable
for the consumers.

Fig 1: Structure of Power System

1|Page
INTRODUCTION Chapter 1

1.2 STRUCTURE OF POWER SYSTEM

The power system is the complex system that may be subdivided into the
following sub-systems.

 Generation Station

 Transmission line

 Sub-Transmission line

 Distribution system

 GENERATION STATION

In generating station, the fuel (coal, water, nuclear energy, etc.) is converted into electrical energy.
The electrical power is generated in the range of 11kV to 25kV, which is step-up for long distance
transmission. The power plant of the generating substation is mainly classified into three types, i.e.,
thermal power plant, hydropower plant and nuclear power plant.

The generator and the transformer are the main components of the generating station. The generator
converts the mechanical energy into electrical energy. The mechanical energy comes from the
burning of coal, gas and nuclear fuel, gas turbines, or occasionally the internal combustion engine.

The transformer transfers the power with very high efficiency from one level to another. The power
transfer from the secondary is approximately equal to the primary except for losses in the
transformer. The step-up transformer will reduce losses in the line which makes the transmission of
power over long distances.

 TRANNSMISSION LINES

The transmission lines carry the overhead lines which transfer the generated electrical energy from
generation to the distribution substations. It only supplies the large bulk of power to bulk power
substations or very big consumers.

2|Page
 INTRODUCTION Chapter 1

The transmission lines mainly perform the two functions

1. It transports the energy from generating stations to bulk receiving stations.

2. It interconnects the two or more generating stations. The neighbouring substations are also
interconnected through the transmission lines.

The transmission voltage is operating at more than 66kv and is standardised at 69kv, 115KV,
138KV, 161KV, 230KV, 345KV, 500KV, and 765KV, line-to-line. The transmission line above
230KV is usually referred to as extra high voltage (EHV).

The high voltage line is terminated in substations which are called high voltage substations,
receiving substations or primary substations. In high voltage substation, the voltage is step-down to
a suitable value for the next part of flow toward the load. The very large industrial consumers may
be served directly to the transmission system.

 SUB – TRANSMISSION LINES

The portion of the transmission system that connects the high voltage substations through the step-
down transformer to the distribution substations is called the sub-transmission system.

The sub-transmission voltage level ranges from 90 to 138KV. The sub-transmission system directly
serves some large industries. The capacitor and reactor are located in the substations for
maintaining the transmission line voltage.

The operation of the sub-transmission system is similar to that of a distribution system. Its differ
from a distribution system in the following manner.

1. A sub-transmission system has a higher voltage level than a distribution system.

2. It supplies only bigger loads.
3. It supplies only a few substations as compared to a distribution system which supplies some
loads.

3|Page
 INTRODUCTION Chapter 1

 DISTRUBUTION SYSTEM

The component of an electrical power system connecting all the consumers in an area to the bulk
power sources is called a distribution system. The bulk power stations are connected to the
generating substations by transmission lines. They feed some substations which are usually situated
at convenient points near the load centres. The substations distribute the power to the domestic,
commercial and relatively small consumers. The consumers require large blocks of power which are
usually supplied at sub-transmission or even transmission system.

1.3 ARTIFICIAL INTELLIGENCE (AI)

Artificial intelligence is known to be the intelligence exhibited by machines and software, for
example, robots and computer programs. The term is generally used to the project of developing
systems equipped with the intellectual processes features and characteristics of humans, like the
ability to think, reason, find the meaning, generalize, distinguish, learn from past experience or
rectify their mistakes.

Artificial general intelligence (AGI) is the intelligence of a hypothetical machine or computer

which can accomplish any intellectual assignment successfully which a human being can
accomplish.

AI is a field of computer science and engineering used for different smart applications aiming to make
intelligent machines. AI works and responds like humans, intelligently and independently through
learning from experience and adjusting to new participations.

Artificial Intelligence (AI) is a machine intelligence tool providing enormous possibilities for smart
industrial revolution. It facilitates gathering relevant data/information, identifying the alternatives,
choosing among alternatives, taking some actions, making a decision, reviewing the decision, and

4|Page
 INTRODUCTION Chapter 1

predicting smartly.

AI has a number of benefits including:

(1) using data to automate learning

(2) enhancing the intelligence abilities to current products

(3) adapting intelligent learning algorithms to do the programming by the data

(4) Analyzing rationally of data, and

(5) improving data accuracy.

AI is based on combining large amounts of data. It processes the data very fast with iterative processing
through the intelligent algorithms, which allow the software to learn from features or patterns of the
data. AI can be divided into three main fields: symbolic learning, statistical learning, and machine
learning

1. SYMBOLIC LEARNING:
Symbolic learning is based on human readable symbols of logic, problems, search and the symbolic
learning rules, which are created through human intervention. Mixtures of symbols with their
interrelations is called reasoning. In order to construct a symbolic reasoning, humans start to learn
the rules of the phenomena relationships, and then the code of those relationships transfer into a
program. Symbolic learning can be divided into cognitive computing and computer vision.

2. STATISTICAL LEARNING:

Statistical learning is mathematics intensive and deals with the problem of finding a predictive
function based on data. It involves forming a hypothesis before proceeding to building a model.
Statistical learning relies on rule based programming and is formalized in the form of relationship
between variables. Statistical learning is also based on a smaller dataset with some attributes,
operates on assumptions, such as normality, no multi-collinearity, and homoscedasticity.

5|Page
INTRODUCTION Chapter 1

3. MACHINE LEARNING:

Machine Learning (ML) creates and automates analytical/ numerical models and algorithms that
can be used to improve the system performance in a specific task. ML uses approaches from
heuristic methods, operations research, and statistics, and finds hidden insights in data without
explicitly being planned where to look or what to accomplish. The major ML subfields are
unsupervised, supervised, and reinforcement learning, which are explained as follows:

a. Unsupervised Learning: Unsupervised learning is a group of understanding Data created

based only on input data. One of the unsupervised learning techniques is clustering that
involves the grouping of data points through a set of data points. The clustering algorithm
can classify each set of data points into cluster group (see Fig. 2 (a)).

b. Supervised Learning: Supervised Learning (SL) develops a model to predict based on

input and output data. SL approaches can be divided into:

(1) Regression that is an approach to find the relationship between variables. In

machine learning, this is used to predict the outcome of an event based on the
relationship between variables obtained from the dataset (see Fig. 2 (b)).

(2) Classification that is trying to identify to which of a set of categories for a new
observation belongs accurately and it also attempts to predict the target class for
each category of the data (see Fig. 2 (c)).

c. Reinforcement Learning: Reinforcement Learning (RL) is a new AI technology based

on decision-making that will help AI to advance extremely into the area of machine
learning of the real world.

6|Page
INTRODUCTION Chapter 1

Fig: 2: A sample unsupervised and supervised learning methods: (a)

clustering; (b) regression;(c) classification

Table 1: Comparison methods of machine learning

7|Page
 INTRODUCTION Chapter 1

1.4 NEED FOR ARTIFICIAL INTELLIGENCE IN POWER SYSTEM

Power system analysis by conventional techniques becomes more difficult because of:

(i) Complex, versatile and large amount of information which is used in calculation, diagnosis
and learning.

(ii) Increase in the computational time period and accuracy due to extensive and vast system
data handling.

For developing industries with the help of the power system: The stability, strengthening,
reliability, technological advances, selectivity and dynamic response of the electrical
system are essential. In this situations AI techniques are very much useful to solve
different problems occurring in industries.

The modern power system operates close to the limits due to the ever increasing energy
consumption and the extension of currently existing electrical transmission networks
and lines.

This situation requires a less conservative power system operation and control operation
which is possible only by continuously checking the system states in a much more
detail manner than it was necessary.

Sophisticated computer tools are now the primary tools in solving the difficult problems
that arise in the areas of power system planning, operation, diagnosis and design.
Among these computer tools, Artificial Intelligence has grown predominantly in recent
years and has been applied to various areas of power systems.

8|Page
LITERATURE REVIEW Chapter 2

CHAPTER 2

LITERATURE REVIEW

2.1 HISTORY OF POWER SYSTEM

In 1881, two electricians built the world's first power system at Godalming in England. It was
powered by two waterwheels and produced an alternating current that in turn supplied seven
Siemens arc lamps at 250 volts and 34 incandescent lamps at 40 volts. Supply to the lamps was
intermittent and in 1882 Thomas Edison and his company, The Edison Electric Light Company,
developed the first steam-powered electric power station on Pearl Street in New York City.
The Pearl Street Station initially powered around 3,000 lamps for 59 customers. The power station
generated direct current and operated at a single voltage. Direct current power could not be
transformed easily to long-distance transmission, so the maximum economic distance between the
generators and load was limited to around half a mile (800 m).

That same year in London, Lucien Gaulard and John Dixon Gibbs demonstrated the "secondary

generator", namely the first transformer suitable for use in a real power system. The practical
value of the transformer was demonstrated in 1884 at Turin where the transformer was used to light
up forty kilometers (25 miles) of railway from a single alternating current generator.

In 1885, the secondary generator of Gaulard and Gibbs, providing it with a closed iron core, and
thus obtained the first true power transformer. In 1885 George Westinghouse, an American
entrepreneur, obtained the Gaulard-Gibbs transformer and imported a number of them along with
a Siemens generator, and set his engineers to experimenting with them in hopes of improving them
for use in a commercial power system. In 1886, one of Westinghouse's engineers, William Stanley,
also recognized the problem with connecting transformers in series as opposed to parallel and also
realized that making the iron core of a transformer a fully enclosed loop would improve the voltage
regulation of the secondary winding. Using this knowledge, he built the first practical transformer-
based alternating-current power system at Great Barrington, Massachusetts in 1886.

By 1888, the electric power industry was flourishing, and power companies had built thousands of
power systems (both direct and alternating current) in the United States and Europe. These

9|Page
LITERATURE REVIEW Chapter 2

networks were effectively dedicated to providing electric lighting. 666

In 1891, Westinghouse installed the first major power system that was designed to drive a 100
horsepower (75 kW) synchronous electric motor, not just provide electric lighting, at Telluride,
Colorado.

On the other side the very first long-distance (175 km, a distance never tried before) high-voltage
(15 kV, then a record) three-phase transmission line from Lauffen am Neckar to Frankfurt am
Main for the Electrical Engineering Exhibition in Frankfurt, where power was used light lamps and
move a water pump. In 1895, after a protracted decision-making process, alternating current was
chosen as the transmission standard with Westinghouse building the Adams No. 1 generating
station at Niagara Falls and General Electric building the three-phase alternating current power
system to supply Buffalo at 11 kV.

Developments in power systems continued beyond the nineteenth century. In 1936 the first
experimental high voltage direct current (HVDC) line using mercury arc valves was built
between Schenectady and Mechanicville, New York.

In 1979, a European consortium including Siemens, Brown Boveri & Cie and AEG realized the
record HVDC link from Cabora Bassa (Mozambique) to Johannesburg (South Africa), extending
more than 1,420 km and rated 1.9 GW at ±533 kV, that resorted to top performing 3.2-kV
thyristors.

In recent times, many important developments have come from extending innovations in
the information and communications technology (ICT) field to the power engineering field. For
example, the development of computers meant load flow studies could be run more efficiently
allowing for much better planning of power systems. Advances in information technology and
telecommunication also allowed for remote control of a power system's switchgear and generators.

10 | P a g e
LITERATURE REVIEW Chapter 2

Fig 3: A sketch of Pearl Steel Station Fig 4: The Adam Beck station

2.2 HISTORY OF ARTIFICIAL INTELLIGENCE

Artificial Intelligence beings first appeared in the ancient Greek myths of Antiquity. The seeds of
modern AI were planted by classical philosophers who attempted to describe the process of human
thinking as the mechanical manipulation of symbols. This work culminated in the invention of
the programmable digital computer in the 1940s, a machine based on the abstract essence of
mathematical reasoning. The field of AI research was founded at a workshop held on the campus
of Dartmouth College during the summer of 1956.

The following is some of the most important events in AI. 

1943
 Warren McCullough and Walter Pitts publish "A Logical Calculus of Ideas Immanent
in Nervous Activity." The paper proposed the first mathematic model for building a
neural network. 

1949
 In his book The Organization of Behavior: A Neuropsychological Theory, Donald
Hebb proposes the theory that neural pathways are created from experiences and that
connections between neurons become stronger the more frequently they're used.
Hebbian learning continues to be an important model in AI.

1950

11 | P a g e
LITERATURE REVIEW Chapter 2

 Alan Turing publishes "Computing Machinery and Intelligence, proposing what is now
known as the Turing Test, a method for determining if a machine is intelligent. 
 Harvard undergraduates Marvin Minsky and Dean Edmonds build SNARC, the first
neural network computer.
 Claude Shannon publishes the paper "Programming a Computer for Playing Chess."
 Isaac Asimov publishes the "Three Laws of Robotics."  

1952
 Arthur Samuel develops a self-learning program to play checkers. 

1954
 The Georgetown-IBM machine translation experiment automatically translates 60
carefully selected Russian sentences into English. 

1956
 The phrase artificial intelligence is coined at the "Dartmouth Summer Research Project
on Artificial Intelligence." Led by John McCarthy, the conference, which defined the
scope and goals of AI, is widely considered to be the birth of artificial intelligence as
we know it today. 
 Allen Newell and Herbert Simon demonstrate Logic Theorist (LT), the first reasoning
program. 

1958
 John McCarthy develops the AI programming language Lisp and publishes the paper
"Programs with Common Sense." The paper proposed the hypothetical Advice Taker, a
complete AI system with the ability to learn from experience as effectively as humans
do.  

1959
 Allen Newell, Herbert Simon and J.C. Shaw develop the General Problem Solver
(GPS), a program designed to imitate human problem-solving. 
 Herbert Gelernter develops the Geometry Theorem Prover program.
 Arthur Samuel coins the term machine learning while at IBM.

12 | P a g e
LITERATURE REVIEW Chapter 2

 John McCarthy and Marvin Minsky found the MIT Artificial Intelligence Project.

1963
 John McCarthy starts the AI Lab at Stanford.

1966
 The Automatic Language Processing Advisory Committee (ALPAC) report by the U.S.
government details the lack of progress in machine translations research, a major Cold
War initiative with the promise of automatic and instantaneous translation of Russian.
The ALPAC report leads to the cancellation of all government-funded MT projects. 

1969
 The first successful expert systems are developed in DENDRAL, a XX program, and
MYCIN, designed to diagnose blood infections, are created at Stanford.

1972
 The logic programming language PROLOG is created.

1973
 The "Lighthill Report," detailing the disappointments in AI research, is released by the
British government and leads to severe cuts in funding for artificial intelligence
projects. 

1974-1980
 Frustration with the progress of AI development leads to major DARPA cutbacks in
academic grants. Combined with the earlier ALPAC report and the previous year's
"Lighthill Report," artificial intelligence funding dries up and research stalls. This
period is known as the "First AI Winter." 

1980
 Digital Equipment Corporations develops R1 (also known as XCON), the first
successful commercial expert system. Designed to configure orders for new computer

13 | P a g e
LITERATURE REVIEW Chapter 2

systems, R1 kicks off an investment boom in expert systems that will last for much of
the decade, effectively ending the first "AI Winter."

1982
 Japan's Ministry of International Trade and Industry launches the ambitious Fifth
Generation Computer Systems project. The goal of FGCS is to develop supercomputer-
like performance and a platform for AI development.

1983
 In response to Japan's FGCS, the U.S. government launches the Strategic Computing
Initiative to provide DARPA funded research in advanced computing and artificial
intelligence. 

1985
 Companies are spending more than a billion dollars a year on expert systems and an
entire industry known as the Lisp machine market springs up to support them.
Companies like Symbolic and Lisp Machines Inc. build specialized computers to run
on the AI programming language Lisp. 

1987-1993
 As computing technology improved, cheaper alternatives emerged and the Lisp
machine market collapsed in 1987, ushering in the "Second AI Winter." During this
period, expert systems proved too expensive to maintain and update, eventually falling
out of favor.
 Japan terminates the FGCS project in 1992, citing failure in meeting the ambitious goals
outlined a decade earlier.
 DARPA ends the Strategic Computing Initiative in 1993 after spending nearly $1 billion
and falling far short of expectations. 

1991
 U.S. forces deploy DART, an automated logistics planning and scheduling tool, during
the Gulf War.

14 | P a g e
LITERATURE REVIEW Chapter 2

1997
 IBM's Deep Blue beats world chess champion Gary Kasparov

2005
 STANLEY, a self-driving car, wins the DARPA Grand Challenge.
 The U.S. military begins investing in autonomous robots like Boston Dynamic's "Big
Dog" and iRobot's "PackBot."

2008
 Google makes breakthroughs in speech recognition and introduces the feature in its
iPhone app. 

2011
 IBM's Watson trounces the competition on Jeopardy!  

2012
 Andrew Ng, founder of the Google Brain Deep Learning project, feeds a neural
network using deep learning algorithms 10 million YouTube videos as a training set.
The neural network learned to recognize a cat without being told what a cat is, ushering
in breakthrough era for neural networks and deep learning funding.

2014
 Google makes first self-driving car to pass a state driving test. 

2016
 Google DeepMind's Alpha Go defeats world champion Go player Lee Sedol. The
complexity of the ancient Chinese game was seen as a major hurdle to clear in AI.

15 | P a g e
LITERATURE REVIEW Chapter 2

2.3 ARTIFICIAL INTELLIGENCE AND ELECTRIC POWER SYSTEMS

Artificial intelligence techniques have become necessary to procedures of monitoring, management

and control of electric power systems. The current expansion of electric power systems is physically
verified by the increase of branches and by the way distribution lines are installed: generators and
loads are interconnected with the distribution lines through multiple paths (radial form) and in ring
among them. This technique increases the confidence index on the system because the failure of one
line does not cause a total failure of the system and can provide the transmission of electric power
from other of its branches. Every new technique offers certain advantages, however when a new
technique is implemented, there is an increase of the complexity of the electric power system.
Because of that there is the need of an efficient protection in which the sector responsible for the
energy transmission and distribution as well as the generating sector are controlled in a quick and
efficient way in order to keep the power generated according to the charges required. That said so,
energy generation must be kept according to the conditions established by the load and comply with
the conditions in which the protection systems are capable of prevent failures of the generation

equipment due to possible overloads.

Recently, new techniques from artificial intelligence (AI) made possible to connect multiple
generating sources of electric power as well as loads to the transmission system. However, although
all these new factors make access easier, they may cause problems by destabilizing the system,
which requires a sophisticated AI based control to assure capable and efficient control of the
generation according to the demand. These actions which modify the operational state of the
electric power systems at any time must be controlled in order to provide power transference in a
safe and coordinated way.

16 | P a g e
LITERATURE REVIEW Chapter 2

17 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

CHAPTER 3

ARTIFICIAL INTELLIGENCE TECHNIQUES USED IN

POWER SYSTEM

Three major AI techniques are considered to be applied in modern power system:

1) Expert System Techniques (XPSs)

2) Artificial Neural Networks (ANNs)
3) Fuzzy Logic System (FL)

3.1 EXPERT SYSTEM (XPSs)

An Expert System obtains the knowledge of a human expert in a narrow specified domain into a
machine implementable form. Expert systems are computer programs which have proficiency and
competence in a particular field. This knowledge is generally stored separately from the program’s
procedural part and may be stored in one of the many forms, like rules, decision trees, models, and
frames. They are also called as knowledge based systems or rule based systems.
An expert system is divided into two subsystems: the inference engine and the knowledge base.
The knowledge base represents facts and rules. The inference engine applies the rules to the known
facts to deduce new facts. Inference engines can also include explanation and debugging abilities.
Expert systems use the interface mechanism and knowledge to solve problems which cannot be or
difficult to be solved by human skill and intellect.
An important note about Expert system is that an expert system is not used to replace the human
experts;instead, it is used to assist the human in making a complex decision. These system do not
have human capcbilities of thinking and work on the bases o the knowledge base of the particular
domain.

17 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

► Components of Expert System:

An expert system mainly consists of three components:

o User Interface
o Inference Engine
o Knowledge Base

Fig 5: Structure of an Expert System

18 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

1) USER INTERFACE:

With the help of a user interface, the expert system interacts with the user, takes queries as an
input in a readable format, and passes it to the inference engine. After getting the response from the
inference engine, it displays the output to the user. In other words, it is an interface that helps a non-
expert user to communicate with the expert system to find a solution.

2) INFERENCE ENGINE (RULES OF ENGINE)

 The inference engine is known as the brain of the expert system as it is the main
processing unit of the system. It applies inference rules to the knowledge base to
derive a conclusion or deduce new information. It helps in deriving an error-free
solution of queries asked by the user.

 With the help of an inference engine, the system extracts the knowledge from the
knowledge base.

 There are two types of inference engine:

i) Deterministic Inference engine: The conclusions drawn from this type of

inference engine are assumed to be true. It is based on facts and rules.
ii) Probabilistic Inference engine: This type of inference engine contains
uncertainty in conclusions, and based on the probability.

 Inference engine uses the below two modes to derive the solutions:

(i) Forward Chaining: It starts from the known facts and rules, and applies the
inference rules to add their conclusion to the known facts.
(ii) Backward Chaining: It is a backward reasoning method that starts from the
goal and works backward to prove the known facts.

19 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

3) KNOWLEDGE BASE

 The knowledge base is a type of storage that stores knowledge acquired from the
different experts of the particular domain. It is considered as big storage of knowledge.
The more the knowledge base, the more precise will be the Expert System.

 It is similar to a database that contains information and rules of a particular domain or

subject.

 Components of Knowledge Base:

o Factual Knowledge: The knowledge which is based on facts and accepted

by knowledge engineers comes under factual knowledge.
o Heuristic Knowledge: This knowledge is based on practice, the ability to
guess, evaluation, and experiences.

Knowledge Representation: It is used to formalize the knowledge stored in the knowledge base
using the If-else rules.

Knowledge Acquisitions: It is the process of extracting, organizing, and structuring the domain
knowledge, specifying the rules to acquire the knowledge from various experts, and store that
knowledge into the knowledge base.

► Advantages of Expert System

o These systems are highly reproducible.

o They can be used for risky places where the human presence is not safe.

o Error possibilities are less if the Knowledge B contains correct knowledge.

o The performance of these systems remains steady as it is not affected by emotions,

tension, or fatigue.

20 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

o They provide a very high speed to respond to a particular query.

► Limitations of Expert System

o The response of the expert system may get wrong if the knowledge base contains the
wrong information.
o Like a human being, it cannot produce a creative output for different scenarios.

o Its maintenance and development costs are very high.

o Knowledge acquisition for designing is much difficult.

o For each domain, we require a specific Expert System, which is one of the big
limitations.
o It cannot learn from itself and hence requires manual updates.

3.2 ARTIFICIAL NEURAL NETWORKs (ANNs)

Artificial Neural Networks are biologically inspired systems which convert a set of inputs into a set
of outputs by a network of neurons, where each neuron produces one output as a function of inputs.
A fundamental neuron can be considered as a processor which makes a simple non-linear operation
of its inputs producing a single output. The understanding of the working of neurons and the pattern
of their interconnection can be used to construct computers for solving real world problems of
classification of patterns and pattern recognition.
They are classified by their architecture: number of layers and topology: connectivity pattern,
feedforward or recurrent.

21 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

Artificial Neural networks consist of input, output layers hidden layers. Transformation of input
into valuable output unit is the main job.  Information flows in neural network happens in two
ways.

 Feedforward Networks – In these signals only travel in one direction without any loop i.e.
towards the output layer. Extensively used in pattern recognition. This network with a single

input layer and a single output layer can have zero or multiple hidden layers though. This
method has two common designs as below

o At the time of its learning or “being trained”

o At the time of operating normally or “after being trained”.

 Feedback Networks – In this recurrent or interactive networks can use their internal state
(memory) to process sequences of inputs.  Signals can travel in both directions with loops in
the network. As of now limited to time series/sequential tasks. Typical human brain model.

22 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

Fig 6: Architecture of a feedforward ANN

Fig 7: Typical structure of an ANN

► Components of Artificial Neural Network:

 Input Layers, Neurons, and Weights –  The basic unit in a neural network is called as
the neuron or node. These units receive input from the external source or some other nodes.
The idea here is to compute an output based associated weight. Weights to the neuron are

23 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

assigned based on its relative importance compared with other inputs. Now finally function
is applied to this for computations.

 Hidden Layers and Output Layers – The hidden layer is always isolated from the external
world hence it’s called as hidden. The main job of the hidden layer to take inputs from the
input layer and perform its job i.e. calculation and transform the result to output nodes.
Bunch of hidden nodes can be called a hidden layer.

► Artificial Neural Network Working Flow – Layers of Learning:

Neural networks learning process is not very different from humans, humans learn from experience
in lives while neural networks require data to gain experience and learn. Accuracy increases with
the amount of data over time. Similarly, humans also perform the same task better and better by
doing any task you do over and over.

The underlying foundation of neural networks is a layer and layers of connections. The entire neural
network model is based on a layered architecture. Each layer has its own responsibility. These
networks are designed to make use of layers of “neurons” to process raw data, find patterns into it
and objects which are usually hidden to naked eyes. To train a neural network, data scientist put
their data in three different baskets.

 Training data set – This helps networks to understand and know the various weights
between nodes.
 Validation data set – To fine-tune the data sets.
 Test data set – To evaluate the accuracy and records margin of error.
 Layer takes input, extract feature and feed into the next layer i.e. each layer work as an input
layer to another layer. This is to receive information and last layer job is to throw output of
the required information. Hidden layers or core layers process all the information in
between.

24 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

3.3 FUZZY LOGIC (FL)

Fuzzy logic is a form of many-valued logic in which the truth values of variables may be any real
number between 0 and 1 both inclusive. It is employed to handle the concept of partial truth, where
the truth value may range between completely true and completely false. By contrast, in Boolean
logic, the truth values of variables may only be the integer values 0 or 1.

Fuzzy logic is based on the observation that people make decisions based on imprecise and non-
numerical information. Fuzzy models or sets are mathematical means of representing vagueness and
imprecise information (hence the term fuzzy). These models have the capability of recognizing,
representing, manipulating, interpreting, and utilizing data and information that are vague and lack
certainty.

Fig 8: Fuzzy Logic System

25 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

► FUZZIFICATION:

Fuzzification provides superior expressive power, higher generality and an improved

capability to model complex problems at low or moderate solution cost. Fuzzy logic allows a
particular level of ambiguity throughout an analysis. Because this ambiguity can specify available
information and minimize problem complexity, fuzzy logic is useful in many applications. For
power systems, fuzzy logic is suitable for applications in many areas where the available
information involves uncertainty. For example, a problem might involve logical reasoning, but can
be applied to numerical, other than symbolic inputs and outputs. Fuzzy logic provides the
conversions from numerical to symbolic inputs, and back again for the outputs.

Fig 9: Benefits of using fuzzy logic

26 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

Fig 10: Fuzzification

► DEFUZZIFICATION:

Defuzzification is the process of producing a quantifiable result in Crisp logic, given fuzzy sets
and corresponding membership degrees. It is the process that maps a fuzzy set to a crisp set. It is
typically needed in fuzzy control systems. These will have a number of rules that transform a
number of variables into a fuzzy result, that is, the result is described in terms of membership
in fuzzy sets. 

Fig 11: Defuzzification

► FUZZY CONTROL SYSTEM

A fuzzy control system is a control system based on fuzzy logic—a mathematical system that

27 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

analyzes analog input values in terms of logical variables that take on continuous values between 0

and 1, in contrast to classical or digital logic, which operates on discrete values of either 1 or 0 (true
or false, respectively).

The process of designing fuzzy control system can be described using following steps:

 STEP 1: Identify the principal input, output and process tasks.

 STEP 2: Identify linguistic variables used and define fuzzy sets and membership accordingly.
 STEP 3: Use these fuzzy sets and linguistic variables to form procedural rules.
 STEP 4: Determine the defuzzification method.
 STEP 5: Test the system and modify if necessary.

28 | P a g e
ARTIFICIAL INTELLIGENCE TECHNIQUES USED Chapter 3
IN POWER SYSTEMS

Fig 12: Fuzzy Logic Control

3.4 COMPARISON BETWEEN DIFFERENT AI TECHNIQUES IN POWER

SYSTEM

Table 2: comparison between different AI techniques

29 | P a g e
APPLICATION OF AI IN POWER SYSTEM Chapter 4

CHAPTER 4
APPLICATION OF ARTIFICIAL INTELLIGENCE IN
POWER SYSTEM

4.1 APPLICATION OF ARTIFICIAL INTELLIGENCE IN POWER

SYSTEM

1. OPERATION OF POWER SYSTEM like unit commitment, hydro- thermal coordination,

economic dispatch, congestion management, maintenance scheduling, state estimation,
load and power flow.

2. PLANNING OF POWER SYSTEM like generation expansion planning, power system

reliability, transmission expansion planning, reactive power planning.

3. CONTROL OF POWER SYSTEM like voltage control, stability control, power flow
control, load frequency control.

4. CONTROL OF POWER PLANTS like fuel cell power plant control, thermal power plant
control.

5. CONTROL OF NETWORK like location, sizing and control of FACTS devices.

6. AUTOMATION OF POWER SYSTEM like restoration, management, fault diagnosis,

network security.

7. APPLICATIONS OF DISTRIBUTION SYSTEM like planning and operation of

distribution system, demand side response and demand side management, operation and
control of smart grids, network reconfiguration.

8. APPLICATIONS OF DISTRIBUTED GENERATION like distributed generation

planning, solar photovoltaic power plant control, wind turbine plant control and
renewable energy resources.

9. FORECASTING APPLICATION like short term and long term load forecasting,
electricity market forecasting, solar power forecasting, wind power forecasting.

29 | P a g e
CONCLUSION Chapter 5

4.2 PRACTICAL APPLICATION OF ARTIFICIAL INTELLIGENCE

SYSTEMS IN TRANSMISSION LINE

Fig 13: Block diagram of application of AI in Power system

 Consider a practical transmission line. If any fault occurs in the transmission line, the fault
detector detects the fault and feeds it to the fuzzy system.
 Only three line currents are sufficient to implement this technique and the angular difference
between fault and pre-fault current phasors are used as inputs to the fuzzy system.
 The fuzzy system is used to obtain the crisp output of the fault type. Fuzzy systems can be
generally used for fault diagnosis.
 Artificial Neural Networks and Expert systems can be used to improve the performance of the
line.
 The environmental sensors sense the environmental and atmospheric conditions and give them
as input to the expert systems.
 The expert systems are computer programs written by knowledge engineers which provide the
value of line parameters to be deployed as the output.

30 | P a g e
CONCLUSION Chapter 5

 The ANNs are trained to change the values of line parameters over the given ranges based on
the environmental conditions. Training algorithm has to be given to ANN. After training is
over, neural network is tested and the performance of updated trained neural network is
evaluated.
 If performance is not upto the desired level, some variations are done like varying number of
hidden layers, varying number of neurons in each layer.
 The processing speed is directly proportional to the number of neurons.
 These networks take different neurons for different layers and different activation functions
between input and hidden layer and hidden and output layer to obtain the desired output.
 In this way the performance of the transmission line is improved.

Fig 14: Using artificial intelligence and machine learning to manage the
electricity grids of the future

31 | P a g e
CONCLUSION Chapter 5

CHAPTER 5

CONCLUTION

The main feature of power system design and planning is reliability, which was conventionally
evaluated using deterministic methods. Moreover, conventional techniques don’t fulfill the
probabilistic essence of power systems. This leads to increase in operating and maintenance costs.
Plenty of research is performed to utilize the current interest AI for power system applications. A lot
of research is yet to be performed to perceive full advantages of this upcoming technology for
improving the efficiency of electricity market investment, distributed control and monitoring,
efficient system analysis, particularly power systems which use renewable energy resources for
operation.

32 | P a g e
REFERENCES

REFERENCES
(1) Warwick K., Ekwue A. And Aggarwal R. (ed). Artificial intelligence techniques in power
systems. The Institution of Electrical Engineers, London, 1997

(2) International Journal of Engineering Intelligent Systems, The special issue on AI applications to
power system protection, edited by M.M. Saha and B.Kasztenny, Vol.5, No.4, December 1997,
pp.185-93.

(3) Dahhaghchi, I.,Christie, R.D, AI application areas in power systems, IEEE Expert,' Vol. 12,
Issue 1 pages 58-66, Jan/Feb 1997

(4) Anis Ibrahim, W.R.; Morcos, M.M, Artificial intelligence and advanced mathematical tools for
power quality applications: a survey, Power Delivery, IEEE Transactions, Vol. 17, Issue 2,
Pages 668-673, April 2002.

(5) Hammons, T. J. (1994). Artificial intelligence in power system engineering: Actual and

potential applications of expert systems, knowledge-based systems, and artificial neural
networks. IEEE Power Engineering Review, 14(2), 11. doi:10.1109/mper.1994.262141.

(6) Khedher M.Z., Fuzzy Logic in Power Engineering,, Regional Conference of CIGRE committees
in Arab Countries, May 25-27 (1997), Doha, Qatar.

(7) Bachmann B., Novosel D., Hart D., Hu Y., Saha M.M., Application of artificial neural
networks for series compensated line protection, Proc. of the Int. Conf. on Intelligent System
Application to Power Systems, Orlando, January 28 - February 2, 1996,
pp.68-73.

(8) Kirkpatrick S., Gelatt C. D., Vecchi M. P., 1983, "Optimization by simulated annealing".
Science. New Series 220, pp.671–680.
Lai, Loi Lei, 1998, Intelligent system applications in power engineering: evolutionary
programming and neural networks, John Willey & Sons, UK

33 | P a g e
REFERENCES

(9) B. Kosko, Neural Networks and Fuzzy Systems, Prentice Hall, Englewood Cliffs, NJ, U.S.A.,
1992.

(10) El-Hawary, Mohamed E., 1998, Electric power applications of fuzzy systems, John Wiley
USA.

(11) Momoh James A., EL-Hawary Mohamed E., 2000, Electric systems, dynamics, and stability
with artificial intelligence, Marcel Dekker, Inc. USA.

(12) Artificial Intelligence in Power Systems R. Pasupathi Nath, V.Nishanth Balaji IOSR Journal
of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p-ISSN: 2278-8727 PP 00-00.

(13) Bose, B. K. (2017). Artificial Intelligence Techniques in Smart Grid and Renewable Energy
Systems—Some Example Applications. Proceedings of the IEEE, 105(11), 2262–
2273. doi:10.1109/jproc.2017.2756596 

(14) Safty, S. M. E., Ashour, H. A., Dessouki, H. E., & Sawaf, M. E. (n.d.). Online fault
detection of transmission line using artificial neural network. 2004 International Conference on
Power System Technology, 2004. PowerCon 2004. doi:10.1109/icpst.2004.1460264

34 | P a g e
9|Page