Professional Documents
Culture Documents
Final Seminar Report
Final Seminar Report
TECHNICAL SEMINAR
REPORT ON
“ARTIFICIAL INTELLIGENCE IN POWER STATIONS”
BACHELOR OF
ENGINEERING IN
ELECTRONICS AND COMMUNICATION ENGINEERING
SUBMITTED BY
VIDYA M (1AH17EC032)
VIII Semester
CERTIFICATE
I wish to extend our profound thanks to Dr. Bharathi Gururaj, Head of the Department,
Electronics and Communication Engineering, for giving us the consent to carry out this
Technical Seminar work.
I would like to express my sincere thanks to the Technical Seminar coordinators, Mr.
Harish L, Asst. Professor, Department of ECE and the internal guide, Dr. H B Bhuvaneswari,
Professor, Department of ECE, for their able guidance and valuable advice at every stage of our
Seminar, which helped us in successful completion of the Technical Seminar.
VIDYA M
(1AH17EC032)
i
ABSTRACT
ii
TABLE OF CONTENTS
Acknowledgement i
Abstract ii
List of Figures v
1 INTRODUCTION 1
1.1.2 Types of AI 2
1.1.3 Stages of AI 5
1.1.4 Applications of AI 6
2 ARTIFICIAL INTELLIGENCE IN 10
POWER STATIONS
3 METHODOLOGY 12
5 CONCLUSION 22
6 REFERENCES 23
iv
Figure Figure Name Page
No. No.
1.5 Self-Aware AI 4
v
ARTIFICIAL INTELLIGENCE IN POWER STATIONS 2020-21
CHAPTER 1
INTRODUCTION
Artificial intelligence (AI) is an area of computer science that emphasizes the creation
of intelligent machines that work and react like humans. Some of the activities computers with
artificial intelligence are designed for include: Speech recognition, Learning, Planning,
Problem solving.
Artificial intelligence systems are critical for companies that wish to extract
value from data by automating and optimizing processes or producing actionable insights.
Artificial intelligence systems powered by machine learning enable companies to leverage
large amounts of available data to uncover insights and patterns that would be impossible for
any one person to identify, enabling them to deliver more targeted, personalized
communications, predict critical care events, identify likely fraudulent transactions, and more.
Limited Memory AI
Limited memory types refer to an A.I.’s ability to store previous data and/or predictions, using
that data to make better predictions. With Limited Memory, machine learning architecture
becomes a little more complex. Every machine learning model requires limited memory to be
created, but the model can get deployed as a reactive machine type.
Theory of mind AI
We have yet to reach Theory of Mind artificial intelligence types. These are only in their
beginning phases and can be seen in things like self-driving cars. In this type of A.I., A.I. begins
to interact with the thoughts and emotions of humans.
Self-Aware AI
These are systems that can form representations of themselves. These would be machines that
are ‘aware’ of themselves and know their internal states.
1.1.3 Stages of AI
Artificial narrow intelligence (ANI or narrow AI) refers to a computer's ability to perform a
single task extremely well, such as crawling a webpage or playing chess.
1.1.4 Applications of AI
The type of primary fuel or primary energy flow that provides a power plant its
primary energy varies. The most common fuels are coal, natural gas, and uranium (nuclear
power). A substantially used primary energy flow for electricity generation
is hydroelectricity (water). Other flows that are used to generate electricity
include wind, solar, geothermal and tidal.
Different countries get their electricity from different types of power plants. For
example, in Canada, most electricity generation comes from hydroelectric power plants which
accounts for about 60% of the total electricity generated in Canada. Please see the data
visualization below to explore how countries around the world get their electricity.
The nuclear power station is the breeding ground of civil nuclear power across the world.
According to the World Nuclear Association nuclear power forms about 11% of the world’s
electricity, with 450 reactors providing 424GW of power, making it the second largest source
of low-carbon power in the world.
It is the technique of using dam water falling from a height to turn the turbines of a generator.
The mechanical energy is converted into electrical form and fed into the national grid system.
The location of a hydroelectric power station must be analyzed by an expert to determine the
effective head for maximum efficiency.
Geothermal energy refers to heat energy stored under the ground for millions of years through
the earth formation. It utilizes a rich storage of unutilized thermal energy that exists under the
earth’s crust. Geothermal energy is site specific but can be very cheap especially when used for
direct heating. It is a challenge to estimate power from this source since it occurs underground
at extremely high temperatures.
Wind power is the conversion of wind energy into electricity or mechanical energy using wind
turbines. The power in the wind is extracted by allowing it to blow past moving blades that
exert torque on a rotor. The amount of power transferred is dependent on the rotor size and the
wind speed.
CHAPTER 2
The use of AI in the power sector is now reaching emerging markets, where
it may have a critical impact, as clean, cheap, and reliable energy is essential to development.
The challenges can be addressed over time by transferring knowledge of the power sector to AI
software companies. When designed carefully, AI systems can be particularly useful in the
automation of routine and structured tasks, leaving humans to grapple with the power
challenges of tomorrow
Artificial intelligence, or AI, has the potential to cut energy waste, lower
energy costs, and facilitate and accelerate the use of clean renewable energy sources in power
grids worldwide. AI can also improve the planning, operation, and control of power systems.
Thus, AI technologies are closely tied to the ability to provide clean and cheap energy that is
essential to development.
The power sector has a promising future with the advent of solutions such
as AI-managed smart grids. These are electrical grids that allow two-way communication
between utilities and consumers. Smart grids are embedded with an information layer that
allows communication between its various components so they can better respond to quick
changes in energy demand or urgent situations. This information layer, created through
widespread installation of smart meters and sensors, allows for data collection, storage, and
analysis.
Paired with powerful data analytics, these smart-grid elements have helped
improve the reliability, security, and efficiency of electricity transmission and distribution
networks. Given the large volume and diverse structures of such data, AI techniques such as
machine learning are best suited for their analysis and use.6 This data analysis can be used for
a variety of purposes, including fault detection, predictive maintenance, power quality
monitoring, and renewable energy forecasting
CHAPTER 3
METHODOLOGY
Artificial neural networks are built like the human brain, with neuron
nodes interconnected like a web. The human brain has hundreds of billions of cells called
neurons. Each neuron is made up of a cell body that is responsible for processing information
by carrying information towards (inputs) and away (outputs) from the brain.
From translating web pages into other languages to having a virtual assistant order grocery
online to conversing with chat bots to solve problems, AI platforms are simplifying transactions
and making services accessible to all at negligible costs.
The idea of fuzzy logic was first advanced by Lotfi Zadeh of the University
of California at Berkeley in the 1960s. Zadeh was working on the problem of computer
understanding of natural language. Natural language -- like most other activities in life and
indeed the universe -- is not easily translated into the absolute terms of 0 and 1. Whether
everything is ultimately describable in binary terms is a philosophical question worth pursuing,
but in practice, much data we might want to feed a computer is in some state in between and
so, frequently, are the results of computing. It may help to see fuzzy logic as the way reasoning
really works and binary, or Boolean, logic is simply a special case of it.
reasoning and cognition. Rather than strictly binary cases of truth, fuzzy logic includes 0 and 1
as extreme cases of truth but with various intermediate degrees of truth.
Rule Base
It contains all the rules and the if-then conditions offered by the experts to control the decision-
making system. The recent update in fuzzy theory provides various methods for the design and
tuning of fuzzy controllers. This updates significantly reduce the number of the fuzzy set of
rules.
Fuzzification
Fuzzification step helps to convert inputs. It allows you to convert, crisp numbers into fuzzy
sets. Crisp inputs measured by sensors and passed into the control system for further processing.
Like Room temperature, pressure, etc.
Inference Engine
It helps you to determines the degree of match between fuzzy input and the rules. Based on the
% match, it determines which rules need implment according to the given input field. After this,
the applied rules are combined to develop the control actions.
Defuzzification
At last the Defuzzification process is performed to convert the fuzzy sets into a crisp value.
There are many types of techniques available, so you need to select it which is best suited when
it is used with an expert system.
The first expert systems were created in the 1970s and then proliferated in
the 1980s. Expert systems were among the first truly successful forms of artificial
intelligence (AI) software. 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.
Soon after the dawn of modern computers in the late 1940s – early 1950s,
researchers started realizing the immense potential these machines had for modern society. One
of the first challenges was to make such machine capable of “thinking” like humans. In
particular, making these machines capable of making important decisions the way humans do.
The medical / healthcare field presented the tantalizing challenge to enable these machines to
make medical diagnostic decisions
Thus, in the late 1950s, right after the information age had fully arrived, researchers
started experimenting with the prospect of using computer technology to emulate human
decision-making. For example, biomedical researchers started creating computer-aided systems
for diagnostic applications in medicine and biology. These early diagnostic systems used
patients’ symptoms and laboratory test results as inputs to generate a diagnostic outcome. These
systems were often described as the early forms of expert systems. However, researchers had
realized that there were significant limitations when using traditional methods such as flow-
charts statistical pattern-matching, or probability theory.
The knowledge base represents facts about the world. In early expert
systems such as Mycin and Dendral, these facts were represented mainly as flat assertions about
variables. In later expert systems developed with commercial shells, the knowledge base took
on more structure and used concepts from object-oriented programming. The world was
represented as classes, subclasses, and instances and assertions were replaced by values of
object instances. The rules worked by querying and asserting values of the objects.
Initial Population
The process begins with a set of individuals which is called a Population. Each individual is a
solution to the problem you want to solve. An individual is characterized by a set of parameters
(variables) known as Genes. Genes are joined into a string to form a Chromosome (solution). In
a genetic algorithm, the set of genes of an individual is represented using a string, in terms of an
alphabet. Usually, binary values are used (string of 1s and 0s). We say that we encode the genes
in a chromosome.
Fitness Function
The fitness function determines how fit an individual is (the ability of an individual to compete
with other individuals). It gives a fitness score to each individual. The probability that an
individual will be selected for reproduction is based on its fitness score.
Selection
The idea of selection phase is to select the fittest individuals and let them pass their genes to the
next generation. Two pairs of individuals (parents) are selected based on their fitness scores.
Individuals with high fitness have more chance to be selected for reproduction.
Cross over
Crossover is the most significant phase in a genetic algorithm. For each pair of parents to be
mated, a crossover point is chosen at random from within the genes.
Mutation
In certain new offspring formed, some of their genes can be subjected to a mutation with a low
random probability. This implies that some of the bits in the bit string can be flipped.
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
Dept. of ECE, ACSCE Page 18
ARTIFICIAL INTELLIGENCE IN POWER STATIONS 2020-21
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. 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 up to the desired
level, some variations can be done like varying number of hidden layers, varying number of
neurons in each layer.
CHAPTER 4
FUTURE SCOPE OF AI
The world is moving towards digitisation. A lot of us across the world are
working from home and attending meetings via Zoom, Teams, Slack , Yammer, and WhatsApp
video calls. The pandemic has reinforced the value of digitisation in our lives and compelled
Dept. of ECE, ACSCE Page 19
ARTIFICIAL INTELLIGENCE IN POWER STATIONS 2020-21
the uninitiated to quickly learn the new skills for staying relevant and useful for their business.
Keeping in line with this trend, a lot of verticals in the economy are moving to upcoming
technologies like Data Analytics, Artificial Intelligence, Internet of Things, etc. One of these
verticals is the power sector.
Artificial intelligence (AI) has the potential to cut energy waste, lower costs,
and accelerate the use of clean renewable energy sources in power grids globally, along with
improving the operation, maintenance, control, planning and plan execution of power systems.
AI is thus closely tied to renewable, clean as well as affordable energy that is necessary for
development. The power sector has a bright future with the advent of AI-managed smart grids
if implemented well. In addition, AI brings the customer back in focus by connecting power
generators, gird managers and end consumers to be connected and served efficiently and better.
It must also be stated that AI is also employed to reduce the environmental impacts from thermal
power plants, improve their performance and thus play a more efficient role in supplying power
to the grid.
The power sector in developed countries has already started using AI,
Data Analytics, Internet of Things (IoT), and related technologies that allow for communication
between smart grids, smart meters, and computer devices. These technologies help prevent
power mismanagement, inefficiency, and lack of transparency, while increasing the use of
renewable energy sources. As per NITI Ayog’s report National Strategy for Artificial
Intelligence, many industries are proactively investing in cognitive and AI solutions, with
global investments expected to achieve a compound annual growth rate of 50.1% reaching
$57.6 billion in 2021. India can also learn from markets such as the USA, where consumers can
choose their energy providers, based on their household budget, or their consumption patterns.
CONCLUSION
The main feature of power system design and planning is reliability. It 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. Power grid simulation analysis requires AI technology to match it.AI
will continue to develop and play an increasingly important role in the area of fault detection
and diagnosis for power generation industry in the coming future.
REFERENCES
[1] Yong Tang, , Yanhao Huang, Hongzhi Wang, Can Wang, Qiang Guo, and Wei Yao
“Framework for Artificial Intelligence Analysis in Large-scale Power Grids Based on Digital
Simulation” IEEE, Volume 4, December 2018.
[2] Chao Lu , Jiafei Lyu , Liming Zhang , Aicheng Gong , Yipeng Fan , Jiangpeng Yan , And
Xiu Li “Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design
and Current Applications—A Systemic Review” IEEE, Volume 3, October 2020.
[3] Firas Basim Ismail Alnaimi, Haider F. Al-Qrimli, Rahmat Izaizi B. Ismail “Artificial
Intelligence Application in Power Generation Industry: Initial considerations” Researchgate,
Volume 5, March 2016.