Академический Документы
Профессиональный Документы
Культура Документы
ABSTRACT
Recently, due to concerns about the liberalization of electricity supply, deregulation, and global impact on
the environment, securing a reliable power supply has become an important social need worldwide. To
ensure this need is fulfilled, detailed investigations and developments are in progress on power distribution
systems and the monitoring of apparatus. Intelligent system techniques may be of great help in the
implementation of area power system controls. Most of these applications require large quantities of system
information, which can be provided by modern telecommunications and computing technology, but require
new processing techniques able to extract salient information from these large sets of raw data. Importantly,
such large data sets are never error free and often contain various types of uncertainty. Finally, control
actions may be based on operating strategies specified in qualitative form, which need to be translated into
quantitative decisions.
Chapter 1:
Introduction
An electric power system is a network of electrical components used to supply, transmit and use electric
power. Power systems engineering is a subdivision of electrical engineering that deals with the generation,
transmission, distribution and utilisation of electric power and the electrical devices connected to such
systems like generators, motors and transformers.
Commonly, artificial intelligence is known to be the intelligence exhibited by machines and software, for
example, robots and computer programs. The term is generally used for developing systems equipped with
the intellectual features and characteristics of humans, like the ability to think, reason, generalize, distinguish,
learn from past experience or rectify their mistakes. It generally refers to machines or programs with ability
to think on an independent level from their operator to make decisions Power system analysis by
conventional techniques becomes more difficult because of: (i) Complex, versatile and large amount of
information used in calculation, diagnosis and maintenance of systems. Increase in data handling and
processing time due to the vast data generated during such processesbeen accepted, prepare it in two-column
format, including figures and tables
In conventional substations, substation apparatus, such as switchgear and transformer, control, protection and
monitoring equipment is independent of every other device, and connection is based on the signals coming
through the cable. On the other hand, an intelligent substation shares all information on apparatus, control,
protection, measurement and apparatus monitoring equipment through one bus by applying both “digital
technology” and “IT-related technology.”
Moreover, high efficiency and miniaturization can be achieved because the local cubicle contains unified
control/protection and measurement equipment that is one integrated system Since an optical bus shares the
information between the apparatus and equipment, the amount of cable is sharply reduced. Moreover, as
international standards (IEC 61850 and 61375 etc.) are adopted and the system conforms to the telecommunications
standard, equipment specifications can be standardized for different vendors.
All the data from each monitoring and measuring device is transmitted and used for a higher-level
monitoring system via an optical bus. The required data is accessed through the Intranet or the Internet at the
maintenance site of an electricity supply company or a manufacturer and the apparatus can be monitored
from a remote location. The construction, analysis and diagnosis of the database including trend management
and history management also become possible. As a result, signs of abnormalities can be checked out well in
advance, and prompt action can be taken in times of emergency.
Maintenance plans can also be drafted to ensure reliability, by inspecting revision description and parts
management, efficient maintenance planning and reliability maintenance are also realized simultaneously.
Power system controls can be broadly classified into two categories: local and area (regional/system-wide).
The boundary between these two categories is not precise as area controls are often implemented by
optimally adjusting local control parameters and set points. Area controls main characteristic is the need to
process information gathered at various points of the network and to model the behavior of large parts of the
power system.
This type of control is usually not limited to the automatic feedback type but often includes strategies based
on empirical knowledge and human intervention. Local control, on the other hand, is typically implemented
using conventional automatic control rules, such as, PID control, which are believed to offer adequate
performance in most applications. Still, this is not to discount the usefulness of new intelligent
methodologies, such as, fuzzy logic controllers, for local controls.
For convenience, power system higher level controls are classified here as:
• Generation scheduling and automatic control: includes unit commitment, economic dispatch, and automatic
generation control; in the past, well established control methods were used but this situation has been
changing to deal with the new scenario created by the power industry restructuring;
• Voltage control: is mostly of the local type but some systems have already gone to a higher coordinated
secondary control to allow a more effective use of reactive power sources and increase stability margins;
• Preventive security control: has the objective to detect insecure operating points and to suggest corrective
actions; the grand challenges in this area are on-line Dynamic and Voltage Security Assessment (DSA and
VSA);
• Emergency control: manages the problem of controlling the system after a large disturbance; it is an event
driven type of control and includes special protection schemes;
• Restorative control: its main function is to re-energize the system after a major disturbance followed by a
partial or total blackout.
Intelligent system techniques may be of great help in the implementation of area power system controls.
Most of these applications require large quantities of system information, which can be provided by modern
telecommunications and computing technology, but require new processing techniques able to extract salient
information from these large sets of raw data. Importantly, such large data sets are never error free and often
contain various types of uncertainty. Finally, control actions may be based on operating strategies specified
in qualitative form, which need to be translated into quantitative decisions
Fig. 2—Gas
Combined Switchgear Miniaturization by Digital Correspondence Sensor. 550-kV GCS (gas combined
switchgear) is shown as an example.
Due to the rapid progress in today’s information field, applying digital technology and adding IT
function to the protection/control system are possible, to support stable power supply, and improve
maintenance. In Japanese protection/control systems, digitization has made advances since the last half of
the 1980s. Digital technology has unique advantages, namely minimizing maintenance and improving
reliability, and it has speeded up the conversion from individual analog-type to digital-type relays.
Now, however, digitization is not only required for independent single-function equipment, but for
the “systematic operation and employment” of the whole substation. Such systems have greatly improved
efficiency in employment and maintenance using IT. The key phrases to fulfill these needs are as follows:
→ Unification of equipment
Thus, there has been a need for constructing a high efficiency system through system-wide
miniaturization and integration of IT
The amount of operation and maintenance needs to be reduced and detailed information in real
time is required on the digital protection and control unit, during disturbances, or when the operations
manager is notified of changes in the status of local equipment to ensure system stability. Also, there have
been demands for remote operation, and manned-control-station operation to remote unmanned
substations. A conventional digital panel saves and analyzes system information (the current/voltage data)
when faults occur, and the CPU has highly automated observation functions.
However, our system collects the voltage and current data that is saved inside the panel, in the
remote maintenance section, and the results of automatic observation are analyzed and applied
immediately. The system has an interface, which directly acquires the data via the network from the
protection and control units in the substation.
It is normally situated in the processing unit and the various kinds of information and operations
supplied from the remote end, enable us to view progress in the network
Chapter 2;
LITERATURE SURVEY
In the last few years there has been an influx of software that utilize elements of Artificial
Intelligence (AI). Subfields of AI such as Machine Learning, Natural Language Processing, Image
Processing, and Data Mining have become important for many of today’s tech giants. Machine
Learning is actively being used in Google’s predictive search bar, in the Gmail spam filter, in
Netflix’s show suggestions, and in the Cleverbot chat website. Natural Language Processing exists
in Apple’s Siri and Google Voice. Image Processing is necessary for Facebook’s facial recognition
tagging software and in Google’s selfdrivingcars. Data Mining has become a “buzz word” in thesoftware
industry due to the mass amounts of data being collected everyday. Companies like Facebook and Google
collect large amounts of statistics from users every second and need a way to interpret the data they
receive. Artificial Intelligence has already proven to be a useful new tool in today’s technology heavy
culture.
Almost all of these technologies that have begun to implement facets of AI have only been
around for a decade or less. Many of these aspects of AI have proven to be hugely helpful in
industry, but these are merely applications of the technologies being researched. AI has greatly
advanced in the last few years and there have been countless improvements within each subfield.
Alan Turing, the “father” of AI, wrote Computing Machinery and Intelligence in 1950. He
attempted to answer the question “Can machines think?” by developing a type of “Imitation
Game” between two subjects. This game is called the Turing Test and it involves written
communication between two subjects without being able to see, hear, or otherwise sense the other
subject. The first subject, a human, will attempt to figure out if the second subject is a machine or
another human simply from written communique. If the first subject cannot tell, or chooses
incorrectly, then Turing declared that his Turing Test proved that machines can think.
However, there has been some doubt that just because a computer can respond coherently
to a user questions or statement doesn’t mean the computer can actually think. Does the computer
really understand the meaning behind the words, or is it simply regurgitating symbols? This was
somewhat addressed in Turing’s paper, but more formally covered in a paper 30 years later by
John Searle. In 1980, Searle published a thought experiment called The Chinese Room [7] that
addressed the idea that the machine in the Turing Test is simply throwing symbols together without
actually understanding the concepts. The Chinese Room uses the analogy of a native English
speaker with no knowledge of how to speak, write, or read Chinese who is given a couple of sets
of rules in English. These rules correlate input in Chinese to coherent output also in Chinese, even
though the “translator” only speaks English. This question has been the topic of various research
topics in Machine Learning and Natural Language Processing.
There are abundant complications when trying to create an intelligent system. Much of the old or
simple AI is a list of conditions for what reaction to have based on expected stimuli. But this is
arguably not intelligence, and imitating true intelligence requires an understanding of how the input
relates to the output, as well as a large interdisciplinary effort among most AI subfields along with
psychology and linguistics .Many complications involve HumanMachine
Interaction because of the complexity Of human interaction. A lot of the communication that happens
between humans cannot be coded facts a machine could simply recite. There are hundreds of subtle ways
that humans interact with each other that affect communication. Intonations in voices, body language,
responses to various
stimuli, emotions, popular culture facts, and slang all affect how two people might communicate.
This is hard to model in a machine that does not have a basic common sense model already in
place that can learn or make inferences.
Fuzzy Logic, which is modeled after humans’ excellent ability of making approximations
without any real values, poses many complications [11]. Computation, by definition, require
numbers and not words or concepts. Complications arise when trying to imitate human intuition or
common sense. The amount of background information that is taken for granted by humans is immense
and hard to replicate in
machines .There is difficulty in trying to imitate human emotion because of how complex and
subjective they especially when multiple emotions are expressed When using a
Machine Learning approach, the system will process conversations that have been labeled by humans, but
these labels are not always consistent
For convenience, power system higher level controls are classified here as:
• Generation scheduling and automatic control: includes unit commitment, economic dispatch, and automatic
generation control; in the past, well established control methods were used but this situation has been
changing to deal with the new scenario created by the power industry restructuring;
• Voltage control: is mostly of the local type but some systems have already gone to a higher coordinated
secondary control to allow a more effective use of reactive power sources and increase stability margins;
• Preventive security control: has the objective to detect insecure operating points and to suggest corrective
actions; the grand challenges in this area are on-line Dynamic and Voltage Security Assessment (DSA and
VSA);
• Emergency control: manages the problem of controlling the system after a large disturbance; it is an event
driven type of control and includes special protection schemes;
• Restorative control: its main function is to re-energize the system after a major disturbance followed by a
partial or total blackout.
Intelligent system techniques may be of great help in the implementation of area power system controls.
Most of these applications require large quantities of system information, which can be provided by modern
Dept. of E&C, KLS, VDRIT, Haliyal Page 10
Artificial intelligence in power stations
telecommunications and computing technology, but require new processing techniques able to extract salient
information from these large sets of raw data. Importantly, such large data sets are never error free and often
contain various types of uncertainty. Finally, control actions may be based on operating strategies specified
in qualitative form, which need to be translated into quantitative decisions
Building and HVAC&R design professionals are being required to evaluate numerous design alternatives and
properly justify their final conceptual selection. This trend, coupled with the retirement of experienced
designers, increasing complexity of energy price structure, and unwillingness of clients and building owners
to commit additional funds to the design phase itself, can only be satisfied by approaching the conceptual
design process in a more scientific, comprehensive, and rational manner as against the current empirical,
and often ad hoc, approach. Knowledge-based expert systems (KBES) offer a promising solution to this
problem of conceptual design. Numerous KBES studies are available in the ASHRAE and allied literature that
relate to areas such as diagnostics, energy consumption analysis, maintenance, and operation. Relatively
little exists in using knowledge-based systems for HVAC&R conceptual design. This paper consists
essentially of two sections: a background on artificial intelligence (AI) methods and a literature review of
KBES applied to engineering design. The purpose of this literature review is not to cover all areas where
KBES can be applied but to focus on the specific area of conceptual design involving synthesis of HVAC&R
components. A subsequent paper will present and illustrate a new methodology based on a combination of
KBES and algorithmic tools that allows the rational conceptual design and selection of secondary and
primary components of HVAC&R systems.
Chapter 3:
METHODOLOGY
There are three types of major power plants known for the massive electricity generation:
1) Thermal power plants
2) Hydal power plants
3) Nuclear power plants
CHAPTER 3
They have the ability to handle situations of incomplete data and information, corrupt data.
Large dimensionality.
Results are always generated even if the input data are unreasonable.
They are not scalable i.e. once an artificial neural network is trained to do certain task, it is difficult to
extend for other tasks without retraining the neural network.
B. Fuzzy Logic:
Fuzzy logic or Fuzzy systems are logical systems for standardisation and formalisation of approximate
reasoning. It is similar to human decision making with an ability to produce exact and accurate solutions
from certain or even approximate information and data. The reasoning in fuzzy logic is similar to human
reasoning. Fuzzy logic is the way like which human brain works, and we can use this technology in machines
so that they can perform somewhat like humans. 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 minimise 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 provide the conversions from numerical to
symbolic inputs, and back again for the outputs
Simply put, it is a fuzzy code designed to control something, generally mechanical input. They can be in
software or hardware mode and can be used in anything from small circuits to large mainframes. Adaptive
fuzzy controllers learn to control complex process much similar to as we do.
Applications:
(i) Stability analysis and enhancement
(ii) Power system control
(iii) Fault diagnosis
(iv) Security assessment
(v) Load forecasting
(vi) Reactive power planning and its control
(vii) State estimation
B. EXPERT SYSTEMS:
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. Expert systems use the interface mechanism and
knowledge to solve problems which cannot be or difficult to be solved by human skill and intellect.
Advantages:
Disadvantage:
Applications:
Many areas of applications in power systems match the abilities of expert systems like decision making,
archiving knowledge, and solving problems by reasoning, heuristics and judgment. Expert systems are
especially useful for these problems when a large amount of data and information must be processed in a
short period of time.
CHAPTER 4
CHAPTER 4
CONCLUSION
The main feature of power system design and planning is reliability, which was conventionally evaluated
using deterministic methods. Moreover, conventional techniques do not 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.
REFERENCES
[1] Stuart Russell, Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson.
[2] Jeff Heaton, Artificial Intelligence for Humans, Volume 1 : Fundamental Algorithms, Create Space
Independent Publishing Platform.
[4] Keith Frankish, William M. Ramsey, The Cambridge Handbook of Artificial Intelligence, Cambridge
University Press.
[7] George F. Luger, Artificial Intelligence : Structures and Strategies for Complex Problem Solving, Pearson.
[8] Stephen Lucci, Danny Kopec, Artificial Intelligence in the 21st Century, Mercury Learning & Information.
[9] David L. Poole, Alan K. Mackworth, Artificial Intelligence : Foundations of Computational Agents,
Cambridge University Press.
[11] Sandhya Samarasinghe, Neural Networks for Applied Sciences and Engineering, Auerbach Publications.
[12] Martin T Hagan, Howard B Demuth, Mark H Beale, Neural Network Design, Martin Hagan.
[13] Laurene V. Fausett, Fundamentals of Neural Networks : Architectures, Algorithms and Applications,
Pearson.